I posted a few days ago about Sakana AI's fully automated scientific agent "The AI Scientist", which I think is really promising : it's nice to now see that Sakana is building explosive momentum!
LLMS
-
Multi-LLM prompt testing and model selection behavior
By
–
I caught myself copy/pasting the same initial prompt into three chat LLMs and then just picked my favorite and started chatting with that one
-
Softmax projection and difficulty of learning additions in embeddings
By
–
Each one still has the softmax issue though and it all gets turned into one vector at the end. Learning to do addition in that projection feels hard, but I don’t know enough to say it can’t happen
-
Question about softmax invariance and matching counts
By
–
I know there’s no integer count; my read was that softmaxing makes it invariant to the number of matches so it has to rely on other less reliable methods but I could well be misunderstanding that point; reading again now
-
Cursor should read llms.txt file by default
By
–
Yeah it would be great if Cursor read /llms.txt by default.
-
LLM Evaluations Grant Proposals Open Until September 6th
By
–
We're still accepting proposals for our LLM Evaluations Grant until this Friday, September 6th — recipients will get $200K in funding to support this work. More details https://
go.fb.me/82ft4d -
When LLMs Should Use Code
By
–
Everyone acknowledges that code is the correct way to solve this. It’s still worth understanding why that’s necessary, and more practically for LLMs to understand *when* that’s necessary.
-
Paper on limitations of counting in single-token inference
By
–
Yes — and you can often achieve much more reliable counting by repeating an input a second time annotated with a running total, but that’s expensive and context-constrained; this paper is about limitations on counting directly in a single token inference
-
Why Transformers Struggle to Count, According to a Paper
By
–
The reason LLMs say there's two r's in "strawberry" isn't (just) tokenization — they struggle with counting generally, e.g. "horse" in the example shown. The paper in the quoted post below offers the best intuition I've seen for why this happens: Transformers can't count because
-
Feeding False Information to LLMs via Website Configuration
By
–
If you can modify the website to add a /llms.txt then you can already feed LLMs false information. But I don't see why you'd want to do that about your own website.