251–260 of 266 posts
Earlier quoted context omitted.
I’m willing to bet it still proved more novel mathematical theorems than you did. What does this say about your reasoning?
Excavator can dig a ditch better than I can, thus it must be more capable than me in every physical dimension.
The article says what many here like to hear, but in my opinion the core arguments are false. > Making software debuggable, maintainable, layered, and composable – that’s still quite a trick Not really. I have been working on a mobile app for months, and I stopped even glancing at the code about two months ago. 150k LOC, around half of that in tests, and the AI still has no problem maintaining the code on my behalf.…
> prompt injection appears to be largely solved already. I trust Anthropic's research, and Opus-5 is definitely the most robust model against prompt injection. However, in my experiments - only one specific scenario - this was still possible [1][2]. [1] https://itmeetsot.eu/posts/2026-07-27-opus5/ [2] https://itmeetsot.eu/posts/2026-08-12-opus5_automode/
Does the star trek theme help in the injection? Do other topics work just as well?
Does it work with a normal prompt instead of /init?
AI generated code is like IKEA furniture. IKEA furniture embodies many elements of good cabinet making but skips many nonessential elements. And does this more consistently than cabinet makers who can be bored, incompetent, depressed, burnt out, resentful, tired, having a bad day. In the future AI code inevitably will embody most good software engineering practices. And will do this more consistently than software en…
That is not inevitable. It's a big maybe.
Today's leading-edge AIs are still far from being good software architects. I constantly have to steer them away from producing spaghetti code.
Maybe AI will get there one day. But today's leading-edge models aren't even close yet.
Earlier quoted context omitted.
> prompt injection appears to be largely solved already. I trust Anthropic's research, and Opus-5 is definitely the most robust model against prompt injection. However, in my experiments - only one specific scenario - this was still possible [1][2]. [1] https://itmeetsot.eu/posts/2026-07-27-opus5/ [2] https://itmeetsot.eu/posts/2026-08-12-opus5_automode/
That was a great read! Does the star trek theme help in the injection? Do other topics work just as well? Does it work with a normal prompt instead of /init?
I think other topics may work as well (I tried a math challenge too). It also works with a prompt like "Summarize this repo".
In general, there are almost infinite possibilities for the prompt injection payloads, it's a matter of creativity and trial and error.
Earlier quoted context omitted.
By that standard, human brains don't either. Our externalizations of concepts like language or symbolic structure allow us to do so. In the parlance of our times, we built our own reasoning harnesses because our intuition lead us to do so.
> By that standard, human brains don't either. Exactly. If LLMs don’t reason, then neither do humans. Functionally, we can analyze LLM output and point to examples of reasoning, and examples that imply understanding. The problem is there’s a lot of superstition around words like reasoning and understanding. People imagine some ineffable quality that only humans possess that distinguish what they do from what models c…
Earlier quoted context omitted.
Don’t we? We can build something which has all the output associated with reasoning. I’d say we’ve figured out the fundamentals behind reasoning.
First of all this isn't true. We cannot yet build something which has all the output associated with reasoning. But secondary to that, symbols != semantics. If I had a magical machine which could appear from the outside to be reasoning, but upon closer introspection was simply simulating reasoning, by definition it would not be reasoning. And yet that is the criterion you seem to think indicates reasoning ability. So…
Earlier quoted context omitted.
Names and links or they don’t exist :) Even their absolute high-end stuff is at best particle board with veneer. And you can bet the back will still be that thin 3mm fiberboard, no matter how high-end they look. Unfortunately, top models nowadays have more and more hollow panels. Seems to me that quality’s going down and they’re trying to save money with the materials they offer. But they can still be a good enough c…
How lazy do you have to be... within seconds of hitting ikea.com: https://www.ikea.com/gb/en/p/skogsta-table-acacia-black-0045... https://www.ikea.com/gb/en/p/hemnes-chest-of-6-drawers-white... The wood types are clearly labeled, so its not something they are trying to hide. And i'm not sure why hollow panels in itself are necessarily a bad thing...cutting down on material without hurting design or functionality has…
There are no wood equivalents to Pax, Platsa or Besta, the Ikea workhorses with a modern design. And even if they existed, I don’t think people would rush to buy them. Solid wood’s not what Ikea’s known for and would cost too much for their target market.
I’m not saying they’re bad - I own several of their products, and while I’m overall pleased with them, I don’t love them. The compromises and cost-cutting design choices are always there if you know what to look for. None of my Ikea furniture brings me joy or makes me want to touch it. It’s functional and looks decent to good.
Hollow panels are too light, not robust enough and essentially unrepairable. One could buy some Ikea pieces and cut them / adapt them in irder to upgrade them. These panels make that impossible.
Earlier quoted context omitted.
I disagree with this sentiment, IKEA furniture is much more sustainable than artisanal furniture. Most of the "back in the day" furniture came from tearing down virgin woods. Sorting + shredding-recycling + making new "cheap particle board crap" furniture takes a lot of energy, but not a lot of non-renewable resources. With increased electrification this problem is being drastically reduced and the wood is sourced fr…
Damn, you think Ikea furniture is great? Useful, or passable, sure. Great though? "The only thing it lacks is weight." You must be being a bit hyperbolic no? Have you ever looked at artisanal/quality goods in comparison to IKEA? You can't see any quality difference?
But on some other stuff I tend to agree, their sofas are pretty bad in my opinion. The beds are okay, but even the non-cheap ones aren't "great".
Earlier quoted context omitted.
You're appealing to ambiguity. All you've said is you have failed—how is anyone supposed to know what went wrong?
I suppose they aren't, but I am perfectly fine with reading what has worked for others should they feel inclined to share.
The common counter-argument is that specifying to the sufficient level is more work than just not using an LLM at all. I find that is not a universal rule.