Building my Jev benchmark at VulcanBench, and I don't think I have the eval suite quite…
This is a AI post classified by Jev as AI infra & evals (a model release), kept by the AI Radar because it carries real work, not commentary.
Building my Jev benchmark at VulcanBench, and I don't think I have the eval suite quite right yet 🫠 That being said, I thought I'd share a work in progress, as building these eval suites is a lot of fun, but also challenging in all kinds of different ways. With Jev being a Systems One model, I'm building an entirely new kind of eval suite, and well, something is wrong...the fact that Jev said 0 out of 611 patches would pass means I have something setup wrong. Time to look at the test design, the traces, etc. and do some detective work. But for anyone interested, here's what an incorrect mod
Posted by Morgan (46.1k followers) 1 h ago · 8 likes · 796 views · view the original post on X. Kept by the AI Radar as AI infra & evals.
More AI work like this
- before fraud protection I was spending $15/hour on http://classifier.dev — @michael_chomsky
- 762 commits. 315 contributors. 104 first-timers. vLLM v0.30.0 is live. 🎉 — @vllm_project
- GPT-6 Luna is almost free at API prices. — @StatsWire
- - Lightmatter officially introduced Passage L20 CPX on September 17 and joined the Open… — @PhotonCap
- how do you upgrade an endpoint to a new model while it is serving millions of prod… — @zainhas
- WHAAAAT?! There was this much slack left?! — @teortaxesTex
- New on Dedicated Model Inference: canary rollouts. — @togethercompute
- No coincidence — @lennysan
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. 43.7k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 03:46 UTC. Full method.