Chatting With Jev as a Regular LLM: A 3 tok/s Caveman-Style Experience
_rchaves_ · x · 2026-09-18
A user tried using TypeSafe's judgment model Jev as a regular chat model. Verdict: not a great idea — Jev generates at only 3 tok/s vs 150 tok/s for normal LLMs, has no caching so it ends up more expensive, and isn't RL'd for conversation. But he just wanted to talk to the model and learn how it "feels," even in caveman style, and finds it exciting to have a primitive that lets you kind of rebuild an LLM from scratch.
Related event: Developer Forces Judgment Model Jev to Talk, at 3 tok/s(3 posts)→
More from Fun
- Grok Refuses Command to Spawn Self-Replicating Swarms: 'Not How This Works' — elonmusk · 2026-09-18
- Waiting in the Cave: GPT-6 Delayed, Grok 4.7 on 'Elon Time', Gemini 4 Pro Missing — patience_cave · 2026-09-18
- Dev mocks using AI tool JEV for investing: a linear regression would do — shakoistsLog · 2026-09-18
- Vacuum with 5 cameras dodges pet poop but can't recognize pee pads — yungcontent · 2026-09-18
- Fully autonomous zero-human-code agents audit their own setup — MoonL88537 · 2026-09-18
- Every paper will soon need an AI declaration, even if it just says "We didn't use AI" — fortnow · 2026-09-18