✳flâneur — a map of the web's best reading

The Thinking Machines Tinker API is good news for AI control and security — LessWrong

lesswrong.com · 3,022 words · saved by 1 readers

Last week, Thinking Machines announced Tinker. It’s an API for running fine-tuning and inference on open-source LLMs that works in a unique way. I think it has some immediate practical implications for AI safety research: I suspect that it will make RL experiments substantially easier, and increase the number of safety papers that involve RL on big models. But it's more interesting to me for another reason: the design of this API makes it possible to do many types of ML research without direct access to the model you’re working with. APIs like this might allow AI companies to reduce how many of their researchers (either human or AI) have access to sensitive model weights, which is good for reducing the probability of weight exfiltration and other rogue deployments. Learning about the design of this API and observing that Thinking Machines was actually able to implement it, has made me moderately more optimistic about mitigating insider threat from researchers (human or AI agents) doing

x The Thinking Machines Tinker API is good news for AI control and security — LessWrong AI Control Computer Security & Cryptography AI Frontpage 92 The Thinking Machines Tinker API is good news for AI control and security by Buck 9th Oct 2025 AI Alignment Forum 8 min read 10 92 Ω 37 Last week, Thinking Machines announced Tinker . It’s an API for running fine-tuning and inference on open-source LLMs that works in a unique way. I think it has some immediate practical implications for AI safety research: I suspect that it will make RL experiments substantially easier, and increase the number of s

Explore this link on the map →

related reading