LLMs are still surprisingly bad at some simple tasks
LLM-Deflate: Extracting LLMs into Datasets
You're not using LLMs enough
These psychological tricks can get LLMs to respond to “forbidden” prompts
Poisoning Well
The maths you need to start understanding LLMs
LLMs easily exploited using run-on sentences, bad grammar, image scaling
Accelerating life sciences research
Forget data labeling: Tencent’s R-Zero shows how LLMs can train themselves
Some thoughts on LLMs and software development
LLMs solving problems OCR+NLP couldn't
One Long Sentence is All It Takes To Make LLMs Misbehave
One long sentence is all it takes to make LLMs misbehave
Apple study shows LLMs also benefit from the oldest productivity trick in the book (Checklists Are Better Than Reward Models For Aligning Language Models)
Making games in Go: 3 months without LLMs vs. 3 days with LLMs
Tinker with LLMs in the privacy of your own home using Llama.cpp
ThinkMesh: A Python lib for parallel thinking in LLMs
