How OpenAI Misled You on RLHF | Notion

JoyCaption, the open source image captioning model that I work on as a hobby, recently had its Beta One release, which was also the first release that used Reinforcement Learning (RL) to improve the model. RL has been a bit of a hot topic ever since the introduction of DeepSeek R1, and for good reason. But I believe people have a fundamental misunderstanding of RL and what its uses are, due in large part to OpenAI. In this article I want to shine a light on the mysteries of RL, as well as dive into specific details of how JoyCaption was run through the RL gauntlet. I love sharing my tools and knowledge with the community, to help others build cool stuff, which is why I’ve previously shared details on my models. So, with all that said, the first half will be dedicated to running through what Reinforcement Learning is and how OpenAI misled people. If you don’t care about that, or are already versed, and want to jump straight into the juicy details of training a model, skip ahead to

Kool & The Gang – Misled

“Misled” is a 1984 song by American R&B group Kool & the Gang taken from their sixteenth studio album, Emergency.

Looming over two cases threatening Musk's car company is a single question: Can he be trusted?

Elon Musk fought court cases on opposite coasts Monday raising a question about the billionaire that could either speed his plan to put self-driving Teslas on U.S. roads or throw up a major roadblock: Can this wildly successful man who tends to exagger...

Families of Lion Air crash victims say proposed Boeing deal not ‘true justice’

Under the deal, Boeing would pay US$1.5 billion and avoid trial over its handling of 737 Max safety issues.

Bluesky