This video is well worth watching. It's a balanced, real-world look at the effectiveness of AI (across many disciplines, not just software dev) and its impact on work, substantiated by a well-designed study that actually compares UI to human workers.
www.youtube.com/watc...
2/2
Caricaturista de India...
Great 20’ talk by @dexhorthy.bsky.social on Context Engineering for coding agents: avoiding the “dumb zone”, Research→Plan→Implement workflow, and sub-agents for brownfield codebases. Highly recommend if you’re struggling with AI on brownfield/legacy code bases. 🤩
youtu.be/rmvDxxNubIg?...
Mi compañero Fran Reyes @fran-reyes.bsky.social y yo estamos buscando equipos con los que colaborar.
Lo que más nos gusta es hacer coaching técnico, formación y/o mentoring, pero también podríamos aportarte valor de otras maneras.
Hablemos.
Contacta con nosotros en contact@codesai.com
I keep seeing lots of people saying "LLMs are like compilers/assemblers for prompts"
Noooooooooo
Noooooooooooooooooooooooooooo
LLMs are not compilers, and they're not assemblers. Determinism is a key aspect to assemblers and compilers.
And they *certainly* can't be part of a reproducible pipeline
A non-deterministic product may produce different outputs with each use, which makes the traditional means of testing and debugging less useful.
"It works well on my machine" will become even more of a joke than it is right now.
I'm so thankful for AI...finally developers are no longer chanting "Microservices" constantly.
🗞️ Para este #openspace, nos hemos juntado con las comunidades Women Techmakers Barcelona, Ladies in Product y Lean Agile Barcelona para conseguir que sea más que especial.
¡Ven y que no te lo cuenten!
📅 14/3 | ⏰ 10:00-14:00
📍42 Barcelona | 🎟️ Gratis (aforo limitado)
eventbrite.es/e/1983993467...
They're all going to The Hague
The “Trust the Tests” pattern is one of the important places where generative coding meets #softwareengineering systems thinking: how do you know whether you want the code that the genie created? www.patreon.com/posts/152229...
this post is actually evergreen, doesn't matter the tech
I started a new chapter of my Agentic Engineering Patternw guide about anti-patterns - things NOT to do
So far I only have one: Inflicting unreviewed code on collaborators, aka dumping a thousand line PR without even making sure it works first simonwillison.net/guides/agent...
what's fascinating is seeing AI use proponents actually re-invent labour unions from first principles, and suggesting that workers form syndicates to work fewer hours per week for the same output in order to capture the value that is being created. steve-yegge.medium.com/the-ai-vampi...
maybe instead of pivoting to AI, GitHub should pivot to showing the fucking code in my fucking repos
This is a good post even if you think he’s off the deep end after gas town steve-yegge.medium.com/the-ai-vampi...
If the collective comprehension and articulation of a concept is flawed, and our individual comprehension is flawed, then we cannot expect AI to be any less flawed than the material it has to work with.
This seems to be at the heart of much of the debate in AI augmented coding.
Studies find AI helps developers release more software—while logging longer hours and fixing problems after the code goes live
A print copy of Designing Data-Intensive Applications, 2nd edition
Just received my author copies of the second edition of DDIA! After years of seeing it only on-screen, holding the final print book in hand is very special. @chris.blue
Turns out lowering bills, protecting the NHS and rebuilding our public services is really popular.
This is just the beginning - people are seeing through the attacks and demanding something better.
And we're making hope normal again - together.
news.sky.com/story/greens...
Only in silence the word,
Only in dark the light,
Only in dying life:
Bright the hawk's flight
On the empty sky.
"Across multiple coding agents and LLMs, we find that context files tend to reduce task success rates compared to providing no repository context, while also increasing inference cost by over 20%"
I've suspected this all along.
arxiv.org/abs/2602.11988
I hate the re-soloing of development. We were so close to learning social skills, creating community, encouraging creativity & purpose, & applying empathy. Easier to manage if each of us is so busy with our genieswarms that we don't have time to talk & reflect.
We live in capitalism. Its power seems inescapable. So did the divine right of kings. Any human power can be resisted and changed by human beings. Resistance and change often begin in art, and very often in our art, the art of words.
I honestly hadn't noticed the Claude outage, as the models I run locally on my computer are working just fine. www.sicpers.info/2026/01/conf...
Relevant Mutants in a Flash
codesai.com/posts/2026/0...
People say “you’re Batman and AI is Robin”.
I don’t buy it.
It’s Lilo and Stitch: powerful, brilliant, and fully capable of wrecking the house in a sec if you get distracted!
El 9, 10, 11, 16 y 17 de marzo de 10.00 a 14.00 hora peninsular haremos una edición en abierto en C# del curso Code Smells & Refactoring 🚀https://codesai.com/cursos/refactoring/
50% de descuento para particulares de colectivos poco representados.
No te lo pierdas! Escribe a contact@codesai.com 💌
