Earlier quoted context omitted.
And it deserves an honest answer.
The answer is genuinely yours
And that changes the game. Again.
Claude, change the “Add to Cart” button to blue
321–330 of 448 posts
Re: Claude, change the “Add to Cart” button to blue
#322Earlier quoted context omitted.
“Post Hoc Rationalisation” https://www.patheos.com/blogs/tippling/2013/11/14/post-hoc-r...
I learned this from "The Elephant in the Brain", which I strongly recommend: https://amzn.to/4iSyLX8
I learned this from Dirk Gently’s Holistic Detective Agency, which I strongly recommend.
Re: Claude, change the “Add to Cart” button to blue
#323At least with Codex, this has not been my experience at all. It still screws up sure, but in every case I can ask "why did you do this" and it can trace back what made it take that particular decision. Typically it's always that I either didn't specify the problem correctly or made a really dumb mistake (executing the task on the wrong project....did this one yesterday) or it's something within a skill file that inst…
Models hallucinate plausible answers to why they did things. It might be true and it might be complete fiction.
To test this, change the history in the context to indicate that the model did or recommended something completely different than it actually did, and then ask it to explain why. You’ll still get a plausible explanation.
Re: Claude, change the “Add to Cart” button to blue
#324Re: Claude, change the “Add to Cart” button to blue
#325I bet if you used the real Opus 5 it could one shot this.
Re: Claude, change the “Add to Cart” button to blue
#326Earlier quoted context omitted.
Plus rigorously ensuring backwards compatibility for a project that is 2 hours old and has zero users.
"Plus rigorously ensuring backwards compatibility for a project that is 2 hours old and has zero users." That is exactly how the slop accretes and you get a pile of crap. Claude somehow assumes that said 2 hour old userless app is some dusty enterprise app with millions of users and billions of dollars at stake for a 1 second outage. I have to constantly have these things "take a deep breath, step back and look at th…
> please restate what i'm asking you to do and why it's important"
This doesn't actually do anything though, right? There's no understanding, so the machine will just reiterate the original token query back to you. The 'why it's important' part will just generate some patronizing boilerplate as a raison d'etre.
Re: Claude, change the “Add to Cart” button to blue
#327Earlier quoted context omitted.
Exactly. I am becoming increasingly convinced that this is actually just a part of how intelligence/cognition works.
But is it really what we want, machines with the same defects as humans? I don't want a pocket calculator that make mistakes "sometimes" so I have to double-check the results, I want a pocket calculator that works (to those who want to argue that pocket calculators don't give the correct result for (1/3)*3: STFU).
>But is it really what we want, machines with the same defects as humans?
Sort of, actually. I think we humans actually have some intuition that we'd be more effective if our cognition were augmented more directly by machine strengths: the ability to run precise calculations, more memory, ability to look facts in some sort of knowledge graph.
I think we're on the right track, but instead of augmenting humans with machine strengths, we're building intelligence in hardware in a way where it can access that augmentation. Plus, then we can quickly distribute updates, run parallel instances, etc.
If intelligence is compression, and hallucinations are essentially loss, then as the models grow in size performance (at least as far as hallucinations) should reduce. Or we'll get things fast enough that we can afford to stop relying on model weights for memory and check an increasingly larger set of discrete facts as part of reasoning.
Right now, the models are making trade-offs. As compute grows, and inference gets faster, we can make fewer of those trade-offs and start to use the unique strengths of machines to fill the gaps we're seeing, I suspect.
Re: Claude, change the “Add to Cart” button to blue
#328Earlier quoted context omitted.
> most people don’t use ai this way though How do they use it? Surely no one is just repeating the same prompt over and over (except as a Ralph loop perhaps, which is automated). I’m really struggling with the notion that most people just throw the same prompt repeatedly hoping it eventually works. Because that doesn’t sound like gambling. It sounds crazy (and frustrating). > and i still feel like the end-psychologic…
> How do they use it? as an example, i was using chatgpt a few weeks back to help me remember the name of a painting i’d seen about a decade ago. i could recall the general shape of the subject and that it was europeanish, but nothing else. after seven turns or so it finally got it, and honestly, the relief of finally remembering the name felt like, well, hitting a jackpot i’ve had a similar feeling of success after…
> the relief of finally remembering the name felt like, well, hitting a jackpot
I understand the joy of success but I fail to see how this is gambling. I could have an equivalent conversation with a friend (more likely about a movie in trying to remember than a painting, but still) and get the exact same type of iterative “no, not that one, it was more like X” and feel elated when my friend finally realizes I’m taking about a scene from Hot Tub Time Machine.
This isn’t gambling in any meaningful sense.
Re: Claude, change the “Add to Cart” button to blue
#329Earlier quoted context omitted.
same. none of the available prompts are what I would prompt claude with and I get way better results than this. makes sense to me why the provided prompts result in the simulated outcomes. garbage in, garbage out.
It "makes sense" that plainly telling the chat bot to make one button blue makes the whole site blue? It "makes sense" that correcting it and repeating 3 times that no, only the one button should be blue, should make the button a gradient and start a philosophical discussion around the nature of "blue"? Wow, you AI people really have a negative view of the technology y'all are trying to sell as the next Jesus
If the agent's change has such a catastrophic effect, the first thing you do is tell it to explain why its change had that effect.
Once you understand what the problem is, you can give it better instructions. If the architecture is shit, the agent is going to have a rough time of it.
Re: Claude, change the “Add to Cart” button to blue
#330Earlier quoted context omitted.
“Post Hoc Rationalisation” https://www.patheos.com/blogs/tippling/2013/11/14/post-hoc-r...
Exactly. I am becoming increasingly convinced that this is actually just a part of how intelligence/cognition works.
When we are really thinking about something we do it forwards, backwards and middle out, and regenerate and distill many times.
When we do meta thinking about that process after the fact, two things happen. 1, we change our total “thought” by adding that meta thinking to it. And 2: it’s a very lossy process, because we don’t have very good data about what our brain or mind was actually doing during that first think and emotional factors are nearly always at play and even more complex.
Now for the more complex AI, the fragmented process of multiple agents and loops and reruns are pretty similar to that first think we do. At least structurally. But the meta think is where they differ. They have no emotion, but they also have even worse data about its own function. They constantly degenerate so I would argue their “changing the thought by thinking about it” factor is also generally way higher than ours.
Getting better at consistent/reproducible thinking, with many ‘steps’, that leaves good documentation of that thinking behind for future analysis, has to be one of the more important areas for the big flagships going forward. I’m certain that “what is this fucker doing and why” is the biggest pain point for AI researchers. Or the math, it’s usually the math.
But you’re correct in the general structure; they generally do the same post hoc analysis we do, just noticeably worse because of their opaque nature(even to themselves) and general degenerative instability.