Ask HN: Will LLMs hurt adoption of new frameworks and technology?
2 points
13 days ago
| 1 comment
| HN
If I ask some LLM/GPT a react question I get good responses. If I ask it about a framework released after the training data was obtained, it will either not know or hallucinate. Or if it's a lesser known framework the quality will be worse than for a known framework. Same with other things like hardware manuals not being trained on yet etc.

As more and more devs rely on AI tools in their work flows, will emerging tech have a bigger hurdle than before to be adopted? Will we regress to the mean?

unraveller
13 days ago
[-]
In the short term obviously yes, I can already feel myself veering away from new things that have @unstableAPIs.

The framework designer may have to design for users and LLM teachers this time. Designers should make it so logical jumps aren't to big like kotlin was back in the day and lagged in all code LLMs metrics until they made synthetic steps to "explain" it to the LLM.

You can always add in the docs as RAG context later, maybe with an LLM synthetic booster explainer segment.

reply