Hacker News Reader

Comment by causal | Hacker News Reader

Strong disagreement on the helpfulness of the name- if anything calling a context file a skill is really misleading. It evokes something like a LoRA or pluggable modality. Skill is the wrong name imo

View on HN

I think skill is the perfect name for this. You provide the LLM with a new skill by telling it how to do a thing and providing supporting scripts to help it do that thing.

Yup! I fully agree. It also taps into the ability of LLMs to write code given good prompts. All you need is for the LLM to recognize that it needs something, fetch it into the context, and write exactly the code that is needed in the current combination of skill + previous context.

You've described instructions. It already had a name.

"Instructions" doesn't cover the bit where you have a folder with markdown with YAML frontmatter metadata plus additional executable scripts - which can then be shared with others.

IMO LoRAs are no different from context tokens. In fact, before LoRAs tuned prompt vectors were a popular adapter architecture. Conceptually, the only difference is that prompt adapters only interact with other tokens through the attention mechanism while LoRAs allow you to directly modify any linear layer in the model. Essentially, you can think of your KV cache as dynamically generated model weights. Moreover, I can't find the paper, but there is some evidence that in-context learning is powered by some version of gradient descent inside the model.

LoRA's are more robust than context tokens - their influence remains strong over long contexts and do a much better job of actually changing behavior rather than mimicking a desired behavior via instruction.

But even if LoRA isn't it - the point is that "skill" seems like the wrong term for something that already has a name: instructions. These are instruct-tuned models. Given instructions they can do new things; this push to rebrand it as a "skill" just seems like marketing.

Reply on news.ycombinator.com