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

601–610 of 631 posts

Re: The last six months in LLMs in five minutes

#601

Post by godelski »

walthamstow wrote: post #278
Philip-J-Fry wrote: post #248

Earlier quoted context omitted.

I don't want to offend (it's AI coded anyway :)) but that does not scream "high quality" to me. The headline gif on that repo just paints a terrible picture. It can't draw a box correctly, there's random underscores all over the screen. The UI itself is just incredibly incoherent. I don't even know what I'm looking at. Like, no it doesn't seem like very high quality work... It just seems like a vibe coded tool. Edit:…

Take it up with Anthropic. It's actually their billion-dollar TUI product you're commenting on. The problem with being such a naysayer is that you're entirely disconnected from what's going on. You haven't tried an agent like Claude Code and experienced it for yourself, so you don't recognise what it looks like when it's in front of you.

I use claude every single day at work. I've burned hundreds of dollars a week in tokens. But I still think you're being too defensive while attacking Philip.

I'm sorry, but you need to look yourself in the mirror. You didn't like what they said so you jumped to the assumption that they must not have used CC (or any other agent). That if they had, they would have the same experience as you did/do. But this whole thread is exactly that conversation, that those experiences aren't shared. That this assumption is baseless. And you know what? That's okay. We're not robots. We're human. Each of us has our own unique world we live in. It's okay that people don't have the same experience as you. It's okay that their favorite color, food, activity, or whatever isn't the same as yours. I'm glad that we live in that kind of world. That's what makes things like culture. I don't want to live in a hive mind, and I don't think anyone else does either.

Re: The last six months in LLMs in five minutes

#602

Post by godelski »

SlinkyOnStairs wrote: post #382
walthamstow wrote: post #278

Earlier quoted context omitted.

Take it up with Anthropic. It's actually their billion-dollar TUI product you're commenting on. The problem with being such a naysayer is that you're entirely disconnected from what's going on. You haven't tried an agent like Claude Code and experienced it for yourself, so you don't recognise what it looks like when it's in front of you.

There are two possibilities here: 1) This tool breaks the Claude TUI. Exactly as described by the comment. 2) The Claude TUI itself is broken. The comment is wrong, but assuming the "billion dollar TUI product" is capable of basic rendering and it's the wrapper that broke it, that is an entirely reasonable assumption The fun here is that both of these softwares were made extensively using AI. No matter which of our o…

  > The Claude TUI itself is broken.
I mean this is also true. You forgot the third option, that 1 and 2 are true (and 4th, that neither are).

Seriously, the Claude TUI fucking sucks. I don't know how anyone thinks otherwise. It breaks constantly if you enter your editor (), or resizing windows/panes, or making another pane full screen, scrolling, or any number of things. It is objectively a bad piece of software.

And honestly, are we surprised? Anthropic says themselves that a lot of code is written by Claude. They've been saying that for years. If you look at agents now and think "man, agents a few years ago sucked" then this shouldn't be surprising at all! I mean FFS the thing spits out text and they designed it like a fucking game engine. It is silly

Re: The last six months in LLMs in five minutes

#603

Post by QuercusMax »

magicalhippo wrote: post #541
skydhash wrote: post #417

Earlier quoted context omitted.

> I think these newfangled tools have made it even more fun, since writing lots of boiler plate, repetitive event handles and whatnot is not my idea of fun That’s what code generators, snippets plugins, macros, and the old copy-paste are here for. I wonder if you were using notepad to code. Because even nano had macros.

Those tools only get you so far, especially if you write something novel to you. Using a new framework or programming language say. Sometimes using a new framework or programming language is the fun part. But sometimes it's just the best way of solving a problem incidental to the fun part. One of the two projects I vibed included a web frontend. I didn't touch a single line of HTML, CSS or JavaScript of the frontend.…

For someone who did a lot of webdev 20 years ago and hasn't done much in the last decade, and does mostly backend development now, being able to vibe code up a quick web or text-mode UI is killer. It might look like crap and not be very maintainable, but who cares - it's a temporary dashboard we'll throw away next quarter when we're done with our migration.

Re: The last six months in LLMs in five minutes

#604

Post by godelski »

embedding-shape wrote: post #523
knollimar wrote: post #504

Earlier quoted context omitted.

If the company making hammers can't hold it right, it suggests something about the hammers, no?

Yeah, they have bad engineers, product people and testers. Microsoft is pretty shit at launching products, does that mean "products" as a concept is wrong? No, it just means Microsoft is bad at products, not more than that. Not sure why you have to extrapolate over an entire ecosystem just because one actor is bad at something.

  > No, it just means Microsoft is bad at products
FYI, that's what people are saying...

Re: The last six months in LLMs in five minutes

#605

Post by QuercusMax »

sofixa wrote: post #344
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.

Counterpoint, I'm also vibecoding a game, and even before doing the "proper" setup (a good AGENTS.md, skills people have published for my chosen game engine, Godot), mechanically , the game was pretty spot on. It looked boring, so I used Claude Design to create a few mockups to choose from, chose the one I liked the most, and told Claude Code to redo the game UI with it. There have been plenty of small issues like ta…

UI fit and finish is really hard for these models, even in with text-mode UIs. The super fiddly stuff still needs to be done by hand, at least for now.

Re: The last six months in LLMs in five minutes

#606

Post by godelski »

kstenerud wrote: post #441
hiw2d wrote: post #412

Earlier quoted context omitted.

tbh youve embarrassed yourself here.

THAT must be why the stars are going up! Thanks for explaining it for me.

Sorry dude, 84 stars isn't that much. It's a good number, be proud, but I wouldn't go boasting about it like you're some hotshot.

https://www.star-history.com/?repos=kstenerud%2Fyoloai&type=...

Re: The last six months in LLMs in five minutes

#607

Post by godelski »

_carbyau_ wrote: post #594
joe_the_user wrote: post #589

Earlier quoted context omitted.

My own informal test when generative AI came out has been "a picture of an old man riding a bicycle over a river". I just ran it for chatgpt with the standard model I have (5.5). It shows the old man on an old bicycle with the bicycle on a slack line and the slack line extending over the river with a medieval village in the background. The point is that the prompt has a subtle ambiguity - "how is the old man going ov…

> but they still fail add the assumptions that people would draw. I have mixed feelings about this. I agree with the default assumptions you have as to "what people would draw", however what do you want from this cognitive automation? Do you want, "what most people would do" or do you want "something creative, an outlier, that still satisfies conditions" ?

I think the point is that language is compressed. There's a lot conveyed in very little. Yes, it is ambiguous, but that's exactly the feature that makes natural language useful. It's also why it is so much easier to speak with your friends than it is with some random person in your town, you've learned how to compress and decompress each other's language better.

But that's also why we invented formal languages like math and programming. Because there's a lot of times where we don't want ambiguity. Law is basically mankind's greatest attempt at making natural language unambiguous and it doesn't take a genius to realize that that's a shitshow and never going to happen. At the end of the day, to make natural language even relatively low in ambiguity requires a metric fuck ton more words than it would take to express via a formal language (which are also overly pedantic and verbose)

So the problem is that the AI doesn't share those expected decompression strategies. Sure, many humans won't either, but developing a shared language is essential for properly communicating with others. We've all worked with someone who feels like they're speaking a different language. It's exhausting, right?

Re: The last six months in LLMs in five minutes

#608

Post by portmanteur »

_carbyau_ wrote: post #594
joe_the_user wrote: post #589

Earlier quoted context omitted.

My own informal test when generative AI came out has been "a picture of an old man riding a bicycle over a river". I just ran it for chatgpt with the standard model I have (5.5). It shows the old man on an old bicycle with the bicycle on a slack line and the slack line extending over the river with a medieval village in the background. The point is that the prompt has a subtle ambiguity - "how is the old man going ov…

> but they still fail add the assumptions that people would draw. I have mixed feelings about this. I agree with the default assumptions you have as to "what people would draw", however what do you want from this cognitive automation? Do you want, "what most people would do" or do you want "something creative, an outlier, that still satisfies conditions" ?

I would want to know the LLM has a reliable and realistic World Model underneath all of the next token prediction.

Whether I am building hardened engineering systems, or discussing cooking methods, or discussing sensitive health concerns, or navigating complex psychological and interpersonal issues, the model will inevitably have to make some assumptions about context I haven’t provided. I want to know that those assumptions are grounded in reality.

For what it’s worth, a slack-line over a river in front of a medieval town is too anachronistic to be interesting, let alone the idea of an old man riding a bicycle well enough over a slack-line. That is output that was not grounded in a solid world model, regardless of how “creative” it was.

Re: The last six months in LLMs in five minutes

#609

Post by bluegatty »

nl wrote: post #596
bluegatty wrote: post #379

Earlier quoted context omitted.

? That's evidence that it does not work. Neither of those are from 'under' they both look either front or top? Imagine yourself under the ducks feet, looking up at an oblique angle - wings as I suggested. The AI won't do that, it has no reference for dimensionality.

What on earth do you mean? I live near an area with lots of pelicans. If you look up at one flying overhead this is what they look like. Here is a photo for comparison: https://commons.wikimedia.org/wiki/File:American_white_pelic...

Sure, something like that. Note like the examples you posted.
Post reply on HN