“This answer feels better” is a useful instinct when working with AI. But how do you…
This is a dev post classified by AGK Intelligence as AI dev tools (a free resource), kept by the Dev Radar because it carries real work, not commentary.
“This answer feels better” is a useful instinct when working with AI. But how do you turn that instinct into a test you can use to judge future answers? @hammer_mt shows how to combine human judgment, model-based checks, and code to compare models, improve agents, and catch regressions. Watch the livestream for free this Thursday, Nov. 5: https://every.to/tv?utm_source=x&utm_campaign=thesis-2027&utm_content=every-261103-teaser-vibe-checks-to-evals
Posted by Every 📧 (58.4k followers) 1 h ago · 3 likes · 566 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: Compound Engineering.
More dev work like this
- YouTube firing on all cylinders. — @rileybrown
- Does your coding agent try to do manual JS Date math for lunisolar holidays? 🌕 — @ChromiumDev
- Here are 18 Grokbot @bot templates that will change your life if you operate an agentic… — @PixelRainbowNFT
- Cache hits are only part of the equation. What matters is their impact on production AI. — @Minio
- You should be running this bot BEFORE you run out of storage, not AFTER! — @PixelRainbowNFT
- I suffer from Dependabot Fatigue: today I sovled it. — @pelaseyed
- We got OCRia-1 generating tokens nearly 10× faster on a single B200. — @llama_index
- 火柴人视频这活儿，如今连"导演"都被做成 AI Skill 了。 — @bkdgiffug
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. 31.3k posts from 5k X accounts over the last 21 days, 9.2k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-03 17:47 UTC. Full method.