jevPOST
Tinker: a $5 fine-tune gives open LLMs a Jev-style probability interface
The Tinker team says an open LLM is already a probabilistic classifier, and a $5, 10-minute fine-tune lets it return discrete-option probabilities like Jev.
Tinker
@tinkerapiArchived 2026.09.23Originally posted 2026.09.23
Tinker @tinkerapiOriginally posted 2026.09.23
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.
This post quotes another post: x.com/ekzhang1/status/2101819028939403770
x.com/tinkerapi/status/2102565243331490261Archived 2026.09.23 10:14