GPT-5.4 Is A Substantial Upgrade
Benchmarks have never been less useful for telling us which models are best.
Lire
/
Quick tips: Sending Laravel output to Ray automatically
Quick tips: Sending Laravel output to Ray automatically
A handy overview of the Ray configuration options in Laravel. You can automatically send duplicate queries, slow queries, exceptions, and dump output straight to Ray without adding any ray() calls to your code. Read more
Lire
Fast Paths and Slow Paths
Autonomous AI systems force architects into an uncomfortable question that cannot be avoided much longer: Does every decision need to be governed synchronously to be safe? At first glance, the answer appears obvious. If AI systems reason, retrieve information, and act autonomously, then surely every step should pass through a control plane to ensure correctness, […]
Lire
SymfonyLive Paris 2026 : Appel aux volontaires étudiants IT !
SymfonyLive Paris 2026, conference in French language only, will take place from March 26 to 27! The schedule is currently being revealed as we go along. More details are available here. 🎓 SymfonyLive Paris 2026 : appel aux volontaires étudiants…
Lire
“A spate of outages, including incidents tied to the use of AI coding tools”, right on schedule
Some with “high blast radius”
Lire
Creating The Perfect Claude Code Status Line
Creating The Perfect Claude Code Status Line
A walkthrough of building a useful Claude Code status line that shows your current repo, git branch, staged/unstaged changes, and context window usage percentage. The context percentage is the most valuable part: it helps you know when to compact or start a fresh session before quality degrades. Read more
Lire
Prompt Caching in LLMs!
A case study on how Claude achieves 92% cache hit-rate.
Lire
Claude Code, Claude Cowork and Codex #5
It feels good to get back to some of the fun stuff.
Lire
Anthropic sues US government, with good reason
As I wrote yesterday, Dario Amodei is no saint, but I fully support his company’s new lawsuit against the US government.
Lire
Import AI 448: AI R&D; Bytedance's CUDA-writing agent; on-device satellite AI
If Ukraine is the first major drone war, when will there be the first major AI war?
Lire
Treat Agent Output Like Compiler Output
Treat Agent Output Like Compiler Output
Why our discomfort with AI-generated code reveals exactly what we haven't built yet, and what the compiler analogy teaches us about trusting coding agents.
Lire
A Practical Guide to Evaluation of LLM Apps (Part C)
Understanding evaluation of conversational LLM systems, toolcalls, tracing, and red teaming.
Lire
There are no heroes in commercial AI
When it comes down to it, Dario Amodei isn’t all that much different from Sam Altman
Lire
Aucun résultat
Essayez avec d'autres termes de recherche.