Can I ask a dumb question as an LLM newbie? What is it about Claude that makes it so good at basic software engineering tasks? Do you think it was finely tuned to be good at these tasks? No joke/trolling: A bunch of people have posted on HN in the last 6 months about creating MVPs (Minimum Viable Products) -- usually web apps -- using Claude. As a non-web-app programmer, I think this is amazing progress!

I think it understands the context better and it was possibly fine tuned better. I have been using GPT since 3 and while the replies have obviously gotten more accurate, it still makes weird assumptions at times, whereas Claude seems to "get it" more often. In tasks other than coding, I've found gpt to be more detailed by default and yet Claude seems to hit the mark better.

IMO it was just the strongest model for awhile for programming. It got the answers right more often than not.

It is faster than the reasoning/chain of thought models. With current o1 and DeepSeek though I haven't logged into Claude in a few weeks.

I have no inside knowledge but I am kind of expecting Sonnet chain of thought any day now and I am sure that will be incredible.

This is gonna sound strange but:

Anthropic's llms always (always? at least since 2) have a distinctive "personality". I obv don't know how to quantify it or what "it" really is, but if you've used it you might know what I mean. Maybe that "personality" is conducive to swe?

Fair, but do you think OpenAI and Gemini are going to be like directionally similar? How much of OpenAI's traffic is from Co-Pilot and other related tools, for example. My local IDE probably generates more queries a day than (pick a profession, idk, nurse? insurance sales? construction worker?) does in a month!

I would be pretty shocked if the Anthropic reasoning model is not mind blowing and doesn't take the lead back.