How useful is llms.txt? It's so useful that Tailwind rejected a PR to add an llms.txt, on the basis that it would be so useful that people wouldn't need to read their docs any more! https://
github.com/tailwindlabs/t
ailwindcss.com/pull/2388
…
@jeremyphoward
-
Tailwind Rejects llms.txt PR for Being Too Useful
By
–
-
Three.js and Major Libraries Adopt llms.txt Standard
By
–
Great to see @threejs supporting llms.txt. I have noticed that the majority of libs/services I work with nowadays seem to have an llms.txt nowadays. Makes me happy! (I've been really enjoying the very comprehensive @GeminiApp llms.txt recently for writing Gemini code.)
-
LoRA Efficiency for Specific AI Tasks and Datasets
By
–
No not the opposite – they just looked at a particular subsets of tasks, datasets, and metrics. There are some things that LoRA is sufficient for.
-
Hyperparameters Remain Stable Across Model Scales
By
–
Hyperparams and architectures are *far* more stable across model and data sizes than most people think. For stuff that does need to change, we have pretty reliable rules of thumb for nearly all of them. (eg: OpenAI did nearly all their GPT4 ablations on ~1000x smaller models.)
-
DoRA vs LoRA: Choosing the Better Fine-tuning Method
By
–
I am once again asking for your support of DoRA. Friends don't let friends use LoRA. Use DoRA and make 2026 a good year.
-
Publishing Barriers for Experimental AI Research Observations
By
–
Thanks for sharing – very well said 🙂
It's really sad that experimental observations have always been nearly impossible to publish in AI/ML journals and conferences, and has definitely held back the field. -
Training on Test Labels vs Inputs: ARC Benchmark Ethics
By
–
Training on test refers to using the *labels* in the test set. Not the *inputs*. Including test inputs is standard common in semi-supervised/self-supervised. Whether or not this approach is against the ARC rules, I don't know. But it is *not* what "training on test" means.
-
Unsupervised Learning Confusion: Training on Test Data Explained
By
–
Man discovers unsupervised learning and confuses it with what "training on test" actually means.
-
LLM API Learning Performance and Training Challenges
By
–
I forked the dialog and tried to help the LLM learn and use the API, but it still did pretty badly: https://
share.solve.it.com/d/cb0c3b8d182b
040de1b20a078b04ec98
… -
Frontier LLMs Struggle with Platonic Solid Net Generation
By
–
Interesting (and surprising to me) discovery from one of our Solveit students: it turns out that frontier LLMs (or @AnthropicAI Opus 4.5 at least) can't create nets for platonic solids, when given a simple API. E.g here's its attempt at a tetrahedron: