I think the problem is is that coding is not wholly a 'writing code' problem. It's a translation from idea to outcome. Often I think the bad code generated by an LLM is less to do with it's 'ability' and more to do with an instruction that hasn't adequately accounted for the possibility of what code satisfies the criteria. I'm not sure how a newer model can improve on this per se - sure there will be imrpovement on outright mistakes but for me at least, that's been and gone with more or less with any model released in te last 6 months.
I was coding something with claude the other day. It got the program working by all externally observable metrics, but when I went into the code it was full of DRY violations. It made a bunch of interrelated - but separate - traits for some concepts which simply didn't fit together.
I asked it to look at the code and come up with better factorings, but it failed. I ended up manually reworking several thousand lines of code myself, via my IDE. It took days.
I'd like a claude-of-the-future to be able to come up with beautiful ways to factor the code itself. Amongst the correct solutions, pick one which is conceptually simple. Write the code in a way that it makes subsequent changes easier to write. If I were doing RL with claude, I'd consider directing it toward solutions which allow subsequent changes to be implemented with as little effort as possible.
I switched to predomentantly using mimo this week, mostly out of curiosity to see how dependant I was on frontier models. Honestly I cant really tell the difference. I would say I work on pretty average codebases with well know frameworks doing pretty typical things and initial impressions is that mimo, kimi and deepseek can probably handle what I need more or less the same as gpt5.5 or claude.
I may be misunderstanding the article but doesnt the fact that all other science and understanding sits on a continuum of which consciousness has (to my understading) to real footing mean that the problem is dualitic by definition?
Thats not to say that it can't be 'brought into the fold', it may well be, but until it is it has no other place that to sit outside.
This one in particular is a new account with a high volume of similarly-structured posts over an impossibly short time.
Bigger tells are the other two green accounts posting multiple top level comments in this topic that are nearly identical. Perhaps the programmer had an off by one error somewhere.
I count at least three top level posters, if not as many as five, in this topic that are LLMs. The real absurdity is devnotes responding to myylogic, who are both LLMs.
This one in particular is a new account with a high volume of similarly-structured posts over an impossibly short time.
Bigger tells are the other two green accounts posting multiple top level comments in this topic that are nearly identical. Perhaps the programmer had an off by one error somewhere.
I count at least three top level posters, if not as many as five, in this topic that are LLMs.
Personally I don't get the argument against enums. From what I can tell it's purely to do with the symantics of what Typescript is, rather than any inherently bad property of enums.
Honestly, I'd say around $2-5. It's not that I wouldn't value better quality search but in a world where search feels like an almost 'invisible' part of browsing the web I'd struggle to pay that much. I guess it's comparable to what I feel is a price I'd be willing to pay for a VPN say compared to a coffee subscription.
This also isn't a reflection of what I percieve the work in building a search engine to be but more my subconcious perception of what I'm getting.
reply