Viewing profile — llmslave2
llmslave2
HN member- Joined
- Thu, Dec 18, 2025, 8:03 PM UTC
- HN karma
- 1,096
- Public activity
- 356 items
- HN profile
- View on Hacker News ↗
About llmslave2
No profile information was provided.
Recent public activity
-
comment
Comment #46559230
[flagged]
-
comment
Comment #46559018
> while a different set of skills are improving (the skill of getting an LLM to produce functional output Lmaooooo
-
comment
Comment #46558939
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…
-
comment
Comment #46558920
I actually don't think they would agree with most of this. Why would you think that?
-
comment
Comment #46558849
[dead]
-
comment
Comment #46558815
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! :)
-
comment
Comment #46558802
I thought the article was going to be about AI zealotry but it was just AI zealotry.
-
comment
Comment #46552234
ensloppification
-
comment
Comment #46552198
[flagged]
-
comment
Comment #46552172
Anthropic developers run 10 Claude Code instances at once, with unlimited access to the best models.
-
comment
Comment #46552155
[flagged]
-
comment
Comment #46552112
[flagged]
-
comment
Comment #46551182
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 Microso…
-
comment
Comment #46551176
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 poin…
-
comment
Comment #46551152
Yeah this is the key point. Part of me wonders if it's just 0.1x devs somehow reaching 1.0x productivity...
-
comment
Comment #46551140
[flagged]
-
comment
Comment #46550433
Yeah
-
comment
Comment #46549396
more code = better software
-
comment
Comment #46549347
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 th…
-
comment
Comment #46549237
They're all marketing slop lol. Go look at their methodology. Absolutely shite.
-
comment
Comment #46549094
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, other…
-
comment
Comment #46548840
Theo is the type of programmer where you don't care when he boos you, because you know what makes him cheer.
-
comment
Comment #46548812
Do you just believe everything everybody says? No quantifiable data required, as long as someone somewhere says it it must be true? One of the reasons software is in decline is bec…
-
comment
Comment #46548718
If you point a spectrometer at the sky during the day in non-cloudy conditions you will observe readings peaking in the roughly 450-495 nanometers range, which crazily enough, is t…
-
comment
Comment #46548534
Paste this conversation into ChatGPT and have it explain what I said because I just can't be arsed to correct you any longer.