Comment Comment by BrokenCogs I believe the authors are wildly overstating the conclusions in their abstract.Did they test modifying the weights of a non-public model?Did they test modifying the weights of a non-LLM (and non-public) model?If not, we can only conclude that GPT-6 Astra is good at reading and writing weights of Qwen (a public LLM), not just any neutral network. parent BrokenCogs 7 days ago
Did they test modifying the weights of a non-public model?
Did they test modifying the weights of a non-LLM (and non-public) model?
If not, we can only conclude that GPT-6 Astra is good at reading and writing weights of Qwen (a public LLM), not just any neutral network.