[tj-teej]

If anyone is curious, a Meta Data Scientist published a great piece about how the facts about what LLMs are actually doing (and therefore able to do) and how it's papered over by using chat bots. It's a long but very engaging read.

https://medium.com/@colin.fraser/who-are-we-talking-to-when-...

[grey-area]

Great article which really explores why we fall for llms and think they are doing a lot more thinking than they are.Thanks.

[non_sequitur]

this is a good article but very outdated - none of the examples he cites are relevant anymore

[tivert]

That article is fantastic.

[rahimnathwani]

This article is long but doesn't mention key concepts like instruction tuning.

I'd suggest the Llama paper as a more worthwhile source.

[grey-area]

It does talk about openai explicitly instruction tuning the llm to try to constrain the output and the limitations of such approaches.