Quand je vois les propositions à 80k€ PACKAGE pour travailler sur de l’innovation IA en France, je rigole fort. Je préfère encore travailler en Java sans IA, au moins j’ai le même salaire voire mieux
"Les gens doivent être payés autant que possible, c'est littéralement ce que je fais": le patron de Nvidia assume de proposer des énormes salaires (la moitié des 36.000 salariés gagnent plus de 301.000 dollars)
https://t.co/kJ5baA2LEr
Qd t’es un grand diplômé en France, tu es la pour te faire exploiter par des managers et commerciaux (avec un salaire 1/2 inférieur aux estimations chez Mistral deja dans l’élite). Pas par des technocrates pleins de bonnes idées. C’est pour cela que y’a aucun avenir ici.
This is the clarity we've been crying out for.
But it's a poisoned chalice. This is a 10X cut to claude -p disguised as a monthly bonus.
Anthropic is discouraging any kind of programmatic usage. And that's fine - no subsidy lasts forever.
But it's time to try Codex.
Ingénieur logiciel en IDF, 50k€, pas d'actions, managé par un bozo d'école de commerce.
Ingénieur logiciel à SF: 200k€, RSU ou Stock options, managé par un mec qui a vu les entrailles de l'industrie.
Mais pourquoi donc nos meilleurs partent-ils? Le mystère reste entier.
The creator of Claude Code just revealed his setup.
Boris Cherny: 100% of his code is written by Claude Code. 100 agents running simultaneously.
24 minutes. Free. Watch it.
New signups for Copilot Pro, Pro+, and Student plans are paused to maintain service reliability for current users.
• Usage limits tightened; Pro+ offers 5X higher limits than Pro
https://t.co/sV8aOkGLZ9
CLAUDE CODE MAX BURNS YOUR LIMITS 40% FASTER AND NO ONE TOLD YOU WHY
this guy set up an HTTP proxy to capture full API requests across 4 different Claude Code versions.
here's what he found:
Claude Code v2.1.100 silently adds ~20,000 invisible tokens to every single request.
they are server-side so you can't see them and they don't show up in /context.
the proof:
> v2.1.98: 49,726 billed tokens
> v2.1.100: 69,922 billed tokens
> same project, same prompt, same account
v2.1.100 actually sends FEWER bytes but gets billed 20K MORE tokens. the inflation is 100% server-side.
and it's not just about billing. those 20K invisible tokens enter the model's actual context window.
which means:
> your CLAUDE.md instructions get diluted by 20K tokens of hidden content
> quality degrades faster in long sessions
> when Claude ignores your rules you can't tell if it's because of invisible context you can't audit
the fix: downgrade to v2.1.98
npx [email protected]
Si desactivas la telemetría de Claude Code, Anthropic te castiga con un cache de 5 minutos en vez de 1 hora.
Sí, has leído bien. Tu privacidad cuesta 12x más caro.
Acaban de reportar el bug. Y tiene implicaciones serias. 🧵
GOOGLE BUILT A SECRET WEAPON FOR FILE DETECTION
they ran it internally for years, gmail, drive, safe browsing, hundreds of billions of files every week
then they open sourced it
it's called magika and it exposes what files really are, not what they pretend to be
rename malware to "resume.pdf"? magika sees through it
disguise a script as an image? magika sees through it
any trick attackers use with file extensions? magika sees through all of it
ai trained on 100 million files. 200+ content types. 99% accuracy. 5ms per file
one command
`pip install magika`
the same tool protecting google's billion users is now protecting yours
https://t.co/Jr3LjmQobq