Hacker News: wave_1

New comment by wave_1 in "xLSTM code release by NX-AI"

wave_1 — Wed, 05 Jun 2024 18:50:48 +0000

state tracking...

New comment by wave_1 in "Feynman Symbolic Regression Database"

wave_1 — Mon, 13 May 2024 16:31:46 +0000

If we can figure out symbolic regression in a universal fashion that would be AGI in a way, right?

New comment by wave_1 in "FireChat was a tool for revolution, then disappeared"

wave_1 — Mon, 29 Apr 2024 22:46:56 +0000

haha the best reply on the Internet

New comment by wave_1 in "What can LLMs never do?"

wave_1 — Sat, 27 Apr 2024 20:49:00 +0000

Thanks. This is just in the labs stage, but moving closer to releasing it, exactly so that you can play with it! I have one angel investor involved in supporting this and it's intended for commercial applications in the para legal space, initially (controlled, structured environment) But you just gave me the motivation to "put it out there" so people can just play with it. It'll take a bit of time, but I will do a Show HN then when it's ready for people to play with. Otherwise, it would be just teasing people to talk about it on the main HN stage without giving access. Hold tight! And thanks again!

New comment by wave_1 in "What can LLMs never do?"

wave_1 — Sat, 27 Apr 2024 20:11:54 +0000

I build an Agentic AI that leverages #6 and #7 at the end of the article as well as techniques not yet published. It tackles hallucination relative not to the world at large but to the facts, entities and causal relationships contained in a document (which is really bad reasoning if we assume LLMs are "reasoning" to begin with) It also tackles cross-reasoning with very large token distance.

https://www.youtube.com/watch?v=99NPzteAz94

This is my first post on HN in 10 years.