Research
LLM next-token prediction is already a probabilistic classifier, so an open LLM can serve a Jev-like interface: discrete options in, fast pr…
LLM next-token prediction is already a probabilistic classifier, so an open LLM can serve a Jev-like interface: discrete options in, fast probabilities out. Our own @ekzhang1 made it better at the job
LLM next-token prediction is already a probabilistic classifier, so an open LLM can serve a Jev-like interface: discrete options in, fast probabilities out. Our own @ekzhang1 made it better at the job with a 5, 10-minute run on Tinker. Did some SFT on Qwen3.6-35B-A3B this evening, just to get it to respond better to Jev-y prompts via https://github.com/ekzhang/openjev-sglang Cost: 5, easy 10 min training run on Tinker. +8% on GPQA diamond and +12% on MMLU-Pro. Also evaled @jaredpalmer's Kev here for comparison
Source: Soumith Chintala (X) | 2026-09-23