191–200 of 259 posts
I haven't seen the definition of an agent, in the paper. Do they differentiate agents from generic online chat interfaces?
An agent takes actions. Chat bots only return text.
You know what. After seeing all these articles about AI/LLM for these past 4 years, about how they are going to replace me as software developers and about how I am not productive enough without using 5 agents and being a project manager. I. Don't. Care. I don't even care about those debates outside. Debates about do LLM work and replace programmers? Say they do, ok so what? I simply have too much fun programming. I…
having fun isn't tied to employment unless you are self-employed even then what's fun should not be the driving force
Earlier quoted context omitted.
Also it really baffles me how many are actually in on the hype train. Its a lot more than the crypto bros back in the day. Good thing AI still cant reason and innovate stuff. Also leaking credentials is a felony in my country so I also wont ever attach it to my codebases.
I think the issue is folks talk past each other. People who find coding agents useful or enjoyable are labeled “on the hype train” and folks for which coding agents don’t work for them or their workflow are considered luddites. There are an incredible number of contradicting claims and predictions out there as well, and I believe what we see is folks projecting their reaction to some amalgamation of them onto others.…
Too many people are invested into AI's success to have a balanced conversation. Things will return to normal after a market shakedown of a few larger AI companies.
Earlier quoted context omitted.
25 years ago, I was slinging apps together super fast using VB6. It was awesome. It was a level of productivity few modern stacks can approach.
> 25 years ago, I was slinging apps together super fast using VB6. It was awesome. It was a level of productivity few modern stacks can approach. If that were too, wouldn't we all be using VB today?
This is pretty recent - the survey they ran (99 respondents) was August 18 to September 23 2025 and the field observations (watching developers for 45 minute then a 30 minute interview, 13 participants) were August 1 to October 3. The models were mostly GPT-5 and Claude Sonnet 4. The study was too early to catch the 5.x Codex or Claude 4.5 models (bar one mention of Sonnet 4.5.) This is notable because a lot of acade…
This is a recurring argument which I don't understand. Doesn't it simply mean that whatever conclusion they did was valid then? The research process is about approximating a better description of a phenomenon to understand it. It's not about providing a definitive answer. Being "an entire model generation" behind would be important if fundamental problems, e.g. no more hallucinations, would be solved but if it's going from incremental changes then most likely the conclusions remain correct. Which fundamental change (I don't think labeling newer models as "better" is sufficient) do you believe invalidate their conclusions in this specific context?
I often tell people that agentic programming tools are the best thing since cscope. The last 6 months I have not used cscope even once after decades of using it nearly daily. [0] https://en.wikipedia.org/wiki/Cscope
Out of curiosity, if I wanted to setup cscope for a bunch of small projects, say dozens of prototypes in their own directory, would it be useful? Too broad?
This is pretty recent - the survey they ran (99 respondents) was August 18 to September 23 2025 and the field observations (watching developers for 45 minute then a 30 minute interview, 13 participants) were August 1 to October 3. The models were mostly GPT-5 and Claude Sonnet 4. The study was too early to catch the 5.x Codex or Claude 4.5 models (bar one mention of Sonnet 4.5.) This is notable because a lot of acade…
I knew in October the game had changed. Thanks for keeping us in the know.
Earlier quoted context omitted.
What's the difference between using llms now vs the first half of 2025 among the best users?
Coding agents and much better models. Claude Code or Codex CLI plus Claude Opus 4.5 or GPT 5.2 Codex. The latest models and harnesses can crunch on difficult problems for hours at a time and get to working solutions. Nothing could do that back in ~March. I shared some examples in this comment: https://news.ycombinator.com/item?id=46436885
Those crunching hard problems will still review what's produced in search of issues.