diff options
| -rw-r--r-- | about/resources.gmi | 206 | ||||
| -rw-r--r-- | gemfeed/2025-06-22-task-samurai.gmi | 24 | ||||
| -rw-r--r-- | gemfeed/2025-06-22-task-samurai.gmi.tpl | 23 | ||||
| -rw-r--r-- | gemfeed/atom.xml | 26 | ||||
| -rw-r--r-- | index.gmi | 2 | ||||
| -rw-r--r-- | uptime-stats.gmi | 2 |
6 files changed, 135 insertions, 148 deletions
diff --git a/about/resources.gmi b/about/resources.gmi index 4fa8d4a5..027eb14f 100644 --- a/about/resources.gmi +++ b/about/resources.gmi @@ -35,105 +35,105 @@ You won't find any links on this site because, over time, the links will break. In random order: -* DNS and BIND; Cricket Liu; O'Reilly -* The Kubernetes Book; Nigel Poulton; Unabridged Audiobook -* Tmux 2: Productive Mouse-free Development; Brain P. Hogan; The Pragmatic Programmers -* The Go Programming Language; Alan A. A. Donovan; Addison-Wesley Professional -* Kubernetes Cookbook; Sameer Naik, Sébastien Goasguen, Jonathan Michaux; O'Reilly +* Effective awk programming; Arnold Robbins; O'Reilly +* Learn You Some Erlang for Great Good; Fred Herbert; No Starch Press +* Site Reliability Engineering; How Google runs production systems; O'Reilly +* Systems Performance Tuning; Gian-Paolo D. Musumeci and others...; O'Reilly * Think Raku (aka Think Perl 6); Laurent Rosenfeld, Allen B. Downey; O'Reilly -* 97 things every SRE should know; Emil Stolarsky, Jaime Woo; O'Reilly -* Developing Games in Java; David Brackeen and others...; New Riders -* The Practise of System and Network Administration; Thomas A. Limoncelli, Christina J. Hogan, Strata R. Chalup; Addison-Wesley Professional Pro Git; Scott Chacon, Ben Straub; Apress -* Effective Java; Joshua Bloch; Addison-Wesley Professional -* 21st Century C: C Tips from the New School; Ben Klemens; O'Reilly -* Concurrency in Go; Katherine Cox-Buday; O'Reilly -* Learn You a Haskell for Great Good!; Miran Lipovaca; No Starch Press +* Pro Puppet; James Turnbull, Jeffrey McCune; Apress +* Clusterbau mit Linux-HA; Michael Schwartzkopff; O'Reilly +* DNS and BIND; Cricket Liu; O'Reilly +* Distributed Systems: Principles and Paradigms; Andrew S. Tanenbaum; Pearson +* Modern Perl; Chromatic ; Onyx Neon Press +* The Docker Book; James Turnbull; Kindle +* Leanring eBPF; Liz Rice; O'Reilly +* The Pragmatic Programmer; David Thomas; Addison-Wesley * Systemprogrammierung in Go; Frank Müller; dpunkt -* Amazon Web Services in Action; Michael Wittig and Andreas Wittig; Manning Publications -* Ultimate Go Notebook; Bill Kennedy -* Terraform Cookbook; Mikael Krief; Packt Publishing +* Programming Ruby 3.3 (5th Edition); Noel Rappin, with Dave Thomas; The Pragmatic Bookshelf * The KCNA (Kubernetes and Cloud Native Associate) Book; Nigel Poulton -* The Pragmatic Programmer; David Thomas; Addison-Wesley -* Pro Puppet; James Turnbull, Jeffrey McCune; Apress -* C++ Programming Language; Bjarne Stroustrup; -* Programming Perl aka "The Camel Book"; Tom Christiansen, brian d foy, Larry Wall & Jon Orwant; O'Reilly -* Object-Oriented Programming with ANSI-C; Axel-Tobias Schreiner +* 21st Century C: C Tips from the New School; Ben Klemens; O'Reilly +* Go Brain Teasers - Exercise Your Mind; Miki Tebeka; The Pragmatic Programmers * Java ist auch eine Insel; Christian Ullenboom; -* 100 Go Mistakes and How to Avoid Them; Teiva Harsanyi; Manning Publications -* Perl New Features; Joshua McAdams, brian d foy; Perl School -* Raku Fundamentals; Moritz Lenz; Apress +* The Practise of System and Network Administration; Thomas A. Limoncelli, Christina J. Hogan, Strata R. Chalup; Addison-Wesley Professional Pro Git; Scott Chacon, Ben Straub; Apress +* Terraform Cookbook; Mikael Krief; Packt Publishing +* Raku Recipes; J.J. Merelo; Apress +* Kubernetes Cookbook; Sameer Naik, Sébastien Goasguen, Jonathan Michaux; O'Reilly +* Object-Oriented Programming with ANSI-C; Axel-Tobias Schreiner * Funktionale Programmierung; Peter Pepper; Springer +* DevOps And Site Reliability Engineering Handbook; Stephen Fleming; Audible +* Perl New Features; Joshua McAdams, brian d foy; Perl School +* Tmux 2: Productive Mouse-free Development; Brain P. Hogan; The Pragmatic Programmers +* Programming Perl aka "The Camel Book"; Tom Christiansen, brian d foy, Larry Wall & Jon Orwant; O'Reilly +* 100 Go Mistakes and How to Avoid Them; Teiva Harsanyi; Manning Publications +* Ultimate Go Notebook; Bill Kennedy +* 97 things every SRE should know; Emil Stolarsky, Jaime Woo; O'Reilly +* Learn You a Haskell for Great Good!; Miran Lipovaca; No Starch Press * Higher Order Perl; Mark Dominus; Morgan Kaufmann -* Go Brain Teasers - Exercise Your Mind; Miki Tebeka; The Pragmatic Programmers -* Hands-on Infrastructure Monitoring with Prometheus; Joel Bastos, Pedro Araujo; Packt -* Modern Perl; Chromatic ; Onyx Neon Press +* Effective Java; Joshua Bloch; Addison-Wesley Professional +* Amazon Web Services in Action; Michael Wittig and Andreas Wittig; Manning Publications +* Polished Ruby Programming; Jeremy Evans; Packt Publishing * The DevOps Handbook; Gene Kim, Jez Humble, Patrick Debois, John Willis; Audible -* DevOps And Site Reliability Engineering Handbook; Stephen Fleming; Audible -* The Docker Book; James Turnbull; Kindle -* Raku Recipes; J.J. Merelo; Apress -* Learn You Some Erlang for Great Good; Fred Herbert; No Starch Press +* The Go Programming Language; Alan A. A. Donovan; Addison-Wesley Professional +* C++ Programming Language; Bjarne Stroustrup; +* Concurrency in Go; Katherine Cox-Buday; O'Reilly +* Hands-on Infrastructure Monitoring with Prometheus; Joel Bastos, Pedro Araujo; Packt +* The Kubernetes Book; Nigel Poulton; Unabridged Audiobook +* Raku Fundamentals; Moritz Lenz; Apress +* Developing Games in Java; David Brackeen and others...; New Riders * Data Science at the Command Line; Jeroen Janssens; O'Reilly -* Leanring eBPF; Liz Rice; O'Reilly -* Effective awk programming; Arnold Robbins; O'Reilly -* Systems Performance Tuning; Gian-Paolo D. Musumeci and others...; O'Reilly -* Distributed Systems: Principles and Paradigms; Andrew S. Tanenbaum; Pearson -* Site Reliability Engineering; How Google runs production systems; O'Reilly -* Clusterbau mit Linux-HA; Michael Schwartzkopff; O'Reilly -* Programming Ruby 3.3 (5th Edition); Noel Rappin, with Dave Thomas; The Pragmatic Bookshelf -* Polished Ruby Programming; Jeremy Evans; Packt Publishing ## Technical references I didn't read them from the beginning to the end, but I am using them to look up things. The books are in random order: -* Relayd and Httpd Mastery; Michael W Lucas -* BPF Performance Tools - Linux System and Application Observability, Brendan Gregg; Addison Wesley -* Implementing Service Level Objectives; Alex Hidalgo; O'Reilly -* Groovy Kurz & Gut; Joerg Staudemeier; O'Reilly * Algorithms; Robert Sedgewick, Kevin Wayne; Addison Wesley +* BPF Performance Tools - Linux System and Application Observability, Brendan Gregg; Addison Wesley * The Linux Programming Interface; Michael Kerrisk; No Starch Press -* Understanding the Linux Kernel; Daniel P. Bovet, Marco Cesati; O'Reilly * Go: Design Patterns for Real-World Projects; Mat Ryer; Packt +* Understanding the Linux Kernel; Daniel P. Bovet, Marco Cesati; O'Reilly +* Relayd and Httpd Mastery; Michael W Lucas +* Implementing Service Level Objectives; Alex Hidalgo; O'Reilly +* Groovy Kurz & Gut; Joerg Staudemeier; O'Reilly ## Self-development and soft-skills books In random order: -* Digital Minimalism; Cal Newport; Portofolio Penguin -* Staff Engineer: Leadership beyond the management track; Will Larson; Audiobook -* Eat That Frog; Brian Tracy -* The Power of Now; Eckhard Tolle; Yellow Kite -* Search Inside Yourself - The Unexpected path to Achieving Success, Happiness (and World Peace); Chade-Meng Tan, Daniel Goleman, Jon Kabat-Zinn; HarperOne -* Eat That Frog!; Brian Tracy; Hodder Paperbacks -* Ultralearning; Scott Young; Thorsons +* Soft Skills; John Sommez; Manning Publications +* Solve for Happy; Mo Gawdat (RE-READ 1ST TIME) * 101 Essays that change the way you think; Brianna Wiest; Audiobook -* The Joy of Missing Out; Christina Crook; New Society Publishers -* Influence without Authority; A. Cohen, D. Bradford; Wiley -* Slow Productivity; Cal Newport; Penguin Random House +* The Bullet Journal Method; Ryder Carroll; Fourth Estate +* Eat That Frog; Brian Tracy +* Who Moved My Cheese?; Dr. Spencer Johnson; Vermilion * Ultralearning; Anna Laurent; Self-published via Amazon -* The Daily Stoic; Ryan Holiday, Stephen Hanselman; Profile Books -* So Good They Can't Ignore You; Cal Newport; Business Plus -* Time Management for System Administrators; Thomas A. Limoncelli; O'Reilly +* Digital Minimalism; Cal Newport; Portofolio Penguin +* Search Inside Yourself - The Unexpected path to Achieving Success, Happiness (and World Peace); Chade-Meng Tan, Daniel Goleman, Jon Kabat-Zinn; HarperOne * Never Split the Difference; Chris Voss, Tahl Raz; Random House Business -* Who Moved My Cheese?; Dr. Spencer Johnson; Vermilion -* Coders at Work - Reflections on the craft of programming, Peter Seibel and Mitchell Dorian et al., Audiobook -* Stop starting, start finishing; Arne Roock; Lean-Kanban University -* Atomic Habits; James Clear; Random House Business +* The Phoenix Project - A Novel About IT, DevOps, and Helping your Business Win; Gene Kim and Kevin Behr; Trade Select * The Complete Software Developer's Career Guide; John Sonmez; Unabridged Audiobook -* Solve for Happy; Mo Gawdat (RE-READ 1ST TIME) -* Psycho-Cybernetics; Maxwell Maltz; Perigee Books -* Getting Things Done; David Allen -* The Bullet Journal Method; Ryder Carroll; Fourth Estate -* Buddah and Einstein walk into a Bar; Guy Joseph Ale, Claire Bloom; Blackstone Publishing +* The Daily Stoic; Ryan Holiday, Stephen Hanselman; Profile Books +* Staff Engineer: Leadership beyond the management track; Will Larson; Audiobook +* The Joy of Missing Out; Christina Crook; New Society Publishers * The Off Switch; Mark Cropley; Virgin Books (RE-READ 1ST TIME) -* The Good Enough Job; Simone Stolzoff; Ebury Edge +* Coders at Work - Reflections on the craft of programming, Peter Seibel and Mitchell Dorian et al., Audiobook +* So Good They Can't Ignore You; Cal Newport; Business Plus +* Time Management for System Administrators; Thomas A. Limoncelli; O'Reilly * Consciousness: A Very Short Introduction; Susan Blackmore; Oxford Uiversity Press -* The Phoenix Project - A Novel About IT, DevOps, and Helping your Business Win; Gene Kim and Kevin Behr; Trade Select -* The Obstacle Is The Way; Ryan Holiday; Profile Books Ltd * Meditation for Mortals, Oliver Burkeman, Audiobook -* Deep Work; Cal Newport; Piatkus +* The Power of Now; Eckhard Tolle; Yellow Kite +* The Good Enough Job; Simone Stolzoff; Ebury Edge +* Influence without Authority; A. Cohen, D. Bradford; Wiley +* Ultralearning; Scott Young; Thorsons +* Getting Things Done; David Allen * The 7 Habits Of Highly Effective People; Stephen R. Covey; Simon & Schuster UK -* Soft Skills; John Sommez; Manning Publications +* Eat That Frog!; Brian Tracy; Hodder Paperbacks +* Stop starting, start finishing; Arne Roock; Lean-Kanban University +* Buddah and Einstein walk into a Bar; Guy Joseph Ale, Claire Bloom; Blackstone Publishing +* Atomic Habits; James Clear; Random House Business +* Deep Work; Cal Newport; Piatkus +* The Obstacle Is The Way; Ryan Holiday; Profile Books Ltd +* Psycho-Cybernetics; Maxwell Maltz; Perigee Books +* Slow Productivity; Cal Newport; Penguin Random House => ../notes/index.gmi Here are notes of mine for some of the books @@ -141,30 +141,30 @@ In random order: Some of these were in-person with exams; others were online learning lectures only. In random order: -* Cloud Operations on AWS - Learn how to configure, deploy, maintain, and troubleshoot your AWS environments; 3-day online live training with labs; Amazon -* MySQL Deep Dive Workshop; 2-day on-site training -* The Ultimate Kubernetes Bootcamp; School of Devops; O'Reilly Online +* AWS Immersion Day; Amazon; 1-day interactive online training * Algorithms Video Lectures; Robert Sedgewick; O'Reilly Online -* Protocol buffers; O'Reilly Online -* The Well-Grounded Rubyist Video Edition; David. A. Black; O'Reilly Online -* Ultimate Go Programming; Bill Kennedy; O'Reilly Online * F5 Loadbalancers Training; 2-day on-site training; F5, Inc. * Functional programming lecture; Remote University of Hagen +* Protocol buffers; O'Reilly Online +* The Ultimate Kubernetes Bootcamp; School of Devops; O'Reilly Online +* Apache Tomcat Best Practises; 3-day on-site training +* Structure and Interpretation of Computer Programs; Harold Abelson and more...; * Linux Security and Isolation APIs Training; Michael Kerrisk; 3-day on-site training +* The Well-Grounded Rubyist Video Edition; David. A. Black; O'Reilly Online * Scripting Vim; Damian Conway; O'Reilly Online -* Structure and Interpretation of Computer Programs; Harold Abelson and more...; -* Developing IaC with Terraform (with Live Lessons); O'Reilly Online -* Apache Tomcat Best Practises; 3-day on-site training * Red Hat Certified System Administrator; Course + certification (Although I had the option, I decided not to take the next course as it is more effective to self learn what I need) -* AWS Immersion Day; Amazon; 1-day interactive online training +* Ultimate Go Programming; Bill Kennedy; O'Reilly Online +* Cloud Operations on AWS - Learn how to configure, deploy, maintain, and troubleshoot your AWS environments; 3-day online live training with labs; Amazon +* Developing IaC with Terraform (with Live Lessons); O'Reilly Online +* MySQL Deep Dive Workshop; 2-day on-site training ## Technical guides These are not whole books, but guides (smaller or larger) which I found very useful. in random order: -* How CPUs work at https://cpu.land -* Advanced Bash-Scripting Guide * Raku Guide at https://raku.guide +* Advanced Bash-Scripting Guide +* How CPUs work at https://cpu.land ## Podcasts @@ -172,56 +172,56 @@ These are not whole books, but guides (smaller or larger) which I found very use In random order: -* Backend Banter +* The ProdCast (Google SRE Podcast) * The Pragmatic Engineer Podcast -* Deep Questions with Cal Newport -* BSD Now [BSD] -* Fork Around And Find Out -* The Changelog Podcast(s) * Fallthrough [Golang] -* The ProdCast (Google SRE Podcast) -* Modern Mentor +* BSD Now [BSD] +* Cup o' Go [Golang] * Maintainable -* Dev Interrupted * Hidden Brain -* Cup o' Go [Golang] +* Dev Interrupted +* Deep Questions with Cal Newport +* Modern Mentor +* Fork Around And Find Out +* The Changelog Podcast(s) +* Backend Banter ### Podcasts I liked I liked them but am not listening to them anymore. The podcasts have either "finished" (no more episodes) or I stopped listening to them due to time constraints or a shift in my interests. -* Go Time (predecessor of fallthrough) -* FLOSS weekly +* CRE: Chaosradio Express [german] * Java Pub House * Modern Mentor +* FLOSS weekly +* Go Time (predecessor of fallthrough) * Ship It (predecessor of Fork Around And Find Out) -* CRE: Chaosradio Express [german] ## Newsletters I like This is a mix of tech and non-tech newsletters I am subscribed to. In random order: -* byteSizeGo -* Changelog News -* The Imperfectionist * The Pragmatic Engineer -* Register Spill -* Ruby Weekly +* Andreas Brandhorst Newsletter (Sci-Fi author) +* The Imperfectionist * VK Newsletter +* Changelog News +* byteSizeGo * Golang Weekly -* Applied Go Weekly Newsletter +* Ruby Weekly * Monospace Mentor * The Valuable Dev -* Andreas Brandhorst Newsletter (Sci-Fi author) +* Applied Go Weekly Newsletter +* Register Spill ## Magazines I like(d) This is a mix of tech I like(d). I may not be a current subscriber, but now and then, I buy an issue. In random order: -* Linux Magazine +* Linux User * LWN (online only) * freeX (not published anymore) -* Linux User +* Linux Magazine # Formal education diff --git a/gemfeed/2025-06-22-task-samurai.gmi b/gemfeed/2025-06-22-task-samurai.gmi index 211d2287..32ab7f89 100644 --- a/gemfeed/2025-06-22-task-samurai.gmi +++ b/gemfeed/2025-06-22-task-samurai.gmi @@ -12,6 +12,7 @@ * ⇢ ⇢ ⇢ How it works * ⇢ ⇢ Where and how to get it * ⇢ ⇢ Lessons learned from building Task Samurai with agentic coding +* ⇢ ⇢ ⇢ Developer workflow * ⇢ ⇢ ⇢ How it went down * ⇢ ⇢ ⇢ What went wrong * ⇢ ⇢ ⇢ Patterns that helped @@ -53,13 +54,13 @@ And follow the `README.md`! ## Lessons learned from building Task Samurai with agentic coding -If you've ever wanted to supercharge your dev speed—or just throw a fireworks display in your terminal—here's a peek behind the scenes of building Task Samurai. This terminal interface for Taskwarrior was developed entirely through agentic coding by me, leveraging OpenAI Codex to do all the heavy lifting (and sometimes some cleanup afterwards). The project name might be snappy, but it was the iterative, semi-automated workflow that made the impact. +### Developer workflow -As a side note, I was trying out OpenAI Codex because I regularly run out of Claude Code CLI (another agentic coding tool I am trying out currently) credits (it still happens!), but Codex was still available to me. So, I seized the opportunity to push agentic coding a bit more. +I was trying out OpenAI Codex because I regularly run out of Claude Code CLI (another agentic coding tool I am trying out currently) credits (it still happens!), but Codex was still available to me. So, I seized the opportunity to push agentic coding a bit more using another platform. I didn't really love the web UI you have to use for Codex, as I usually live in the terminal. But this is all I have for Codex for now, and I thought I'd give it a try regardless. The web UI is simple and pretty straightforward. There's also a Codex CLI one could use directly in the terminal, but I didn't get it working. I will try again soon. -For every task given to Codex, it spins up its own container. From there, you can drill down and watch what it is doing. At the end, the result (in the form of a code diff) will be presented. From there, you can make suggestions about what else to change in the codebase. What I found inconvenient is that for every additional change, there's an overhead because Codex has to spin up a container again, which adds extra delay. That could be eliminated by setting up predefined custom containers, but that feature still seems to be somewhat limited. +For every task given to Codex, it spins up its own container. From there, you can drill down and watch what it is doing. At the end, the result (in the form of a code diff) will be presented. From there, you can make suggestions about what else to change in the codebase. What I found inconvenient is that for every additional change, there's an overhead because Codex has to spin up a container and bootstrap the entire development environment again, which adds extra delay. That could be eliminated by setting up predefined custom containers, but that feature still seems somewhat limited. Once satisfied, you can ask Codex to create a GitHub PR; from there, you can merge it and then pull it to your local laptop or workstation to test the changes again. I found myself looping a lot around the Codex UI, GitHub PRs, and local checkouts. @@ -81,7 +82,7 @@ It's worth noting that I worked on it in the evenings when I had some free time, Going agentic isn't all smooth sailing. Here are the hiccups I ran into, plus a few hard-earned lessons: * Merge Floods: Every minor feature or fix existed on its branch, so merging was a constant process. It kept progress flowing but also drowned the committed history in noise and the occasional conflict. I found this to be an issue with OpenAI's Codex in particular. Not so much with other agentic coding tools like Claude Code CLI (not covered in this blog post.) -* Fixes on Fixes: Features like "fireworks on exit" had chains of "fix exit," "fix cell selection," etc. Sometimes, new additions introduced bugs that needed rapid patching. +* Fixes on fixes: Features like "fireworks on exit" had chains of "fix exit," "fix cell selection," etc. Sometimes, new additions introduced bugs that needed rapid patching. ### Patterns that helped @@ -95,15 +96,12 @@ Maybe a better approach would have been to design the whole application from scr ### What I learned using agentic coding -Stepping into agentic coding with Codex as my "pair programmer" was a genuine shift. I learned a ton—not just about automating code generation, but also about how you have to tightly steer, guide, and audit every line as things move at breakneck speed. I must admit, I sometimes lost track of what all the generated code was actually doing. But as the features seemed to work after a few iterations, I was satisfied. - -Discussing requirements with Codex forced me to clarify features and spot logical pitfalls earlier. All those fast iterations meant I was constantly coaxing more helpful, less ambiguous code out of the model—making me rethink how to break features into clear, testable steps. I now see agentic coding not just as a productivity tool but also as a learning accelerator. +Stepping into agentic coding with Codex as my "pair programmer" was a genuine shift. I learned a lot—not just about automating code generation, but also about how you have to tightly steer, guide, and audit every line as things move at breakneck speed. I must admit, I sometimes lost track of what all the generated code was actually doing. But as the features seemed to work after a few iterations, I was satisfied—which is a bit concerning. Imagine if I approved a PR for a production-grade deployment without fully understanding what it was doing (and not a toy project like in this post). +Discussing requirements with Codex forced me to clarify features and spot logical pitfalls earlier. All those fast iterations meant I was constantly coaxing more helpful, less ambiguous code out of the model—making me rethink how to break features into clear, testable steps. ### How much time did I save? -Here's the million-dollar (or many hours saved) question: Did it buy me speed? - -Let's do some back-of-the-envelope math: +Did it buy me speed? Let's do some back-of-the-envelope math: * Say each commit takes Codex 5 minutes to generate, and you need to review/guide 179 commits = about _6 hours of active development_. * If you coded it all yourself, including all the bug fixes, features, design, and documentation, you might spend _10–20 hours_. @@ -111,13 +109,11 @@ Let's do some back-of-the-envelope math: ## Conclusion -Building Task Samurai with agentic coding was a wild ride—rapid feature growth, plenty of churns, countless fast fixes, and more merge commits I'd expected. The big lessons? Keep the iterations short (or maybe in my next experiment, much larger, with better and more complete design before generating a single line of code), keep tests and documentation concise, and review and refine for final polish at the end. Even with the bumps along the way, shipping a polished terminal UI in days instead of weeks is a testament to the raw power (and some hazards) of agentic development. +Building Task Samurai with agentic coding was a wild ride—rapid feature growth, plenty of churns, countless fast fixes, and more merge commits I'd expected. Keep the iterations short (or maybe in my next experiment, much larger, with better and more complete design before generating a single line of code), keep tests and documentation concise, and review and refine for final polish at the end. Even with the bumps along the way, shipping a polished terminal UI in days instead of weeks is a testament to the raw power (and some hazards) of agentic development. Am I an agentic coding expert now? I don't think so. There are still many things to learn, and the landscape is constantly evolving. -While working on Task Samurai, there were times I genuinely missed manual coding and the satisfaction that comes from writing every line yourself, debugging issues through sheer logic, and crafting solutions from scratch. However, this is the direction in which the industry seems to be shifting, unfortunately. If applied correctly, AI will boost performance, and if you don't use AI, your next performance review may be awkward. - -If you're considering going agentic, be prepared for a sprint, keep your toolkit sharp, and be ready to learn a lot along the way. +While working on Task Samurai, there were times I genuinely missed manual coding and the satisfaction that comes from writing every line yourself, debugging issues manually, and crafting solutions from scratch. However, this is the direction in which the industry seems to be shifting, unfortunately. If applied correctly, AI will boost performance, and if you don't use AI, your next performance review may be awkward. Personally, I am not sure whether I like where the industry is going with agentic coding. I love "traditional" coding, and with agentic coding you operate at a higher level and don't interact directly with code as often, which I would miss. I think that in the future, designing, reviewing, and being able to read and understand code will be more important than writing code by hand. diff --git a/gemfeed/2025-06-22-task-samurai.gmi.tpl b/gemfeed/2025-06-22-task-samurai.gmi.tpl index 3ae6e174..57f7fe2f 100644 --- a/gemfeed/2025-06-22-task-samurai.gmi.tpl +++ b/gemfeed/2025-06-22-task-samurai.gmi.tpl @@ -40,13 +40,13 @@ And follow the `README.md`! ## Lessons learned from building Task Samurai with agentic coding -If you've ever wanted to supercharge your dev speed—or just throw a fireworks display in your terminal—here's a peek behind the scenes of building Task Samurai. This terminal interface for Taskwarrior was developed entirely through agentic coding by me, leveraging OpenAI Codex to do all the heavy lifting (and sometimes some cleanup afterwards). The project name might be snappy, but it was the iterative, semi-automated workflow that made the impact. +### Developer workflow -As a side note, I was trying out OpenAI Codex because I regularly run out of Claude Code CLI (another agentic coding tool I am trying out currently) credits (it still happens!), but Codex was still available to me. So, I seized the opportunity to push agentic coding a bit more. +I was trying out OpenAI Codex because I regularly run out of Claude Code CLI (another agentic coding tool I am trying out currently) credits (it still happens!), but Codex was still available to me. So, I seized the opportunity to push agentic coding a bit more using another platform. I didn't really love the web UI you have to use for Codex, as I usually live in the terminal. But this is all I have for Codex for now, and I thought I'd give it a try regardless. The web UI is simple and pretty straightforward. There's also a Codex CLI one could use directly in the terminal, but I didn't get it working. I will try again soon. -For every task given to Codex, it spins up its own container. From there, you can drill down and watch what it is doing. At the end, the result (in the form of a code diff) will be presented. From there, you can make suggestions about what else to change in the codebase. What I found inconvenient is that for every additional change, there's an overhead because Codex has to spin up a container again, which adds extra delay. That could be eliminated by setting up predefined custom containers, but that feature still seems to be somewhat limited. +For every task given to Codex, it spins up its own container. From there, you can drill down and watch what it is doing. At the end, the result (in the form of a code diff) will be presented. From there, you can make suggestions about what else to change in the codebase. What I found inconvenient is that for every additional change, there's an overhead because Codex has to spin up a container and bootstrap the entire development environment again, which adds extra delay. That could be eliminated by setting up predefined custom containers, but that feature still seems somewhat limited. Once satisfied, you can ask Codex to create a GitHub PR; from there, you can merge it and then pull it to your local laptop or workstation to test the changes again. I found myself looping a lot around the Codex UI, GitHub PRs, and local checkouts. @@ -68,7 +68,7 @@ It's worth noting that I worked on it in the evenings when I had some free time, Going agentic isn't all smooth sailing. Here are the hiccups I ran into, plus a few hard-earned lessons: * Merge Floods: Every minor feature or fix existed on its branch, so merging was a constant process. It kept progress flowing but also drowned the committed history in noise and the occasional conflict. I found this to be an issue with OpenAI's Codex in particular. Not so much with other agentic coding tools like Claude Code CLI (not covered in this blog post.) -* Fixes on Fixes: Features like "fireworks on exit" had chains of "fix exit," "fix cell selection," etc. Sometimes, new additions introduced bugs that needed rapid patching. +* Fixes on fixes: Features like "fireworks on exit" had chains of "fix exit," "fix cell selection," etc. Sometimes, new additions introduced bugs that needed rapid patching. ### Patterns that helped @@ -82,15 +82,12 @@ Maybe a better approach would have been to design the whole application from scr ### What I learned using agentic coding -Stepping into agentic coding with Codex as my "pair programmer" was a genuine shift. I learned a ton—not just about automating code generation, but also about how you have to tightly steer, guide, and audit every line as things move at breakneck speed. I must admit, I sometimes lost track of what all the generated code was actually doing. But as the features seemed to work after a few iterations, I was satisfied. - -Discussing requirements with Codex forced me to clarify features and spot logical pitfalls earlier. All those fast iterations meant I was constantly coaxing more helpful, less ambiguous code out of the model—making me rethink how to break features into clear, testable steps. I now see agentic coding not just as a productivity tool but also as a learning accelerator. +Stepping into agentic coding with Codex as my "pair programmer" was a genuine shift. I learned a lot—not just about automating code generation, but also about how you have to tightly steer, guide, and audit every line as things move at breakneck speed. I must admit, I sometimes lost track of what all the generated code was actually doing. But as the features seemed to work after a few iterations, I was satisfied—which is a bit concerning. Imagine if I approved a PR for a production-grade deployment without fully understanding what it was doing (and not a toy project like in this post). +Discussing requirements with Codex forced me to clarify features and spot logical pitfalls earlier. All those fast iterations meant I was constantly coaxing more helpful, less ambiguous code out of the model—making me rethink how to break features into clear, testable steps. ### How much time did I save? -Here's the million-dollar (or many hours saved) question: Did it buy me speed? - -Let's do some back-of-the-envelope math: +Did it buy me speed? Let's do some back-of-the-envelope math: * Say each commit takes Codex 5 minutes to generate, and you need to review/guide 179 commits = about _6 hours of active development_. * If you coded it all yourself, including all the bug fixes, features, design, and documentation, you might spend _10–20 hours_. @@ -98,13 +95,11 @@ Let's do some back-of-the-envelope math: ## Conclusion -Building Task Samurai with agentic coding was a wild ride—rapid feature growth, plenty of churns, countless fast fixes, and more merge commits I'd expected. The big lessons? Keep the iterations short (or maybe in my next experiment, much larger, with better and more complete design before generating a single line of code), keep tests and documentation concise, and review and refine for final polish at the end. Even with the bumps along the way, shipping a polished terminal UI in days instead of weeks is a testament to the raw power (and some hazards) of agentic development. +Building Task Samurai with agentic coding was a wild ride—rapid feature growth, plenty of churns, countless fast fixes, and more merge commits I'd expected. Keep the iterations short (or maybe in my next experiment, much larger, with better and more complete design before generating a single line of code), keep tests and documentation concise, and review and refine for final polish at the end. Even with the bumps along the way, shipping a polished terminal UI in days instead of weeks is a testament to the raw power (and some hazards) of agentic development. Am I an agentic coding expert now? I don't think so. There are still many things to learn, and the landscape is constantly evolving. -While working on Task Samurai, there were times I genuinely missed manual coding and the satisfaction that comes from writing every line yourself, debugging issues through sheer logic, and crafting solutions from scratch. However, this is the direction in which the industry seems to be shifting, unfortunately. If applied correctly, AI will boost performance, and if you don't use AI, your next performance review may be awkward. - -If you're considering going agentic, be prepared for a sprint, keep your toolkit sharp, and be ready to learn a lot along the way. +While working on Task Samurai, there were times I genuinely missed manual coding and the satisfaction that comes from writing every line yourself, debugging issues manually, and crafting solutions from scratch. However, this is the direction in which the industry seems to be shifting, unfortunately. If applied correctly, AI will boost performance, and if you don't use AI, your next performance review may be awkward. Personally, I am not sure whether I like where the industry is going with agentic coding. I love "traditional" coding, and with agentic coding you operate at a higher level and don't interact directly with code as often, which I would miss. I think that in the future, designing, reviewing, and being able to read and understand code will be more important than writing code by hand. diff --git a/gemfeed/atom.xml b/gemfeed/atom.xml index f1d42901..174f2676 100644 --- a/gemfeed/atom.xml +++ b/gemfeed/atom.xml @@ -1,6 +1,6 @@ <?xml version="1.0" encoding="utf-8"?> <feed xmlns="http://www.w3.org/2005/Atom"> - <updated>2025-06-22T23:02:51+03:00</updated> + <updated>2025-06-23T00:56:54+03:00</updated> <title>foo.zone feed</title> <subtitle>To be in the .zone!</subtitle> <link href="gemini://foo.zone/gemfeed/atom.xml" rel="self" /> @@ -33,6 +33,7 @@ <li>⇢ ⇢ <a href='#how-it-works'>How it works</a></li> <li>⇢ <a href='#where-and-how-to-get-it'>Where and how to get it</a></li> <li>⇢ <a href='#lessons-learned-from-building-task-samurai-with-agentic-coding'>Lessons learned from building Task Samurai with agentic coding</a></li> +<li>⇢ ⇢ <a href='#developer-workflow'>Developer workflow</a></li> <li>⇢ ⇢ <a href='#how-it-went-down'>How it went down</a></li> <li>⇢ ⇢ <a href='#what-went-wrong'>What went wrong</a></li> <li>⇢ ⇢ <a href='#patterns-that-helped'>Patterns that helped</a></li> @@ -75,13 +76,13 @@ <br /> <h2 style='display: inline' id='lessons-learned-from-building-task-samurai-with-agentic-coding'>Lessons learned from building Task Samurai with agentic coding</h2><br /> <br /> -<span>If you've ever wanted to supercharge your dev speed—or just throw a fireworks display in your terminal—here's a peek behind the scenes of building Task Samurai. This terminal interface for Taskwarrior was developed entirely through agentic coding by me, leveraging OpenAI Codex to do all the heavy lifting (and sometimes some cleanup afterwards). The project name might be snappy, but it was the iterative, semi-automated workflow that made the impact.</span><br /> +<h3 style='display: inline' id='developer-workflow'>Developer workflow</h3><br /> <br /> -<span>As a side note, I was trying out OpenAI Codex because I regularly run out of Claude Code CLI (another agentic coding tool I am trying out currently) credits (it still happens!), but Codex was still available to me. So, I seized the opportunity to push agentic coding a bit more.</span><br /> +<span>I was trying out OpenAI Codex because I regularly run out of Claude Code CLI (another agentic coding tool I am trying out currently) credits (it still happens!), but Codex was still available to me. So, I seized the opportunity to push agentic coding a bit more using another platform.</span><br /> <br /> <span>I didn't really love the web UI you have to use for Codex, as I usually live in the terminal. But this is all I have for Codex for now, and I thought I'd give it a try regardless. The web UI is simple and pretty straightforward. There's also a Codex CLI one could use directly in the terminal, but I didn't get it working. I will try again soon.</span><br /> <br /> -<span>For every task given to Codex, it spins up its own container. From there, you can drill down and watch what it is doing. At the end, the result (in the form of a code diff) will be presented. From there, you can make suggestions about what else to change in the codebase. What I found inconvenient is that for every additional change, there's an overhead because Codex has to spin up a container again, which adds extra delay. That could be eliminated by setting up predefined custom containers, but that feature still seems to be somewhat limited.</span><br /> +<span>For every task given to Codex, it spins up its own container. From there, you can drill down and watch what it is doing. At the end, the result (in the form of a code diff) will be presented. From there, you can make suggestions about what else to change in the codebase. What I found inconvenient is that for every additional change, there's an overhead because Codex has to spin up a container and bootstrap the entire development environment again, which adds extra delay. That could be eliminated by setting up predefined custom containers, but that feature still seems somewhat limited.</span><br /> <br /> <span>Once satisfied, you can ask Codex to create a GitHub PR; from there, you can merge it and then pull it to your local laptop or workstation to test the changes again. I found myself looping a lot around the Codex UI, GitHub PRs, and local checkouts.</span><br /> <br /> @@ -105,7 +106,7 @@ <br /> <ul> <li>Merge Floods: Every minor feature or fix existed on its branch, so merging was a constant process. It kept progress flowing but also drowned the committed history in noise and the occasional conflict. I found this to be an issue with OpenAI's Codex in particular. Not so much with other agentic coding tools like Claude Code CLI (not covered in this blog post.)</li> -<li>Fixes on Fixes: Features like "fireworks on exit" had chains of "fix exit," "fix cell selection," etc. Sometimes, new additions introduced bugs that needed rapid patching.</li> +<li>Fixes on fixes: Features like "fireworks on exit" had chains of "fix exit," "fix cell selection," etc. Sometimes, new additions introduced bugs that needed rapid patching.</li> </ul><br /> <h3 style='display: inline' id='patterns-that-helped'>Patterns that helped</h3><br /> <br /> @@ -120,15 +121,12 @@ <br /> <h3 style='display: inline' id='what-i-learned-using-agentic-coding'>What I learned using agentic coding</h3><br /> <br /> -<span>Stepping into agentic coding with Codex as my "pair programmer" was a genuine shift. I learned a ton—not just about automating code generation, but also about how you have to tightly steer, guide, and audit every line as things move at breakneck speed. I must admit, I sometimes lost track of what all the generated code was actually doing. But as the features seemed to work after a few iterations, I was satisfied. </span><br /> -<br /> -<span>Discussing requirements with Codex forced me to clarify features and spot logical pitfalls earlier. All those fast iterations meant I was constantly coaxing more helpful, less ambiguous code out of the model—making me rethink how to break features into clear, testable steps. I now see agentic coding not just as a productivity tool but also as a learning accelerator.</span><br /> +<span>Stepping into agentic coding with Codex as my "pair programmer" was a genuine shift. I learned a lot—not just about automating code generation, but also about how you have to tightly steer, guide, and audit every line as things move at breakneck speed. I must admit, I sometimes lost track of what all the generated code was actually doing. But as the features seemed to work after a few iterations, I was satisfied—which is a bit concerning. Imagine if I approved a PR for a production-grade deployment without fully understanding what it was doing (and not a toy project like in this post).</span><br /> <br /> +<span>Discussing requirements with Codex forced me to clarify features and spot logical pitfalls earlier. All those fast iterations meant I was constantly coaxing more helpful, less ambiguous code out of the model—making me rethink how to break features into clear, testable steps.</span><br /> <h3 style='display: inline' id='how-much-time-did-i-save'>How much time did I save?</h3><br /> <br /> -<span>Here's the million-dollar (or many hours saved) question: Did it buy me speed?</span><br /> -<br /> -<span>Let's do some back-of-the-envelope math:</span><br /> +<span>Did it buy me speed? Let's do some back-of-the-envelope math:</span><br /> <br /> <ul> <li>Say each commit takes Codex 5 minutes to generate, and you need to review/guide 179 commits = about _6 hours of active development_.</li> @@ -137,13 +135,11 @@ </ul><br /> <h2 style='display: inline' id='conclusion'>Conclusion</h2><br /> <br /> -<span>Building Task Samurai with agentic coding was a wild ride—rapid feature growth, plenty of churns, countless fast fixes, and more merge commits I'd expected. The big lessons? Keep the iterations short (or maybe in my next experiment, much larger, with better and more complete design before generating a single line of code), keep tests and documentation concise, and review and refine for final polish at the end. Even with the bumps along the way, shipping a polished terminal UI in days instead of weeks is a testament to the raw power (and some hazards) of agentic development.</span><br /> +<span>Building Task Samurai with agentic coding was a wild ride—rapid feature growth, plenty of churns, countless fast fixes, and more merge commits I'd expected. Keep the iterations short (or maybe in my next experiment, much larger, with better and more complete design before generating a single line of code), keep tests and documentation concise, and review and refine for final polish at the end. Even with the bumps along the way, shipping a polished terminal UI in days instead of weeks is a testament to the raw power (and some hazards) of agentic development.</span><br /> <br /> <span>Am I an agentic coding expert now? I don't think so. There are still many things to learn, and the landscape is constantly evolving.</span><br /> <br /> -<span>While working on Task Samurai, there were times I genuinely missed manual coding and the satisfaction that comes from writing every line yourself, debugging issues through sheer logic, and crafting solutions from scratch. However, this is the direction in which the industry seems to be shifting, unfortunately. If applied correctly, AI will boost performance, and if you don't use AI, your next performance review may be awkward.</span><br /> -<br /> -<span>If you're considering going agentic, be prepared for a sprint, keep your toolkit sharp, and be ready to learn a lot along the way.</span><br /> +<span>While working on Task Samurai, there were times I genuinely missed manual coding and the satisfaction that comes from writing every line yourself, debugging issues manually, and crafting solutions from scratch. However, this is the direction in which the industry seems to be shifting, unfortunately. If applied correctly, AI will boost performance, and if you don't use AI, your next performance review may be awkward.</span><br /> <br /> <span>Personally, I am not sure whether I like where the industry is going with agentic coding. I love "traditional" coding, and with agentic coding you operate at a higher level and don't interact directly with code as often, which I would miss. I think that in the future, designing, reviewing, and being able to read and understand code will be more important than writing code by hand.</span><br /> <br /> @@ -1,6 +1,6 @@ # Hello! -> This site was generated at 2025-06-22T23:08:11+03:00 by `Gemtexter` +> This site was generated at 2025-06-23T00:56:54+03:00 by `Gemtexter` Welcome to the ... diff --git a/uptime-stats.gmi b/uptime-stats.gmi index 8cba511f..0d75434b 100644 --- a/uptime-stats.gmi +++ b/uptime-stats.gmi @@ -1,6 +1,6 @@ # My machine uptime stats -> This site was last updated at 2025-06-22T23:08:11+03:00 +> This site was last updated at 2025-06-23T00:56:54+03:00 The following stats were collected via `uptimed` on all of my personal computers over many years and the output was generated by `guprecords`, the global uptime records stats analyser of mine. |