Hacker News: llmslave2https://news.ycombinator.com/user?id=llmslave2Hacker News RSShttps://hnrss.org/hnrss v2.1.1Sat, 23 May 2026 02:00:30 +0000<![CDATA[New comment by llmslave2 in "My article on why AI is great (or terrible) or how to use it"]]>[flagged]

]]>Fri, 09 Jan 2026 20:58:10 +0000https://news.ycombinator.com/item?id=46559230llmslave2https://news.ycombinator.com/item?id=46559230https://news.ycombinator.com/item?id=46559230<![CDATA[New comment by llmslave2 in "AI coding assistants are getting worse?"]]>> while a different set of skills are improving (the skill of getting an LLM to produce functional output

Lmaooooo

]]>Fri, 09 Jan 2026 20:39:03 +0000https://news.ycombinator.com/item?id=46559018llmslave2https://news.ycombinator.com/item?id=46559018https://news.ycombinator.com/item?id=46559018<![CDATA[New comment by llmslave2 in "My article on why AI is great (or terrible) or how to use it"]]>Yep. I'd say it's an order of magnitude more effort to read code you haven't written too, compared to reading code you wrote. So there is approximately zero chance the people using AI to generate code are reading it at a level where they actually understand it, or else they would lose all of their supposed productivity gains.

]]>Fri, 09 Jan 2026 20:32:07 +0000https://news.ycombinator.com/item?id=46558939llmslave2https://news.ycombinator.com/item?id=46558939https://news.ycombinator.com/item?id=46558939<![CDATA[New comment by llmslave2 in "My article on why AI is great (or terrible) or how to use it"]]>I actually don't think they would agree with most of this. Why would you think that?

]]>Fri, 09 Jan 2026 20:30:34 +0000https://news.ycombinator.com/item?id=46558920llmslave2https://news.ycombinator.com/item?id=46558920https://news.ycombinator.com/item?id=46558920<![CDATA[New comment by llmslave2 in "My article on why AI is great (or terrible) or how to use it"]]>Good news: the evidence points to it being slower than non-ai workflows. So we're destroying our economy, society, and planet to make worse software, more slowly! :)

]]>Fri, 09 Jan 2026 20:23:47 +0000https://news.ycombinator.com/item?id=46558815llmslave2https://news.ycombinator.com/item?id=46558815https://news.ycombinator.com/item?id=46558815<![CDATA[New comment by llmslave2 in "My article on why AI is great (or terrible) or how to use it"]]>I thought the article was going to be about AI zealotry but it was just AI zealotry.

]]>Fri, 09 Jan 2026 20:22:34 +0000https://news.ycombinator.com/item?id=46558802llmslave2https://news.ycombinator.com/item?id=46558802https://news.ycombinator.com/item?id=46558802<![CDATA[New comment by llmslave2 in "Anthropic blocks third-party use of Claude Code subscriptions"]]>ensloppification

]]>Fri, 09 Jan 2026 10:24:50 +0000https://news.ycombinator.com/item?id=46552234llmslave2https://news.ycombinator.com/item?id=46552234https://news.ycombinator.com/item?id=46552234<![CDATA[New comment by llmslave2 in "Anthropic blocks third-party use of Claude Code subscriptions"]]>[flagged]

]]>Fri, 09 Jan 2026 10:19:17 +0000https://news.ycombinator.com/item?id=46552198llmslave2https://news.ycombinator.com/item?id=46552198https://news.ycombinator.com/item?id=46552198<![CDATA[New comment by llmslave2 in "Anthropic blocks third-party use of Claude Code subscriptions"]]>Anthropic developers run 10 Claude Code instances at once, with unlimited access to the best models.

]]>Fri, 09 Jan 2026 10:15:45 +0000https://news.ycombinator.com/item?id=46552172llmslave2https://news.ycombinator.com/item?id=46552172https://news.ycombinator.com/item?id=46552172<![CDATA[New comment by llmslave2 in "Anthropic blocks third-party use of Claude Code subscriptions"]]>[flagged]

]]>Fri, 09 Jan 2026 10:08:33 +0000https://news.ycombinator.com/item?id=46552112llmslave2https://news.ycombinator.com/item?id=46552112https://news.ycombinator.com/item?id=46552112<![CDATA[New comment by llmslave2 in "AI coding assistants are getting worse?"]]>I'm sorry but I'm not going to take "research" about Claude seriously from Anthropic, the company who makes and sells Claude. I'm also not going to do that for Copilot from Microsoft, the company who makes and sells Copilot.

]]>Fri, 09 Jan 2026 08:00:32 +0000https://news.ycombinator.com/item?id=46551182llmslave2https://news.ycombinator.com/item?id=46551182https://news.ycombinator.com/item?id=46551182<![CDATA[New comment by llmslave2 in "AI coding assistants are getting worse?"]]>But useful in the context of these debates isn't that it solves any single problem for someone. Nobody is arguing that LLM's have zero utility. So I don't really see what your point is?

]]>Fri, 09 Jan 2026 07:59:20 +0000https://news.ycombinator.com/item?id=46551176llmslave2https://news.ycombinator.com/item?id=46551176https://news.ycombinator.com/item?id=46551176<![CDATA[New comment by llmslave2 in "AI coding assistants are getting worse?"]]>Yeah this is the key point. Part of me wonders if it's just 0.1x devs somehow reaching 1.0x productivity...

]]>Fri, 09 Jan 2026 07:55:36 +0000https://news.ycombinator.com/item?id=46551152llmslave2https://news.ycombinator.com/item?id=46551152https://news.ycombinator.com/item?id=46551152<![CDATA[New comment by llmslave2 in "AI coding assistants are getting worse?"]]>[flagged]

]]>Fri, 09 Jan 2026 07:53:59 +0000https://news.ycombinator.com/item?id=46551140llmslave2https://news.ycombinator.com/item?id=46551140https://news.ycombinator.com/item?id=46551140<![CDATA[New comment by llmslave2 in "AI coding assistants are getting worse?"]]>Yeah

]]>Fri, 09 Jan 2026 05:39:58 +0000https://news.ycombinator.com/item?id=46550433llmslave2https://news.ycombinator.com/item?id=46550433https://news.ycombinator.com/item?id=46550433<![CDATA[New comment by llmslave2 in "AI coding assistants are getting worse?"]]>more code = better software

]]>Fri, 09 Jan 2026 02:21:03 +0000https://news.ycombinator.com/item?id=46549396llmslave2https://news.ycombinator.com/item?id=46549396https://news.ycombinator.com/item?id=46549396<![CDATA[New comment by llmslave2 in "AI coding assistants are getting worse?"]]>I've seen some interesting work going the other way, having LLMs generate constraint solvers (or whatever the term is) in prolog and then feeding input to that. I can't remember the link but could be worthwhile searching for that.

]]>Fri, 09 Jan 2026 02:14:36 +0000https://news.ycombinator.com/item?id=46549347llmslave2https://news.ycombinator.com/item?id=46549347https://news.ycombinator.com/item?id=46549347<![CDATA[New comment by llmslave2 in "AI coding assistants are getting worse?"]]>They're all marketing slop lol. Go look at their methodology. Absolutely shite.

]]>Fri, 09 Jan 2026 01:59:56 +0000https://news.ycombinator.com/item?id=46549237llmslave2https://news.ycombinator.com/item?id=46549237https://news.ycombinator.com/item?id=46549237<![CDATA[New comment by llmslave2 in "AI coding assistants are getting worse?"]]>I actually prefer no syntax highlighting, and I certainly wouldn't make any claims about it being useful. But something being "useful" is often personal - I find IDEs useful, others find Vim useful, maybe one is better or worse than the other or maybe we're all different and our brains function in different ways and that explains the difference.

With assembly versus say, Go for writing a web server? That's trivially observable, good luck arguing against that one.

]]>Fri, 09 Jan 2026 01:37:58 +0000https://news.ycombinator.com/item?id=46549094llmslave2https://news.ycombinator.com/item?id=46549094https://news.ycombinator.com/item?id=46549094<![CDATA[New comment by llmslave2 in "AI coding assistants are getting worse?"]]>Theo is the type of programmer where you don't care when he boos you, because you know what makes him cheer.

]]>Fri, 09 Jan 2026 01:04:47 +0000https://news.ycombinator.com/item?id=46548840llmslave2https://news.ycombinator.com/item?id=46548840https://news.ycombinator.com/item?id=46548840