Supervised fine tuning on curated data is reinforcement learning

Re:Supervised fine tuning on curated data is reinforcement l... by mandevil on Tuesday July 29, 2025 @04:47PM (#44728100)

Interesting to see two independent researchers on this. Makes me curious as to what the back-story is? Side project?

[ Parent | on HN ]

Re:Supervised fine tuning on curated data is reinforcement l... by jtspringenberg on Tuesday July 29, 2025 @05:58PM (#44728730)

Author here, just to clarify: we are both no longer working for DeepMind. This was purely an independent effort for the sake of research and understanding! Happy to answer any questions.

[ Parent | on HN ]

Re:Supervised fine tuning on curated data is reinforcement l... by babelfish on Tuesday July 29, 2025 @05:03PM (#44728235)

Especially interesting given they both work for Google DeepMind.

[ Parent | on HN ]

Re:Supervised fine tuning on curated data is reinforcement l... by GabrielBianconi on Tuesday July 29, 2025 @05:36PM (#44728534)

Yeah, I hadn't noticed!

[ Parent | on HN ]