Most active commenters
  • nojito(3)
  • roywiggins(3)

←back to thread

Coding with LLMs in the summer of 2025 – an update

(antirez.com)
600 points antirez | 14 comments | 20 Jul 25 11:04 UTC | HN request time: 0.283s | source | bottom
Show context
bgwalter ◴[20 Jul 25 13:59 UTC] No.44625261[source]▶
Translation: His company will launch "AI" products in order to get funding or better compete with Valkey.

I find it very sad that people who have been really productive without "AI" now go out of their way to find small anecdotal evidence for "AI".

replies(2): >>44625432 #>>44625574 #
brokencode ◴[20 Jul 25 14:18 UTC] No.44625432[source]▶
I find it even more sad when people come out of the woodwork on every LLM post to tell us that our positive experiences using LLMs are imagined and we just haven’t realized how bad they are yet.
replies(4): >>44625504 #>>44625551 #>>44625771 #>>44625799 #
1. cratermoon ◴[20 Jul 25 14:56 UTC] No.44625771[source]▶
We don't just tell you they were imagined, we can provide receipts.

https://metr.org/blog/2025-07-10-early-2025-ai-experienced-o...

replies(3): >>44625900 #>>44627683 #>>44629513 #
2. nojito ◴[20 Jul 25 15:08 UTC] No.44625900[source]▶
Cursor is an old way of using LLMs.

Not to mention in the study less than 1/2 have ever used it before the study.

replies(1): >>44625959 #
3. roywiggins ◴[20 Jul 25 15:15 UTC] No.44625959[source]▶
The AI tooling churn is so fast that by the time a study comes out people will be able to say "well they were using an older tool" no matter what tool that the study used.
replies(4): >>44625995 #>>44626051 #>>44630751 #>>44630786 #
4. cratermoon ◴[20 Jul 25 15:18 UTC] No.44625995{3}[source]▶
It's the eternal future. "AI will soon be able to...".

There's an entire class of investment scammers that string along their marks, claiming that the big payoff is just around corner while they fleece the victim with the death of a thousand cuts.

5. nojito ◴[20 Jul 25 15:23 UTC] No.44626051{3}[source]▶
Not really. Chatting with a llm was cutting edge for 3 years it’s only within the last 8-10 months with Claude code and Gemini cli do we have the next big change in how we interact with llms
replies(2): >>44626110 #>>44627479 #
6. roywiggins ◴[20 Jul 25 15:29 UTC] No.44626110{4}[source]▶
Claude Code was released in May.
replies(1): >>44626290 #
7. nojito ◴[20 Jul 25 15:44 UTC] No.44626290{5}[source]▶
Yup. But they are improvements over what cursor was releasing over the last year or so.
replies(1): >>44626339 #
8. roywiggins ◴[20 Jul 25 15:49 UTC] No.44626339{6}[source]▶
If there are paradigm-shattering improvements every six months, every single study that is ever released will be "behind" or "use an older tool." In six months when a study comes out using Claude Code, people dissatisfied with it will be able to point to the newest hotness, ad infinitum.
9. camdenreslink ◴[20 Jul 25 17:46 UTC] No.44627479{4}[source]▶
How is Claude Code and Gemini CLI any different from using Cursor in agent mode? It's basically the same exact thing.
replies(1): >>44627667 #
10. steveklabnik ◴[20 Jul 25 18:04 UTC] No.44627667{5}[source]▶
I can't speak to how they're technically different, but in practice, Cursor was basically useless for me, and Claude Code works well. Even with Cursor using Claude's models.
11. steveklabnik ◴[20 Jul 25 18:06 UTC] No.44627683[source]▶
> We do not provide evidence that:

> AI systems do not currently speed up many or most software developers

> We do not claim that our developers or repositories represent a majority or plurality of software development work

12. brokencode ◴[20 Jul 25 21:34 UTC] No.44629513[source]▶
Certainly an interesting result, but remember that a single paper doesn’t prove anything. This will no doubt be something studied very extensively and change over time as tools develop.

Personally, I find the current tools don’t work great for large existing codebases and complex tasks. But I’ve found they can help me quickly make small scripts to save me time.

I know, it’s not the most glamorous application, but it’s what I find useful today. And I have confidence the tools will continue to improve. They hardly even existed a few years ago.

13. bubblyworld ◴[21 Jul 25 00:39 UTC] No.44630751{3}[source]▶
What is the problem with this, exactly? It's a valid criticism of the study (when applied to current agentic coding practices). That the pace of progress is so fast sucks for researchers, in some sense, but this is the reality right now.
14. ◴[21 Jul 25 00:45 UTC] No.44630786{3}[source]▶