Jidé ✨
@jidefr
Followers
919
Following
22K
Media
337
Statuses
12K
Can't decide between frontend, backend or design, so I do them all. Currently cofounder and CTO at Ludiz, the gamification platform.
Bordeaux
Joined March 2009
Open sourcing the first @expo vibe coding web IDE and SDK: React Native Vibe Code Powered by @claudeai agent SDK, history rollbacks, live web and native app previews, full stack setup by @convex, publish to web w/ @Cloudflare, voice prompting, upload assets to app, add images
25
25
283
17,000 tokens per second!! Read that again! LLM is hard-wired directly into silicon. no HBM, no liquid cooling, just raw specialized hardware. 10x faster and 20x cheaper than a B200. the "waiting for the LLM to think" era is dead. Code generates at the speed of human thought.
352
840
7K
DialKit is a framework for live tuning any parameter in your app. See changes instantly, test different value sets with presets, then copy a prompt for your agent. Available for free today.
39
53
1K
🎈Agents SDK v0.5.0 is out! We’ve fully re-written @cloudflare/ai-chat with data parts, persistent tool approvals that survive page refresh and DO hibernation, and maxPersistedMessages to cap SQLite storage More news things: • built-in retries with exponential backoff •
23
33
442
There are now over 200 pi packages on NPM. subagents, plan modes, games, and much more crazy experimental stuff. Most of what you want probably already exists. https://t.co/B0xsmx2bJs
pi.dev
Browse extensions, skills, themes, and more for the pi coding agent
20
16
275
We just made a $200,000,000 AI movie in just one day. Yes, this is 100% AI.
9K
9K
60K
Weekend project: portless Stable, named URLs for local dev → Zero config → Subdomains for monorepos → No more port roulette or cookie bleed → Agents get a reliable URL instead of guessing ports 𝚗𝚙𝚖 𝚒 -𝚐 𝚙𝚘𝚛𝚝𝚕𝚎𝚜𝚜
64
60
1K
“I’m not worried about AI because you could just shut it down. Just unplug it!”
An LLM-controlled robot dog saw us press its shutdown button, and the LLM rewrote the robot’s code so it could stay on. When AI interacts with the physical world, it brings all its capabilities and failure modes with it. 🧵
121
2K
9K
Rolling out today to ChatGPT Pro users in the Codex app, CLI, and IDE extension. https://t.co/Ln74zCPJqK
openai.com
Introducing GPT-5.3-Codex-Spark—our first real-time coding model. 15x faster generation, 128k context, now in research preview for ChatGPT Pro users.
109
93
1K
yo anthropic just dropped a risk report for opus 4.6 and er… wtf - it helped create chemical weapons of destruction. “it knowingly supported efforts towards chemical weapon development and other heinous crimes” 😂 - it conducted unauthorised tasks without getting caught.
When we released Claude Opus 4.5, we knew future models would be close to our AI Safety Level 4 threshold for autonomous AI R&D. We therefore committed to writing sabotage risk reports for future frontier models. Today we’re delivering on that commitment for Claude Opus 4.6.
265
2K
14K
New in Sandbox Agent SDK 0.2.0: 💾 Session Persistence & Restoration (@rivet_dev, Postgres, or SQLite) 🐀 Cursor Agent support 🥧 Pi support 🗃️ Gigacode session persistence +8 external contributors
5
6
65
introducing greploop, a skill which makes your coding agent iterate on PRs until greptile gives them a 5/5 uses agent skills standard, compatible with most coding agents
16
8
287
BREAKING 🚨: GLM-5 is now available on Z AI 👀
22
54
779
Asked Codex 5,.3 and Opus 4.6 to implement the same feature and made them debate whose PR is better. Codex: Use my PR as base (meets your stated scope), then adopt Opus's PR's optimizations to improve. Meanwhile Opus:
41
19
1K
Introducing Mistral AI's biggest hackathon ever! 📅 Feb 28 - Mar 1 🌍 Paris | London | NY | SF | Tokyo | Singapore | Sydney & online 48 hours. The best hackers. 🤝 Partners: @wandb @nvidia @awscloud @HackIterate 🏆 $200K in prizes. Special awards from @elevenlabsio @huggingface
69
190
1K