News for hackers. Stuff that matters.

SknCode

Re:Microsoft's ONNX Runtime has disappeared from GitHub on Wednesday November 18, 2026 @02:48AM (#50543084)
What do you use instead?
While I agree with the gist of it, the conclusion - AI agents are not dangerous - is wrong. They did use weakness in the system deliberatelly, not by accident. Better security therefore is sufficient only to the point of capabilities of these models.
I am sorry, but this site is vibecoded beyond my comprehension. What is it trying to say?
How?
Re:Meta Superintelligence's surprising first paper on Sunday October 12, 2025 @02:20PM (#45560452)
I am not sure if I understand things correctly.

I came to believe the LLMs work with token embeddings. Is then the REFRAG only "something" in front of the LLM, and the decoder is the RL policy which expands only some token chunk embeddings into token embeddings feedable to LLM? Or the REFRAG needs you to 'tune' the LLM to be able to work with both token embeddings and token chunk embeddings?