How do you make that assessment? I'll admit, the knowledge base is not 10x every few months anymore, but the agent capabilities keep getting better. The newer models can do a lot of useful work accurately for a while. That wasn't true several months ago.
Wake me up when they solve hallucination.
LLMs, maybe. AI? Hardly.
>AI? Hardly.
what are some examples of 'hardly' ?
There are a ton of big examples of advances across all subfields of AI over the last year, but the first one that came to my mind was AlphaGeometry2 [0], which combines Gemini with a symbolic agent to solve (offer proofs for) the vast majority of IMO geometry problems. I believe that this sort of approach can be applied to many other types of problems.
There's a serious issue around naming here, I'll agree.
I assume "AI" in contemporary articles, especially as it pertains to investments, means "Generative AI, especially or exclusively LLMs."
In this case it means research, as it pertains to universities.
This is about "AI for science" and I don't think LLMs are the biggest deal there. Alphafold is maybe the best AI science so far and it isn't a language model.