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.
Tinker fine-tunes Qwen3.6 for Jev-style probability prompts in 10 minutes
AISummary
Tinker says an open LLM can serve a Jev-like interface that takes discrete options and returns fast probabilities, since next-token prediction is already a probabilistic classifier. A post by @ekzhang1 reports that a $5, 10-minute supervised fine-tuning run on Tinker improved Qwen3.6-35B-A3B's handling of Jev-style prompts, with +8% on GPQA Diamond and +12% on MMLU-Pro.
Post on XView on X
@tinkerapi
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: Tinker · x.comPublished · added here