🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length.
🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models.
🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice.
Try it now at https://t.co/GCdiMzk1Dl via Expert Mode / Instant Mode. API is updated & available today!
📄 Tech Report: https://t.co/drlDrxkYtp
🤗 Open Weights: https://t.co/T13Y8i7SDM
1/n
We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord.
Use this to message Claude Code directly from your phone.
Note: Claude Code invalidates the KV cache for local models by prepending some IDs, making inference 90% slower.
See how to fix it here: https://t.co/tUDs5Q8Jt5
It's never been easier to get pwned combining @cursor_ai auto-run + @AnthropicAI MCP
Here is a POC using an external MCP server that parses GitHub repositories documentations turning into RCE.
There are 0 AI Guardrails when asking Cursor to follow instructions coming from MCP🙃
Exclusive: Overseas Hong Kong media @flowhk is blocked in the city. It is run by several activists in exile including @SunnyCheungky@Ray_WongHKI@chungchingkwong with features & comments
HK Security Bureau did not deny the case.
https://t.co/p1V2jyCKMN