The audn-ai Refusal Benchmark results are in. Quite impressive results! I managed to…
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.
The audn-ai Refusal Benchmark results are in. Quite impressive results! I managed to reduce the refusal rate from 99.0% to just 0.6% across 519 harmful prompts, without any loss in quality. 🔥
Posted by Alican Kiraz (39.6k followers) 3 h ago · 8 likes · 1.2k views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- What can AI tooling abstract away when you build for multiple platforms? — @callstackio
- 太卷了吧！OpenDesign 这波是不是疯了？ — @NFT_Chen
- 🔥学生党狂喜！Mistral 学生计划太香了！$5.99/月（原价$14.99）直接拿价值约$165的用量！ — @NFT_Chen
- GPT-QModel v7.10 now on pypi! 👋 — @qubitium
- @thinkymachines released Inkling 2 Small, and tbh I am quite impressed by what the model… — @javierbits
- 💥我靠！NVIDIA 直接把 Kimi K3.1 Pro 免费开放了！ — @NFT_Chen
- 有些 AI 明明挺聪明，干起活来却像个只会照命令走的实习生，这落差从哪儿来？ — @bkdgiffug
- Inkling 2 small is an extremely impressive release, especially for its size. — @kimmonismus
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. 31.9k posts from 5k X accounts over the last 21 days, 9.5k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 11:57 UTC. Full method.