591–600 of 603 posts
Earlier quoted context omitted.
Asking might work better than telling
How do you do that???? Say the words but in the form of a question? I feel like that will go a lot worse than just telling (but nicely). I have a daughter too so I am genuinely willing to try anything
Earlier quoted context omitted.
>I've resorted to append things like "THIS IS JUST A QUESTION. DO NOT EDIT CODE. DO NOT RUN COMMANDS". Which is ridiculous. Funny to read that, because for me it's not even new behavior. I have developed a tendency to add something like "(genuinely asking, do not take as a criticism)". I'm from a more confrontational culture, so I just assumed this was just corporate American tone framing criticism softly, and me com…
You can just put it in PLAN mode (assuming VS Code), that works well enough - never seen it edit code when in that state.
Earlier quoted context omitted.
I've spent 30 years seeing the junk many human developers deliver, so I've had 30 years to figure out how we build systems around teams to make broken output coalesce into something reliable. A lot of people just don't realise how bad the output of the average developer is, nor how many teams successfully ship with developers below average. To me, that's a large part of why I'm happy to use LLMs extensively. Some thi…
Did you also notice the evolution of average developers over time? I mean, if you take code from a developer ten years ago and compare it with their output now, you can see improvement. I assume that over time, the output improves because of the effort and time the developer invests in themselves. However, LLMs might reduce that effort to zero — we just don't know how developers will look after ten years of using LLM…
LLMs might help the new joiner produce code on the level of an average developer faster. But, at the same time, if LLMs are really trained on all open source repositories without any selection, that level might be limited.
I have recently published a potentially related article: https://link.springer.com/article/10.1007/s44427-025-00019-y
It looks like the overwhelming majority of projects on Github, does not really follow stable growth tendencies. In all fairness, as these were the smaller projects, their developers might have never intended to demonstrate best practices, or make the project sustainable on the long-term.
This is all fine, experimentation and learning are very welcome in open source. But, with 83,9% of the projects (in my study) falling into this category, LLM might pick them up as demonstrating overwhelmingly popular best practices. In the worst case, this might even lead to actual best practices being drowned out, over time.
Earlier quoted context omitted.
Thou shalt not make repetitive generic music, thou shalt not make repetitive generic music, thou shalt not make repetitive generic music, thou shalt not make repetitive generic music. Thou shalt not pimp my ride. Thou shalt not scream if you wanna go faster. Thou shalt not move to the sound of the wickedness. Thou shalt not make some noise for Detroit. When I say "Hey" thou shalt not say "Ho". When I say "Hip" thou s…
I have no idea how this ended up here, but after giving it a listen, thank you for the chuckle. I wouldn’t have come across it otherwise.
Earlier quoted context omitted.
It has a lot. I find by challenging it often, getting it to explain it's assumptions, it's usually guessing. This can be overcome by continuously asking it to justify everything, but even then...
Trust shouldn't be inherent in our adoption of these models. However, constant skepticism is an interesting habit to develop. I agree, continually asking it to justify may seem tiresome, especially if there's a deadline. Though with less pressure, "slow is smooth...". Just this evening, a model gave an example of 2 different things with a supposed syntax difference, with no discernible syntax difference to my eyes. W…
Earlier quoted context omitted.
It has a lot. I find by challenging it often, getting it to explain it's assumptions, it's usually guessing. This can be overcome by continuously asking it to justify everything, but even then...
It's almost like an emergent feature of a tool that's literally built on best guesses is...guesswork. Not what you want out of a tool that's supposed to be replacing professionals!
I guess I'm more interested in understanding what it can and can't do.
Earlier quoted context omitted.
It actually is, don't know for how long but it prompted me to try this a few days ago
Can't be rolled out to all users then yet, because I just get: > Unknown skill: btw
Earlier quoted context omitted.
The point is that if the harness’ workflow gives contradictory and confusing instructions to the model, it’s a harness issue, not necessarily a model issue.
First it was a model issue, then it was a prompting issue, then it was a context issue, then it was an agent issue, now it's a harness issue. AI advocates keep accusing AI skeptics of moving goalposts. But it seems like every 3-6 months another goalpost is added.
Because, yes, first, it was a model issue, and then more advanced models started appearing and prompting them correctly became more important. Then models learned through RLHF to deal with vague prompting better, and context management became more important. Then models became better (though not great) at inherent context recollection and attention distribution, so now, you need to be careful what instructions a model receives and at what points because it’s literally better at following them. It’s not so much that the goalposts are being moved, it’s that they’re literally being, like, *cleared*.
This isn’t a tech that’s already fully explored and we just need to make it good now, it’s effectively an entirely new field of computing. When ChatGPT came out years ago no one would have DREAMT of an LLM ever autonomously using CLI tools to write entire projects worth of code off of a single text prompt. We’d only just figured out how to turn them into proper chatbots. The point is that we have no idea where the ceiling is right now, so demanding well-defined goalposts is like saying we need to have a full geological map of Mars before we can set foot on it, when part of the point of going to Mars is to find out about that.
As a side point, the agent is the harness; or, rather, an agent is a model called on a loop, and the harness is where that loop lives (and where it can be influenced/stopped). So what I can say about most - not all, but most, including you, seemingly - AI skeptics is that they tend to not actually be particularly up-to-date and/or engaged with how these systems actually work and how capable they actually are at this point. Which is not supposed to be a dig or shade, because I’m pretty sure we’ve never had any tech move this fast before. But the general public is so woefully underinformed about this. I’ve recently had someone tell me in awe about how ChatGPT was able to read their handwritten note and solve a few math equations.
Earlier quoted context omitted.
> And I've seen Claude identify data races that have sat in our code base for nearly a decade how do you know that claude isn't just a very fast monkey with a very fast typewriter that throws things at you until one of them is true ?
Iteration is inherent to how computers work. There's nothing new or interesting about this. The question is who prunes the space of possible answers. If the LLM spews things at you until it gets one right, then sure, you're in the scenario you outlined (and much less interesting). If it ultimately presents one option to the human, and that option is correct, then that's much more interesting. Even if the process is "…
Also how were the data races significant if nobody noticed them for a decade ? Were you all just coming to work and being like "jeez I dont know why this keeps happening" until the LLM found them for you?
Earlier quoted context omitted.
>I've resorted to append things like "THIS IS JUST A QUESTION. DO NOT EDIT CODE. DO NOT RUN COMMANDS". Which is ridiculous. Funny to read that, because for me it's not even new behavior. I have developed a tendency to add something like "(genuinely asking, do not take as a criticism)". I'm from a more confrontational culture, so I just assumed this was just corporate American tone framing criticism softly, and me com…
Same here. I quickly learned that if you merely ask questions about it's understanding or plans, it starts looking for alternatives because my questioning is interpreted as rejection or criticism, rather than just taking the question at face value. So I often (not always) have to caveat questions like that too. It's really been like that since before Claude Code or Codex even rolled around. It's just strange because…