Comment by tstrimple
25 days ago
> Whenever I feel stuck or overthink how to do something, just do it first - even with all the flaws that I'm already aware of, and if it feels almost painful to do it so badly. Then improve it a bit, then a bit, then before I know it a clear picture start to emerge... Feels like magic.
Funny how these things when done by a human is a positive and when done by an LLM is a negative. According to all the anti-llm experts... Humans generate perfect code on the first pass every time and it's only LLMs that introduce bad implementations. And this isn't a callout on this user in specific. It's a generalization to the anti-ai sentiment on HN. If incremental improvement works, incremental improvement works.
> Funny how these things when done by a human is a positive and when done by an LLM is a negative.
> Humans generate perfect code on the first pass every time and it's only LLMs that introduce bad implementations.
That's not what the "anti-llm experts" are saying at all. If you think of LLMs as "bad first draft" machines, then you'll likely be successful in finding ways to use LLMs.
But that's not what is being sold. Atman and Amodei are not selling "this tool will make bad implementations that you can improve on". They are selling "this tool will replace your IT department". Calling out that the tool isn't capable of doing that is not pretending that humans are perfect by comparison.