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

491–500 of 631 posts

Re: The last six months in LLMs in five minutes

#491

Post by kamaal »

Glohrischi wrote: post #423
hollowturtle wrote: post #275

Earlier quoted context omitted.

First of all it just underlines how shitty the web has become, second If that's your work I'd chase a career path where Claude can't one-shot this kind of dumb stuff

Thats quite a surprisingly arrogant take. CRUD applications and converting business requirements into code is the thing software developers do to 99% day in day out.

If you break down a complicated coding problem in smaller parts, it could be any problem.

You will see its basically a very reusable part thats already done uncountable times else where.

People who think they do something so special and novel that it just can't be done by non-human, struggle with breaking down a problem in smaller parts.

Even if you do have such novel problems, its not like every single day, every single bit of work you do is like that.

Re: The last six months in LLMs in five minutes

#492

Post by rm_-rf_slash »

sigmoid10 wrote: post #315
GistNoesis wrote: post #285

Last 6 months is humanity losing control of LLMs. - Memory market cornering which mitigated the adoption of local AI despite great open model being released. - Fast penetration of IP exfiltrating tools in companies world-wide. - Developers producing more code that they can read. - Autonomous agents killing Open Source by siphoning the attention economy - Autonomous agents destroyed online communities (including HN) -…

If you only read bad news (i.e. mass news these days since that sells better) this will be the picture. But I have personally seen some insane stuff happen in biotech. Like, I can't believe we're lucky enough to possibly live our life in this kind of future. We already have actual therepeutics developed using Alphafold being tested right now in real clinical trials, but the next generation of stuff that will go into…

My mother is going on 5 years with multiple myeloma, a cancer that would have offed her in 5 months if it weren’t for advances in maintenance chemotherapy.

Medicine has done amazing things in my lifetime.

Re: The last six months in LLMs in five minutes

#493

Post by embedding-shape »

knollimar wrote: post #453
embedding-shape wrote: post #359

Earlier quoted context omitted.

> Take it up with Anthropic. It's actually their billion-dollar TUI product you're commenting on. That's like blaming the company making hammers because you're unable to build a lasting house with the hammer, it really isn't up to Anthropic, but all about how you use the tool you're holding.

Do they also hold their hammer wrong when their TUI flickers for months?

That's just poor engineering, product building and testing, same can happen with/without LLMs, no doubt.

Re: The last six months in LLMs in five minutes

#494

Post by mrothroc »

rTX5CMRXIfFG wrote: post #12

Am I crazy, or are these differences between the best models so marginal that you’d get roughly the same performance if you use the same high-quality harness (ie preloaded instructions from md files, including custom skills)?

I have the same experience. I've been running sequential agents in my own harness that is a standard SDLC pipeline (plan, design, code, build, test). It has gates between each stage to control quality.

The big benefit of automating this for so long is that I have lots of data. I analyzed it and found that I can change the models out without much of a change in the output quality.

For one-off tasks, where there is no harness and you're just YOLOing with the TUI, yes, big difference. You need a harness.

The pipeline controls the quality far more than the model, empirically.

Re: The last six months in LLMs in five minutes

#495

Post by kstenerud »

sjagauanbdvva wrote: post #478
kstenerud wrote: post #454

Earlier quoted context omitted.

> You aren’t having a disagreement with a person. You’re having a disagreement with reality. How so? Are you going to instruct us all on how a termcaps mismatch bug is an indicator of poor code quality, rather than an unfortunate bug emerging from within the chaos of the many layers of disparate technologies that must somehow be stitched together (along with their idiosyncrasies) in order to make a project like this…

Because you won’t listen to a word anyone says lol. You had a visual bug right at the top of the repos README. Then insisted you hadn’t noticed it before. Whats important is not that specific visual bug, it’s what that bug says about the rest of the code. How can we believe that this code is high quality if we see a glaring issue 5 seconds into opening the github? We didn’t seek out your repo and start lobbing critiq…

> you won’t listen to a word anyone says

Really? So the discussion leading to the theory that there's likely a problem with termcaps disparity between layers didn't happen?

> Whats important is not that specific visual bug, it’s what that bug says about the rest of the code.

Really? So you can tell from a single cosmetic bug which doesn't affect its ability to perform its task, that the rest of the codebase is deficient? That's a pretty damn impressive skill!

Hater's gonna hate, I guess ¯\_(ツ)_/¯

The otherwise timid pack always circles after they sense a single drop of blood, no matter how small and insignificant.

Re: The last six months in LLMs in five minutes

#496

Post by embedding-shape »

malfist wrote: post #434
embedding-shape wrote: post #405

Earlier quoted context omitted.

I don't see how it cannot be true. Are you claiming that every developer who uses the same LLM harness + model would produce equal code, regardless of the prompt? That's clearly not true in my experience, and I cannot understand how it could be either. And if that's not true, then it's quite literally about how you're holding this hammer.

There's a cowboy artist that paints with his penis and does amazing work. If I tried that it'd turn out incredibly poorly, I prefer to paint with paintbrushes. Just because the naked cowboy can paint well with just his penis, doesn't mean a penis is the right tool for painting. It doesn't matter how you hold your penis, it's not the right tool.

Hmm, ok, I think the penis in case is a bit distracting, can you de-analogize this to their real terms and tell me what this is supposed to mean and be related to developing with LLMs?

Re: The last six months in LLMs in five minutes

#497

Post by righthand »

Insanity wrote: post #10

I wonder how much the 'inflection point' is a thing vs marketing. I'm sure the models got somewhat better, but even now when I'm trying to 'vibe code' a game with the latest models (combination of Codex w/ gpt5.5 and gpt5.3-codex), they really do struggle. They definitely get something barebones up and running, but it's far from a fully fledged application.

I mean this blog post and many from this author are pure evangelism and marketing. Can you find anything critical or any dissent from this author about LLMs?

Re: The last six months in LLMs in five minutes

#498

Post by john_strinlai »

TeMPOraL wrote: post #455
GistNoesis wrote: post #285

Last 6 months is humanity losing control of LLMs. - Memory market cornering which mitigated the adoption of local AI despite great open model being released. - Fast penetration of IP exfiltrating tools in companies world-wide. - Developers producing more code that they can read. - Autonomous agents killing Open Source by siphoning the attention economy - Autonomous agents destroyed online communities (including HN) -…

> - Memory market cornering (...) Wait, what? What is that? > - Fast penetration of IP exfiltrating tools in companies world-wide. That goes on the benefit side, I believe. > - Autonomous agents killing Open Source by siphoning the attention economy Anything attention economy disappearing is a "good riddance" to me.

>Wait, what? What is that?

i believe they are just saying that RAM prices went crazy

Re: The last six months in LLMs in five minutes

#499

Post by kstenerud »

windexh8er wrote: post #437
kstenerud wrote: post #219

Earlier quoted context omitted.

The polarization comes from the very disparate coding experiences and output quality that different people find when using these tools. For example, I've had the opposite experience of yours, generating very high quality work using Claude (such as https://github.com/kstenerud/yoloai ). Just in dealing with all the bugs and idiosyncrasies in the technologies I'm using, the agent has been a godsend in discovering and c…

A standard Docker container, with the container UID/GID mirrored to the host user, holding the host user's API keys, with the host user's project directory bind-mounted. The tooling doesn't even use gVisor / Kata by default which could implement the claim made, but in reality this entire project appears to be security theater.

[dead]

Re: The last six months in LLMs in five minutes

#500

Post by Antibabelic »

captn3m0 wrote: post #487
Antibabelic wrote: post #157

Earlier quoted context omitted.

I don't understand this response. Human artists can and do make SVGs.

They typically use a visual editor like Inkscape with visual feedback. Nobody is hand-coding a complex SVG.

The end result is the same: an SVG file. Definitely doesn't matter to an LLM what produced it.
Post reply on HN