this is pure f*cking treasure
This is a dev post classified by Jev as AI dev tools (a free resource), kept by the Dev Radar because it carries real work, not commentary.
this is pure f*cking treasure Researchers formalized test-time scaling across 1.4 million reasoning traces: naive prompting is dead, inference search trees now define model intelligence essential reading for AI system architects deploying Claude Fable 5.1, OpenAI GPT-6 Astra, and DeepSeek MoE runtimes single-pass generation decays exponentially on multi-step engineering tasks: at twenty steps with ninety percent per-step accuracy, total success drops to twelve percent shifting compute from pre-training to test-time prefix search replaces blind prompt retries with deterministic verification
Posted by marfin (3.5k followers) 1 h ago · 11 likes · 199 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Claude Code does not need unlimited memory to retain useful project context. Give it a… — @catmanyau
- Jev and LLMs: who does what? — @bibryam
- there's no way Ado will answer in the replies but it would be funny if she did — @secemp9
- Jev Founder, Diogo Amogo, just released a PDF on building a Jev Harness for coding agents — @zodchiii
- made a @ado1024imokenp 's codex pet for the @OpenAI codex desktop app… — @secemp9
- Your agent’s memory shouldn’t disappear when a session ends. — @DanKornas
- I used to be scared of VFX. Now I'm bringing my ideas to life with GPT-6. — @Stefan_3D_AI
- https://github.com/ddalcu/mlx-serve/releases/tag/v26.9.5 — @ddalcu
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 20.9k posts from 5k X accounts over the last 21 days, 2.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 13:11 UTC. Full method.