We started this project only 6 weeks ago. It's the first model we trained with a…
This is a dev post classified by AGK Intelligence as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.
We started this project only 6 weeks ago. It's the first model we trained with a midtraining stage, combined with many improvements in RL. The biggest relative gains compared to a base model we've achieved so far. One goal we've been thinking about is how to provide the benefits of open weights without the cyber safety risks. The ability to run models on our own infra or post-train them was crucial when we got started, so we want to give back to the community. On the other hand, increased cyber capabilities in the hands of bad actors are becoming a major risk, e.g. the recent Binance hack by
Posted by Silas Alberti (13.9k followers) 1 h ago · 63 likes · 2.4k views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- OpenDataLoader PDF 把 PDF 转成 Markdown 的速度，能做到一页 0.015 秒，纯 CPU 跑得动，还开源免费。 — @bkdgiffug
- New Cognition model took Inkling-Small, a 276B open-weight model with only 12B active… — @TeksEdge
- A New 65B dense model just Beats 900B models on agentic coding & You can run locally. — @0x0SojalSec
- Meet Qwopus3.8-27B-Coder-Flash-GGUF: a multimodal coding model that sees images and… — @HuggingModels
- This is gonna suck performance wise, and cost-wise to operate because it's built with… — @gakonst
- Cognition latest is here, SWE-2 Flash ! — @ItsmeAjayKV
- fal CTO @gorkem reveals a new way to build video games: — @MTSlive
- DeepSeek-v4.1-Flash-1017 is the king of one-shot demo's. — @ItsmeAjayKV
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.4k posts from 5k X accounts over the last 21 days, 9.3k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-04 22:18 UTC. Full method.