Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The last six months in LLMs in five minutes

simonwillison.net

Post reply on HN
Print view View original

531–540 of 631 posts

Re: The last six months in LLMs in five minutes

#531

Post by pprotas »

kstenerud wrote: post #371
andai wrote: post #364

Earlier quoted context omitted.

I think you can fix that by setting an environment variable (regarding the terminal?) but it was a while since I checked. (I was running Claude as a subprocess and had similar issues.) Also this reminds me of a principle I learned from a mentor. "People are visual buyers. If it looks good, people will think the code is good." Unfortunately it doesn't matter whose fault the janky TUI is, people will see that and assoc…

It's more along the lines of: Anyone with an axe to grind will find something to grind it on. Early stage products will have some rough edges. We've seen that in Docker, Kubernetes, AWS, Azure, LXC, KVM, etc. And people griped and raged about the sheer incompetence of the maintainers and utter lack of quality, but they still used those tools even before the rough edges were polished away and folks finally settled dow…

"This is, unfortunately, how narcissists behave. It's simply impossible for a narcissist to be wrong. They truly believe themselves to be right, all the time, and will even distort reality around them to "make" it true. And they do it all unconsciously." - kstenerud

Re: The last six months in LLMs in five minutes

#533

Post by Miraste »

hollowturtle wrote: post #507
epolanski wrote: post #502

Earlier quoted context omitted.

Half the projects I listed are system's programming related. In general you do seem to be unaware of the trend. And I want to stress it out: I'm not stoked for the trend or changes, but I'm not blind either.

> Half the projects I listed are system's programming related. No they're not and those who are, are in overwhelming control by the engineers that steer continuously the agents in the right direction. First of all this isn't something you can do for novel ideas, especially in gaming, second it is indeed very bad the code they produce otherwise it won't require that much effort from high end professionals to bend the…

What novel ideas are you thinking of? In my experience there are very few games with novel software engineering. New gameplay mechanics or story or art or design, sure, but they're generally built with very old and standardized patterns.

Re: The last six months in LLMs in five minutes

#535

Post by opto »

hug wrote: post #448
opto wrote: post #376

Earlier quoted context omitted.

I mean only that I see no use for it myself, in my own work. I'm sure there are people working in roles around me who believe they get some use out of AI doing their work for them, and they will have to answer to auditors when they find problems with their work, or when someone is killed. To me, as a non-techie person, it feels as if people who work in software believe that because their work can be done by AI, every…

I don't mean to tar you with a too-wide brush, and I feel like you have a good handle on your personal acceptance for LLM assistance. No complaint there. I do think, maybe alternative to your view, that LLMs can provide useful feedback to graduate-level employees in most fields. It is not that the work can be done by LLMs -- we're not there, yet, in software or otherwise -- but that LLMs as useful tutors specifically…

What does that really mean though — ten more years of data centers exploiting local communities for their resources will mean that a computer might be able to teach people to tie knots, and reliably check their work... No government would allow that to certify someone, and no company would risk the lawsuit when someone dies doing what the AI tells them, so it's a non-starter. Even if it were possible, and governments got on board with certifying training like that, would anyone think this was better than what we have now?

What are the likely use cases in my industry then? That AI is used to bodge the important paperwork that protects lives; is used to draft legislation; is used by both employees and management to do things like personal development reports.

Is anyone meant to be impressed? Is this worth communities having their water stolen from them?

I appreciate I am skeptical, but it is hard not to be when the world spends all day telling you a piece of technology is going to fundamentally change the world, and in real life you only see people use it to blag CVs, personal reports, and lesson planning.

Re: The last six months in LLMs in five minutes

#536

Post by draftsman »

oooyay wrote: post #506
kstenerud wrote: post #389

Earlier quoted context omitted.

The issue is likely that the tmux session being generated is for some reason not propagating all term caps. Most likely it's an interop issue between tmux and docker and the image running under docker - possibly even something with the terminal client that the pipeline doesn't like somewhere. Claude Code correctly reduces its display to 7-bit ASCII in response (still functional, although less pretty). Once I get arou…

What's really interesting in this comment chain is an observation I've expressed a lot more lately. When someone knows an LLM was involved they raise their expectations. I do it too in my own work and I have to remind myself things like "this bug would've also likely occurred with a human working at this level of complexity." The real question is did the operator arbitrarily and knowingly increase the level of comple…

And there’s good reason for that. Anthropic, OpenAI, Salesforce, and so on have aggressively marketed LLMs as better than humans at working. It’s no surprise when we find out something is build using an LLM, we expect it to match the marketing.

Re: The last six months in LLMs in five minutes

#537

Post by breuleux »

freedomben wrote: post #460
kstenerud wrote: post #427

Earlier quoted context omitted.

You consider adding in-place constructed items to an array to be code duplication?

I've noticed that the bar for "quality" when people judge AI is often significantly higher than what they'd hold a human to. I'm not saying GP et al are doing this (I haven't looked myself), but it is a widespread pattern I've noticed both professionally and personally. I don't know why it is.

People who use AI set the bar themselves when they claim they generate "very high quality work using Claude". Humans more rarely make such claims about the code they write themselves, but when they do, I expect they face similar scrutiny.

AI code is competent, but it's not great or high quality unless you have a good enough eye for quality to steer it with an iron hand. But if you do, you know the quality comes from proper guidance, so you still wouldn't say AI code is great. If you do say exactly that, it comes across as having low standards (which is fine if you own it) and people are going to jump on that just to bring you down a peg.

Re: The last six months in LLMs in five minutes

#538

Post by ThrowawayR2 »

freedomben wrote: post #460
kstenerud wrote: post #427

Earlier quoted context omitted.

You consider adding in-place constructed items to an array to be code duplication?

I've noticed that the bar for "quality" when people judge AI is often significantly higher than what they'd hold a human to. I'm not saying GP et al are doing this (I haven't looked myself), but it is a widespread pattern I've noticed both professionally and personally. I don't know why it is.

> "I've noticed that the bar for 'quality' when people judge AI is often significantly higher than what they'd hold a human to."

Because that is literally the hype being fed to us by the marketers at the AI companies and HN users promoting AI.

- AI promoters: "AI is doing Ph.D level work! LLMs are not just a token predictor, it is actually thinking and reasoning! It will replace all developers, including _you_, so get on board the AI hype train now!"

- AI promoters when confronted with blatant mistakes and reasoning errors from cutting edge models: "Why are you holding LLMs up to higher standards than humans? That's not fair or reasonable."

Re: The last six months in LLMs in five minutes

#539

Post by NortySpock »

gib444 wrote: post #89

Starting from zero today, how would someone quickly get upto speed with the latest and greatest AI tooling on an extremely limited budget? Is the only choice to pay for the "max" plans? Or just read so much about it that you bs your way through an interview and then use the company's resources? Simon, I'm curious too how much you invest each month researching all the latest and great AI tech?

I made an account on OpenRouter.ai , created an API key, plugged the API key into the Zed editor, and started asking free models questions about my codebase.

Once I felt I had some confidence on what the spend rate would be, I bought $20 USD worth of credits and would occasionally point my editor at a cheap paid model for some real-time questions.

I've still only spent less than $2 in credits so far, as often a free model can answer my question fast enough.

I have not yet tried agentic coding, but at least with OpenRouter API keys it's trivial to cost-cap keys so you can pay for lower latency and still cap your spending.

Re: The last six months in LLMs in five minutes

#540

Post by kstenerud »

draftsman wrote: post #536
oooyay wrote: post #506

Earlier quoted context omitted.

What's really interesting in this comment chain is an observation I've expressed a lot more lately. When someone knows an LLM was involved they raise their expectations. I do it too in my own work and I have to remind myself things like "this bug would've also likely occurred with a human working at this level of complexity." The real question is did the operator arbitrarily and knowingly increase the level of comple…

And there’s good reason for that. Anthropic, OpenAI, Salesforce, and so on have aggressively marketed LLMs as better than humans at working. It’s no surprise when we find out something is build using an LLM, we expect it to match the marketing.

But what constitutes "better than humans at working"?

Zero defects? Because you can always find at least one defect. But people don't naturally think statistically, so they grasp the thing that confirms their bias and then hang on tenaciously.

You'll notice the incredible amount of vitriol resulting from a purely cosmetic bug (which, it turns out, results from a missing TERM env in the base image - Claude is very conservative when it can't determine utf-8 support with 100% certainty).

Post reply on HN