Sonnet 4.6 has issues.

Well, at least, we can still spend 💸 and burn money 💰🔥 on Opus 😅

AMD tire à vue sur Anthropic : Claude Code ne sait plus coder L'outil de codage star d'Anthropic est accusé de bâcler le travail depuis février. Le problème : cette dégradation survient alors que l'entreprise enchaîne fuite de code source, pannes à répétition et afflux record d'utilisateurs.

La directrice IA d'AMD a analysé près de 7 000 sessions Claude Code. Son verdict : l'outil ne sait plus réfléchir. Et Anthropic accumule les crises au pire moment.

My hot take on AI in engineering: It's an exoskeleton, not a replacement. 🦾

It gives us the strength to move faster and build bigger, but the human dev is still the one in the pilot's seat making the hard calls.

Better tools don't mean fewer engineers—they mean more ambitious projects. 🛠️

2026 dev workflow: 8 Claude Code sessions running in parallel on one wide screen. Next logical step is obviously a cockpit setup with 2 ultra wides. No other way.

70% of Devin sessions are still human-triggered. Nader Dabit thinks that flips to 10/90 within a year. The interesting part: what engineers do changes more than what agents do. Less code, more system design for autonomous loops.

Imaginez 10 ans plus tard je sors une suite à Curvytron et je l’annonce un 1er avril ?
Nan je rigole.

Mais imaginez quand même : curvytron2.com

https://www.youtube.com/watch?v=79sDQ7JXVvQ

An agent writes 2,000 lines. It's 80% right. Your instinct says ship it. Wrong move. At Semji we now generate multiple implementations of the same feature, compare architectural trade-offs, then pick. Code is disposable. Judgment is the product.

Designing delightful frontends with GPT-5.4 | OpenAI Developers Practical techniques for steering GPT-5.4 toward polished, production-ready frontend designs.

Counter-intuitive: GPT-5.4 produces better frontends with LOW reasoning than high. When the model overthinks, it over-designs. Restraint beats intelligence. OpenAI's new frontend guide: strong constraints, moderate reasoning, ship.

developers.openai.com/blog/designi...

OpenAI: How AI is reshaping the craft of building software - The Pragmatic Summit Tibo Sottiaux (Head of Engineering, Codex, OpenAI) and Vijaye Raji (CTO of Applications, OpenAI) at The Pragmatic Summit: www.pragmaticsummit.com. Watch sessions, with Q&A:…

OpenAI's Codex team starts meetings with unanswered questions. They fire off Codex threads in the background. 20 minutes later, answers are ready. Five or six questions per meeting, all handled by "little consultants working in the background."
www.youtube.com/watch?v=Bo6G...

OpenAI: How AI is reshaping the craft of building software - The Pragmatic Summit Tibo Sottiaux (Head of Engineering, Codex, OpenAI) and Vijaye Raji (CTO of Applications, OpenAI) at The Pragmatic Summit: www.pragmaticsummit.com. Watch sessions, with Q&A:…

New practice at OpenAI: instead of debating trade-offs in a design doc, they spin up multiple implementations in parallel and pick the one that works best. When prototyping costs near-zero, "let's just try all three" beats "let's discuss which one."
www.youtube.com/watch?v=Bo6G...

OpenAI: How AI is reshaping the craft of building software - The Pragmatic Summit Tibo Sottiaux (Head of Engineering, Codex, OpenAI) and Vijaye Raji (CTO of Applications, OpenAI) at The Pragmatic Summit: www.pragmaticsummit.com. Watch sessions, with Q&A:…

OpenAI's designers now ship more production code than engineers did 6 months ago. The models got good enough that designer-written code is mergeable as-is. Role boundaries aren't blurring. They're dissolving.
www.youtube.com/watch?v=Bo6G...

More Magic Math from OpenAI? When it comes to OpenAI, smart money is starting to do the math out loud. And something doesn’t add up. On surface, today’s news that OpenAI is offering 17.5% guaranteed returns to priv…

More Magic Math from OpenAI? om.co/2026/03/23/m...

OpenAI: How AI is reshaping the craft of building software - The Pragmatic Summit Tibo Sottiaux (Head of Engineering, Codex, OpenAI) and Vijaye Raji (CTO of Applications, OpenAI) at The Pragmatic Summit: www.pragmaticsummit.com. Watch sessions, with Q&A:…

One PM runs the entire OpenAI Codex team. During a bug bash, he sent Codex to collect feedback, generate a Notion doc, file tickets in Linear, assign them, and follow up with everyone. One person doing the coordination work of five. AI doesn't just scale engineering.
www.youtube.com/watch?v=Bo6G...

Building WhatsApp with Jean Lee How did a tiny team of 30 engineers build the world-famous messaging app more than a decade ago, and what can dev teams learn from that feat today? Jean Lee was engineer #19 at WhatsApp, joining when…

30 engineers. 450M users. No code reviews. No Scrum. No Agile. No TDD.

WhatsApp's secret? Brian Acton reviewed your first PR in extreme detail. After that, you were trusted.

Meanwhile, Skype had 1,000 engineers and lost.
www.youtube.com/watch?v=5Kn3...

How Stripe’s Minions Ship 1,300 PRs a Week Every week, Stripe merges over 1,300 pull requests that contain zero human-written code. Not a single line. These PRs are produced by “Minions,” Stripe’s internal coding agents, which work completely…

Stripe built devboxes that spin up in 10s, 3M tests, sub-5s linting... all for human engineers. Turns out AI agents love the exact same things. Their "Minions" now ship 1,300 PRs/week. Best AI investment? Great developer experience.
blog.bytebytego.com/p/how-stripe...

The Pulse: What will the Staff Engineer role look like in 2027 and beyond? Also: new trend of token costs becoming a worry for CTOs, 10% cuts at Atlassian, and more.

What does Staff Engineer look like in 2027? When agents write most of the code, expertise shifts. Less code craftsmanship. More architecture, orchestration, and judgment. The title stays. The job is being rewritten in real time.
newsletter.pragmaticengineer.com/p/the-pulse-...

Building Claude Code with Boris Cherny Claude Code creator Boris Cherny on building AI-powered coding tools, parallel agents, and how the engineer's role is evolving in an AI-first world.

Claude Code now accounts for 4% of all public GitHub commits. DAUs doubled last month. This isn't an experiment. It's infrastructure. And it's 100% self-written. The tool that writes code is written by the code it writes. We're in a new era. 🔥
newsletter.pragmaticengineer.com/p/building-c...

"Claude Code is now 100% written by Claude Code." - Boris Cherny, March 2026.
→ May 2025: 80% AI-generated
→ Dec 2025: 259 PRs in a month, zero IDE opened
→ Mar 2026: fully self-written
The AI coding tool that improves itself. Let that sink in. 🔥

OpenAI just dropped GPT-5.4 mini and nano. The numbers: 400k context, 128k output, mini at $0.75/$4.50 per 1M tokens, nano at $0.20/$1.25. Nano edges past GPT-5 mini on SWE-Bench Pro. The small model race keeps accelerating.

Counter-intuitive: directors and senior leaders use Claude Code 2x more than junior devs. The people with the most context and judgment are going hardest on AI. Makes sense. AI amplifies expertise, it doesn't replace it.

25 ans à fédérer la communauté PHP en France... Mais ce début d'année 2026 nous inquiète. Vraiment.

Fêter 25 ans ensemble, c'était beau. Mais 2026 s'annonce difficile pour l'AFUP. Sponsors en retrait, billetteries en recul… Sans la communauté, il n'y a pas d'AFUP.
On vous explique nos difficultés dans cet article, et on compte sur vous ! 💙
buff.ly/sh1OMTU

Au delà de SpecKit, la valeur de notre travail se situe de plus en plus en amont de l’implémentation pure, au niveau de la définition des specs techniques : comment faire telle implémentation, à quel endroit, en utilisant quel composant, etc. Ces choix deviennent ensuite, « exécutables ».

Spec Kit just hit 76.8k stars. The idea? Write specs, not code. Specifications become executable, AI agents do the implementation. 20+ agent integrations (Claude, Copilot, Cursor...). "Software engineering" is becoming "specification engineering" in real time.

New data point: token costs for building a production feature now cost less than a 30-minute planning meeting. If "just trying it" is cheaper than "planning it in detail", maybe we should prototype first, plan second.

OpenAI built 1M+ lines of code in 5 months with zero manually typed code. Their biggest challenge? Not the AI. It's "designing environments, feedback loops, and control systems." We're shifting from writing code to writing constraints.

Birgitta Böckeler nails it: the real engineering challenge with AI agents isn't prompting, it's building the harness. Linters, structural tests, context pipelines. The boring stuff that keeps agents from going off the rails.

Simon Willison stopped reading AI-generated code. His safety net? Tests. "Tests are effectively free. No longer even remotely optional." When agents write more code than you do, tests become the product.

Cursor just hit $2B in annual revenue. Doubled in 3 months. And they just launched Automations: agents that trigger from code changes, Slack messages, or timers. No human in the prompt loop. The IDE is becoming an OS for AI agents.

The Dead Companies Walking: What Steve Yegge Sees Coming | Victorino Group Yegge predicts 50% engineering cuts and eight levels of AI adoption. The real insight is about organizational absorption, not speed.

Small teams metabolize the change naturally. Large orgs choke on their own processes.

This is why startups are winning right now.

🔗 victorinollc.com/thinking/yeg...

The Dead Companies Walking: What Steve Yegge Sees Coming | Victorino Group Yegge predicts 50% engineering cuts and eight levels of AI adoption. The real insight is about organizational absorption, not speed.

Steve Yegge nails it: the bottleneck for AI in engineering isn't the models. It's organizational absorptive capacity.

QA, compliance, deployment — everything is calibrated for human-speed.