@elonmusk@mark_k I think follow the claude ,building coding model roadmap can make the AGI. coding can easy to make model to "AGI" .grok code have great skill and power to make code easy. hope grok model can make better. using grok create b2b & b2c software(claude code) easy to help grok powerful
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]
⚡ Faster than Fast. Designed for Agentic AI.
Introducing Xiaomi MiMo-V2-Flash — our new open-source MoE model: 309B total params, 15B active.
Blazing speed meets frontier performance.
🔥 Highlights:
🏗️ Hybrid Attention: 5:1 interleaved 128-window SWA + Global | 256K context
📈 Performance:
⚔️ Matches DeepSeek-V3.2 on general benchmarks — at a fraction of the latency
🏆 SWE-Bench Verified: 73.4% | SWE-Bench Multilingual: 71.7% — new SOTA for open-source models
🚀 Speed: 150 output tokens/s with Day-0 support from @lmsysorg🤝
🤗 Model: https://t.co/4Etm0yZKTL
📝 Blog Post: https://t.co/5zxmcDuB6o
📄 Technical Report: https://t.co/crac1YTLYl
🎨 AI Studio: https://t.co/nSReUs6QgW