Pinned Tweet
Today I am launching AI;DR 🚀🚀
AI;DR is having automated workflows that reads the day's AI news from 20+ sources and publishes one ranked edition.
Ranking and summaries are done by Jev/LLM powered by AnyRouter. The results are combined into one snapshot and then distributed to the site, email, and Telegram.
AI;DR is fully Open Source. Hosted on @Cloudflare.
aidr.today/?lang=en now using Nemotron 3.5 Bolt for Vietnamese translation as Gemma is always more good at Vietnamese
Nemotron 3.5 Bolt E4B is now available for FREE on AnyRouter.
NVIDIA Nemotron 3.5 Bolt E4B is a small language model post-trained from Gemma 4 E4B. It improves multi-turn tool use, instruction following and input grounding for fast voice and device assistants, interactive personas and embedded interfaces, with low memory use and low time to first token.
duyet retweeted
Atria Dawn is now on AnyRouter.
An agentic model from the Shanghai Artificial Intelligence Laboratory, built on the 744B-parameter GLM-5.2 mixture-of-experts base and released under the MIT license.
anyrouter.dev/model/atria-as…
Introducing Atria Dawn Preview:
From Research Questions to Verifiable Results.
Atria Dawn Preview is an agentic foundation model built for long-horizon tasks, helping researchers and engineers turn open-ended questions into executable, verifiable, and reproducible outcomes.
Explore Atria Dawn Preview:
🌐 Website: atria-asi.ai/
💻 GitHub: github.com/atria-asi/Atria-D…
🤗 Hugging Face: huggingface.co/internlm/Atri…
🤖 ModelScope: modelscope.cn/models/Shangha…
🚀 Try Atria:
EN：api.atria-asi.ai/
ZH：discovery.intern-ai.org.cn/t…
duyet retweeted
Hey fellow Tailscale loving friends, with all the security shenanigans going on here’s a prompt I recommend for making sure the weakest link on your talilnet can’t wreck everything else over ssh or otherwise.
Give your agent this and let it walk you thru locking down your ACL:
gist.github.com/alexknowshtm…
duyet retweeted
Nemotron 3.5 Bolt E4B is now available for FREE on AnyRouter.
NVIDIA Nemotron 3.5 Bolt E4B is a small language model post-trained from Gemma 4 E4B. It improves multi-turn tool use, instruction following and input grounding for fast voice and device assistants, interactive personas and embedded interfaces, with low memory use and low time to first token.
AI;DR: Cerebras Deploys Trillion-Parameter AI; Why is AI generated and Five Qwen3.8-27B models outperform.
1. Cerebras Deploys Trillion-Parameter AI: Cerebras Deploys Trillion-Parameter AI Models
2. Why is AI generated: Why is AI generated language so hard to understand?
3. Five Qwen3.8-27B models outperform: They offer Fable 5-level coding at one-fifth the price
4. Neural chip decodes interactions: The system could enable more precise brain monitoring.
5. OpenMobile-2 proves open-source smartphone: OpenMobile-2 proves open-source smartphone agents can rival proprietary models
aidr.today/date/2026-10-25?u…
duyet retweeted
MiniMax M3.1 Flash is paid on most platforms now, but AnyRouter still has it free 🔥
• $0 API access
• no daily request cap
• up to 2,400 requests/min per key
• sign in required
• no end date announced yet
base URL: anyrouter.dev/api/v1
model: minimax/minimax-m3.1-flash:free
details: anyrouter.dev/blog/minimax-m…
duyet retweeted
chmonitor v0.3.9 — Know who runs what
chmonitor v0.3.9 ships 9 new features and 10 fixes since v0.3.8. Every query the dashboard sends now carries who ran it and from which page, a new Dashboard Usage page reads that back, the users page shows who is active, and repeat alerts.
Thariq left Anthropic
I’ve left Anthropic after more than a year of working on Claude Code and seeing it scale larger than I ever imagined.
I have really loved working at Ant and believe deeply in the mission, and most of all, the idea of a race to the top.
The idea that if we work hard and responsibly, we can raise the bar and inspire others to great outcomes. And if we all push each other to be better, things can be radically good. I will carry the spirit of this with me forever.
My colleagues at Anthropic are the most talented, thoughtful, competent, and earnest people I have ever met. I am glad they are at the wheel and trust them deeply.
To the community on X, thank you for everything. You’ve made this the most fun (and sometimes stressful) job I’ve ever had.
For me, it is time for a bit of a break before diving into something new.
If you want more excellent Claude Code content, you should follow @addyosmani , @lydiahallie, @_catwu, @ClaudeDevs and of course @bcherny who started it all.
duyet retweeted
We’re adding support for MCP Tasks and Elicitations in Claude.
Tasks let Claude give plugins long-running jobs such as deep research and report back when they’re done.
duyet retweeted
Together, we create a large pool for free models, more people = more tokens. See how the AnyRouter Pool works: anyrouter.dev/pool
duyet retweeted
With Go $2/mo you can access all 37 models unlimited via AnyRouter Pool.
- Dots Studio: Dots3-Note Preview
- MiniMax: MiniMax M3.1 Flash
- Poolside: Laguna S 2.1
- NVIDIA: Nemotron 3 Ultra 550B
base_url = anyrouter.dev/api/v1
Using with claude code:
$ anyr claude --yolo
anyrouter.dev/models?free=tr…
duyet retweeted
Introducing Kimi K3.1 Pro: our most capable 3T-class open-weight model.
🔹 1M-token context, 2.8T total / 104B active params (MoE), Multimodal.
🔹 Full-project coding: games in Unreal, Unity & Godot.
🔹 Excels at parametric 3D modeling in Blender & CAD.
🔹 More reliable at finance work: Accurate modeling with hallucination down by 65%.
🔹 Matching the strongest proprietary models across coding, agentic and knowledge benchmarks.
Kimi K3.1 Pro and K3.1 Pro Highspeed (2–3× faster) are now live on Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.
Open weights by Nov 4, 2026.
🔗 API: platform.kimi.ai
🔗 Tech blog: kimi.ai/blog/kimi-k3-1-pro
