🤯This is insane… you can now run Codex inside Claude Code.
No tab switching.
No copy-pasting.
No second IDE.
Just one terminal — two AI agents working together.
It’s called codex-plugin-cc.
Here’s what this unlocks:
• Delegate entire coding tasks from Claude → Codex
• Ask Codex to review your changes before commit
• Run adversarial design reviews on your architecture
• Launch long-running fixes in the background
• All using your existing ChatGPT subscription
You literally get Claude planning + Codex executing in one workflow.
Even wilder — this is officially built by OpenAI.
Not a wrapper. Not a hack. Not a community fork.
OpenAI shipped a plugin that connects their agent
to Anthropic’s Claude Code environment.
Two competing AI labs.
One terminal.
One codebase.
That sentence shouldn’t exist in 2026.
The commands are clean:
/codex:review → full code review
/codex:adversarial-review → challenge architecture decisions
/codex:rescue → hand off bugs to Codex
/codex:status → track background jobs
/codex:result → fetch output
You can literally say:
“Ask Codex to investigate why tests are failing”
…and it runs in the background while you keep coding.
No API keys required.
Works with ChatGPT subscription.
Installs in one command.
100% open source.
This is the first real multi-agent coding workflow inside a single terminal.
Anthropic pays Applied AI Engineers $750,000+ a year to build AI agents that run for hours.
two of them just broke down the exact principles behind every agent that actually ships.for free.
[in this 75 min talk they cover:]
→ how one engineer with Claude outperforms an entire product team
→ the harness decisions that determine whether your build succeeds or breaks
→ the primitives Anthropic uses internally — tools, skills, hooks, sub-agents
→ why most first builds fail before they start
these are the 4 principles I used to put together a complete builder's guide on shipping your first product with Claude.
bookmark this for the weekend. then read the builder's guide below.
Anthropic just paid millions to hire Andrej Karpathy.
He gave you the same knowledge for $0 the same week.
Co-founder of OpenAI. Former head of AI at Tesla. The man who coined vibe coding.
No recruitment fee. No exclusive access. Just a link and 29 minutes.
LLMs are ghosts not animals.
Vibe coding is dead.
Software 3.0 is here.
Watch it.
Then read this.
Because Karpathy tells you what Software 3.0 is.
This shows you how to build one - a software factory with Claude Code that ships features while you sleep.
The full build guide is below.
Anthropic pays $750,000+ a year for engineers who know how to build LLMs from scratch.
Stanford just released the exact lecture that teaches it - 1 hour 44 minutes, free, straight from CS229.
Bookmark and watch it this weekend.
It'll teach you more about how ChatGPT & Claude actually work than most people at top AI companies learn in their entire careers.
@BFMTV Bref rien de bon qui aille pour le futur de ce pays. Taxer les vrais riches est une fausse solution rapide qui engendrera de la délocalisation, une fuite des capitaux, une perte de confiance et compétitivité et productivité pour lequel la France souffre déjà.
@BFMTV Et pour le coup oui je trouve que quelqu’un payé 1500-1800€ est vraiment mal payé. Le salaire et le coût de la vie ne coincident pas du tout. La France paye mal et taxe fortement la majorité de son peuple.
@BFMTV Et notre Président actuel à vraiment pousser le bouchon trop loin. Trop c’est trop! J’en ai marre de bosser pour payer pour finir par payer des factures de l’Etat. J’aime mon pays mais la France est vraiment devenue une poche trouée.
@BFMTV Je n’ai rien contre le fait de payer des impôts quand je sais où ils vont et comment ils sont investi. Là ça devient n’importe quoi on paye une série en chaîne de mauvaise politique de gauche comme de droite.