The last six months in LLMs in five minutes
591–600 of 631 posts
Re: The last six months in LLMs in five minutes
#592Earlier quoted context omitted.
Next generation is healing already and staying away from social media, etc.
My generation will be the new fox news boomers, but instead of Fox news it will be ChatGPT and Claude telling them that Israel is the greatest country in the world and if you disagree you must be an antisemite.
Maybe thats just your bubble. People I know are back to books and encyclopedias.
Re: The last six months in LLMs in five minutes
#593Earlier quoted context omitted.
As a random example of a "hard" problem solved by AI that I couldn't have realistically done myself, despite having decades of wide industry experience: Reverse engineering a proprietary protocol from a binary executable. I heard about people finding security vulnerabilities in compiled code with the combination of Claude Mythos wired up to a disassembler like NSA's Ghidra. Someone here mentioned that GPT 5.5 "extra…
> There is no way I could have reverse engineered this myself from compiled C++ code and/or packet captures! The format isn't self-describing and is incredibly dense (similar to NetFlow). In a hex viewer it looks like line noise! I think you could have. However I don't think you would have - there is a big difference. It is a lot of work to to that, and people who try normally give up. However if your boss told you c…
Of course, there is a philosophical difference between "impossible" and "intractable", but to a business with a budget and a schedule there isn't.
Re: The last six months in LLMs in five minutes
#594> there’s zero chance any AI lab would train a model for such a ridiculous task. A lot of people here stated that this is a ridiculous metric, but no one seems to remember that it was introduced in the initial GPT report ("Sparks of Artificial General Intelligence: Early experiments with GPT-4" [1]) by Microsoft about 3 years ago. Shortly after that it was parroted by a network of booster accounts and became a thing…
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" ?
Re: The last six months in LLMs in five minutes
#595> The coding agents got really good It's since november 2025, the so called "inflection point", that I'm still wondering for who coding agents become "really good". All I observe they got better at tool call and answering questions about big codebases, especially if the question has a vague pattern to search, and they're superuseful for that! For generating production code even with a lot of steering and baby sitting…
I'm convinced that the polarization is that one's impression of AI has a direct 1:1 mapping with one's previous level of skill and sensitivity to quality. Most people are by definition average and they are impressed. Is there anyone in the industry noted for their skill, quality, and taste, e.g. Jonathon Blow, who is impressed and thinks the AI is really good? I haven't seen any. In my personal circle, the best devs…
This is contradicted by the amount of AI use at top tech firms.
Re: The last six months in LLMs in five minutes
#596Earlier quoted context omitted.
> Try to get the AI to draw the pelican form a very odd angle - like underneath, to the right, one wing extended, one wing not ... 0% chance. Proof by existence? https://gist.github.com/nlothian/50241d34a654fcf0caa280d4475... Looks pretty good to me. ChatGPT in "Thinking" model. Edit: I've added the Opus version on the same link.
? 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...
Re: The last six months in LLMs in five minutes
#597Earlier quoted context omitted.
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.
Products isn't the analogy, but in my example it would say something about microsofts tooling and processes. I wouldn't trust a toolmaker who doesn't know how to use the tools decently.
> I wouldn't trust a toolmaker who doesn't know how to use the tools decently.
I agree but would extend that qualification:
I wouldn't trust a toolmaker who doesn't know how to use the tools decently for exactly the same field of expertise.
Re: The last six months in LLMs in five minutes
#598> I put together these annotated slides from my five minute lightning talk at PyCon US 2026
Is there a video or audio of this talk?
Re: The last six months in LLMs in five minutes
#599[flagged]
Re: The last six months in LLMs in five minutes
#600Earlier 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…
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:…
> I don't want to offend (it's AI coded anyway :)) but that does not scream "high quality" to me.
FWIW, I agree with Philip here. I don't think this screams "high quality" to me. I'm also not trying to take a shit on your project. Nothing screams "terrible" to me, but yeah, it does look a bit sloppy. There's no polish to it. It looks like someone that grades on "it works" and that's fine. But it also isn't everyone's cup of tea. Where the sloppiness comes in is like what Philip said. First thing I saw was the gif and well... I think Claude Code is sloppy. But this is also a great example at how and where LLMs visibly fail. Creating a box in text is pretty simple. There's tons of tools to do it. And the LLM 100% knows about characters like ⌜⌝⌞⌟⎜, it just doesn't use them and doesn't care. The code itself also looks very LLM generated.
It's fine and I don't think you have any reason to be ashamed of it, but I also wouldn't go around boasting that it is an example of high quality work too. And FWIW, I can't think of a single heavily LLM assisted code where I don't have similar feelings. I've seen stuff with more polish, but yeah, they feel off.
> TUI
I think this is true for a lot of stuff, not just TUIs or bash tools. Things just smell... off...