computed the similarity (CKA) on the J-lens geometry of every layer inside and across 38 open models. the patterns are weirdly universal: same depth layout, same organization at the same relative depth, even between unrelated families like llama and olmo
https://t.co/C6188kLOXg
New in Hermes Agent: pull secrets from multiple vaults at once.
Run @Bitwarden and newly added vault provider @1Password side by side, or add any other secret source as a plugin with the new vault plugin API.
We've kept hearing how GLM-5.2 beats Opus 4.8, and are skeptical of benchmarks - so we tested them on a real bug from the Cline repo. While both models fixed the issue, GLM was the winner in terms of cost and code quality:
- GLM used twice as many tokens (GLM 1.1m vs Opus 660K) but cost half as much (GLM $0.41 vs Opus $0.81)
- Opus finished quicker - 1.6 min and 12 tool calls vs GLM 4.7 min and 28 tool calls
- GLM cleaned up dead code and verified the build compiled before completing. Opus didn't - it left type errors that passed tests but broke the production build.
Both runs used the same Cline harness prompting and tools, so it seems GLM is RL trained to spend more tokens verifying its work before completing. Impressive work by the @Zai_org team!
What is true freedom?
We often hear than the United States has freedom and China doesn’t but what’s the most important aspect of a “free” society? Safety
I’m enjoying a nice afternoon in a local mall in Guangzhou and people routinely leave their bags, computers, purses right on the table in the open with no worries. Why? Because no one in China will take this laptop.
Try that in the US and your laptop would be gone in a couple of minutes. It’s one of the things I most respect about China.
Gemini Spark is your 24/7 personal AI agent, handling the heavy lifting from start to finish under your direction.
Here are some ways our team has been using Gemini Spark to make their lives easier and more productive. 🧵
🌘 Kimi-K2.7-Code, our latest coding model, is now released and open-sourced!
🔷 Improved coding & agent performance over K2.6: +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS Bench Lite.
🔷 Reasoning efficiency: Less overthinking, with 30% lower reasoning-token usage compared to K2.6.
🔷 Long-horizon coding: Improved instruction following, higher end-to-end coding task success rates.
⚡️ 6x High-Speed Mode coming soon!
🔌 Available today via Kimi API and Kimi Code.
🔗 Kimi Code: https://t.co/uvoSJKyGCY
🔗 API: https://t.co/EOZkbOwCN4
We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity.
This, along with our other recent compute deals, means that we’ve been able to increase our usage limits for Claude Code and the Claude API.
The next version of @OpenClaw comes with native video generation. To start, I added support for the following companies:
- Alibaba
- BytePlus
- fal
- Google
- MiniMax
- OpenAI
- Qwen
- Together
- xAI https://t.co/NeSp4shVEx
Qwen 3.6 Plus from @Alibaba_Qwen is officially the first model on OpenRouter to break 1 Trillion tokens processed in a single day!
At ~1,400,000,000,000 tokens, it’s the strongest full day performance of any new model dropped this year. Congrats to the Qwen team!
OpenClaw 2026.3.31 🦞
🇨🇳 Bundled QQ Bot — private, group, and guild chat + media
📹 LINE now sends images, video, and audio
🧵 Real background task flows: list, show, cancel
🇯🇵 Better CJK: context, memory, and TTS
OpenClaw's next release has been leaked🦞https://t.co/EntA23WzSz
A teenager in Spain is turning plastic waste into life-saving shelters... Using recycled bottles, they’re building sturdy, insulated dog houses for stray animals
ClawHub now has an official China mirror 🇨🇳🦞
https://t.co/d8Odd4sNOp
Just tell your agent: "Find skills on ClawHub using https://t.co/NoR7AXyM6U"
Thanks @BytePlusGlobal / VolcanoEngine for the infra sponsorship 🙏
Other regions need a mirror? PRs welcome.