Jaden Teo
An AI researcher and co-author of the paper Sparks of Weight Space Programming, which studies the ability of large models to read and modify the weights of neural networks.
Timeline (last 90 days)
Four MIT researchers (led by Rikia Takehi and Jaden Teo) published a paper proposing the concept of 'weight-space programming,' i.e., handing the raw weights of a small network to GPT-6 Astra and letting it read, repair, or write new weights from scratch.
The research was led by MIT first-year PhD student Rekia Takehi, with collaborators including Jaden Teo, Alex Zhang and Omar Khattab; the results were released as a blog post, and all experiment logs are fully public.
The researchers gave 17,253 weights to GPT-6 Astra, and all four networks were correctly identified as their corresponding games.
All Facts (3)
Four MIT researchers (led by Rikia Takehi and Jaden Teo) published a paper proposing the concept of 'weight-space programming,' i.e., handing the raw weights of a small network to GPT-6 Astra and letting it read, repair, or write new weights from scratch.
50%UnverifiedThe research was led by MIT first-year PhD student Rekia Takehi, with collaborators including Jaden Teo, Alex Zhang and Omar Khattab; the results were released as a blog post, and all experiment logs are fully public.
50%UnverifiedThe researchers gave 17,253 weights to GPT-6 Astra, and all four networks were correctly identified as their corresponding games.
50%