196
AI chatbots tend to choose violence and nuclear strikes in wargames
(www.newscientist.com)
This is a most excellent place for technology news and articles.
If that's really how they work, it wouldn't explain these:
https://notes.aimodels.fyi/researchers-discover-emergent-linear-strucutres-llm-truth/
https://notes.aimodels.fyi/self-rag-improving-the-factual-accuracy-of-large-language-models-through-self-reflection/
https://adamkarvonen.github.io/machine_learning/2024/01/03/chess-world-models.html
https://poke-llm-on.github.io/
https://arxiv.org/abs/2310.02207
Yes. There is self organization and possibility to self reflection going on in something that wasn't designed for it. That's going to spawn a lot more research.
I will read those, but I bet "accidentally good enough to convince many people." still applies.
A lot of things from LLM look good to nonexperts, but are full of crap.
https://poke-llm-on.github.io/
Reinforcement learning. Cool project. Still no need to "know" anything. I usually play this type of have with short rules and monitoring the current state.
https://arxiv.org/abs/2310.02207
2 author paper with interesting evidence. Again, evidence not proof. Wait for the papers that cite this one.
https://adamkarvonen.github.io/machine_learning/2024/01/03/chess-world-models.html
Author later discusses training on you data versus general datasets.
I am out of my depth, but does not seem to provide strong evidence for the modem not just repeating information that shows up a lot for the given inputs.
https://notes.aimodels.fyi/self-rag-improving-the-factual-accuracy-of-large-language-models-through-self-reflection/
A cool paper. Using the LLM to judge value of new inputs.
I am always skeptical of summaries of journal articles. Even well meaning people can accidentally distort the conclusions.
Still LLM is a bullshit generator that can check bullshit level of inputs.
https://notes.aimodels.fyi/researchers-discover-emergent-linear-strucutres-llm-truth/
References a 2 author paper. I am not an expert in the field, but it is important to read the papers that reference this one. Those papers will have criticisms that are thought out. In general, fewer authors means less debate between the authors and easier to miss details.