| ▲ | anttiharju a day ago |
| I like AI for software development. Sometimes I am uncertain whether it's an absolute win. Analogy: I used to use Huel to save time on lunches to have more time to study. Turns out, lunches were not just refueling sessions but ways to relax. So I lost on that relaxation time and it ended up being +-0 long-term. AI for sure is net positive in terms of getting more done, but it's way too easy to gloss over some details and you'll end up backtracking more. "Reality has a surprising amount of detail" or something along those lines. |
|
| ▲ | energy123 21 hours ago | parent | next [-] |
| I find the hardest thing is explaining what you want to the LLM. Even when you think you've done it well, you probably haven't. It's like a genie, take care with what you wish for. I put great effort into maintaining a markdown file with my world model (usecases x principles x requirements x ...) pertaining to the project, with every guardrail tightened as much as possible, and every ambiguity and interaction with the user or wider world explained. This situates the project in all applicable contexts. That 15k token file goes into every prompt. |
| |
| ▲ | anttiharju 7 hours ago | parent | next [-] | | > It's like a genie, take care with what you wish for. I used to be stuck with this thought. But I came across this delightful documentation RAG project and got to chat with the devs. Idea was that people can ask natural language questions and they get shown the relevant chunk of docs for that query. They were effectively pleading to a genie if I understood it right. Worse yet, the genie/LLM model kept updating weekly from the cloud platform they were using. But the devs were engineers. They had a sample set of docs and sample set of questions that they knew the intended chunk for. So after model updates they ran the system through this test matrix and used it as feedback for tuning the system prompt. They said they had been doing it for a few months with good results, search remaining capable over time despite model changes. While these agents.md etc. appear to be useful, I'm not sure they're going to be the key for long-term success. Maybe with a model change it becomes much less effective and the previous hours spent on it become wasteful. I think something more verifiable/strict is going to be the secret sauce for llm agents. Engineering. I have heard claude code has decent scaffolding. Haven't gotten the chance to play with it myself though. I liked the headline from some time ago that 'what if LLMs are just another piece of technology'? | |
| ▲ | hu3 6 hours ago | parent | prev | next [-] | | > That 15k token file goes into every prompt. Same here. Large AGENTS.md file in current project. Today I started experimenting splitting into smaller SKILL.md files but I'm weary that the agent might mistakenly decide to not load some files. | |
| ▲ | pixl97 12 hours ago | parent | prev | next [-] | | >I find the hardest thing is explaining what you want to the LLM. Honestly this isn't that much different then explaining to human programmers. Quite often we assume the programmer is going to automatically figure out the ambiguous things, but commonly it leads to undefined behavior or bugs in the product. Most of the stuff I do is as a support engineer working directly with the client on identifying bugs, needed features, and short failings in the application. After a few reports I've made going terribly wrong when the feature came out I've learned to overly detailed and concise. | |
| ▲ | greazy 15 hours ago | parent | prev [-] | | Do I read correctly that your md file is 15k tokens? how many words is that? that's a lot! | | |
| ▲ | energy123 14 hours ago | parent [-] | | 20k words by the 0.75 words/token rule of thumb. It's a lot, but for quick projects I don't do this. Only for one important project that I have ownership of for over a year. Maintaining this has been worth it. It makes the codebase more stable, it's like the codebase slowly converges to what I want (as defined in the doc) the more inferences I run, rather than becoming spaghetti. |
|
|
|
| ▲ | jijijijij 15 hours ago | parent | prev | next [-] |
| For the life of me, I don't get the productivity argument. At least from a worker perspective. I mean, it's at best a very momentary thing. Expectations will adapt and the time gained will soon be filled with more work. The free time net gain will ultimately be zero, optimistically, but I strongly suspect general life satisfaction will be much lower, since you inherently lose confidence in creation, agency, and the experience in self-efficacy is therefore lessened, too. Even if external pressure isn't increased, the brain will adapt to what's considered a new normal for lazy. Everybody hates clearing the dish washer, aversion threshold is the same as washing dishes by hand. And yeah, in the process you atrophy your problem solving skills and endurance of frustration. I think we will collectively learn how important some of these "inefficiencies" are for gaining knowledge and wisdom. It's reminiscent of Goodhart's Law, again, and again. "Output" is an insufficient metric to measure performance and value creation. Costs for using AI services does not at all reflect actual costs to sustainably run them. So, these questionable "productivity gains" should be contrasted with actual costs, in any case. Compare AI to (cheap, plastic) 3D printing, which is factually transformative, revolutionary tech in almost every (real) industry, I don't see how trillions of investments, the absurd energy and resource wasting could ever justify what's offered, or even imaginable for AI (considering inherent limitations). |
| |
| ▲ | anttiharju 10 hours ago | parent [-] | | For me it boils down to that I'm much less tied to tech stacks I've previously worked on and can pick up unfamiliar ones quicker. Democratization they call it. | | |
| ▲ | jijijijij 8 hours ago | parent [-] | | > and can pick up unfamiliar ones quicker Do you tho? Does "picking up" a skill mean the same thing it used to? Do you fact check all the stuff AI tells you? How certain are you, you are learning correct information? Struggling through unfamiliar topics, making mistakes and figuring out solutions by testing internal hypotheses is a big part of how deep, explanatory knowledge is acquired for human brains. Or maybe, it's been always 10,000 kilowatt-hours, after all. Even, if you would actually learn different tech stacks faster with AI telling you what to do, it's still a momentary thing, since these systems are fundamentally poisoned by their own talk, so shit's basically frozen in time, still limited to pre-AI-slop information, or requires insane amounts of manual sanitation. And who's gonna write the content for clean new training data anyway? Mind you, I am talking about the possible prospect of this technology and a cost-value evaluation. Maybe I am grossly ignorant/uninformed, but to me all of it just doesn't add up, if you project inherent limitations onto wider adoption and draw the obvious logical conclusions. That is, if humanity isn't stagnating and new knowledge is created. | | |
| ▲ | anttiharju 7 hours ago | parent [-] | | > Do you tho? Recent success I've been happy with has been moving my laptop config to Nix package manager. Common complaint people have is Nix the language. It's a bit awkward, "JSON-like". I probably would not have had the patience to engage with it with the little time I have available. But AI mostly gets the syntax right, allowing me to engage with it, and I think I've a decent grasp by this point of the ecosystem and even syntax. It's been roughly a year I think. Like, I don't know all the constructs available in the language, but I can still reason about things as a commoner that I probably don't want to define my username multiple times in my config, esp. when trying to have the setup be reproducible on an arbitary set of personal laptops. So that for a new laptop I just define one new array item as a source of truth and everything downstream just works. I feel like with AI the architetural properties are more important than the low-level details. Nix has the nice property of reproducibility/declarativeness. You could for sure put even more effort into alternative solutions, but if they lack reproducibility I think you're going to keep suffering, no matter how much AI you have available. I am certain my config has some silliness in it that someone more experienced would pick out, but ultimately I'm not sure how much that matters. My config is still reproducible enough that I have my very custom env up and running after a few commands on an arbitary macbook. > Does "picking up" a skill mean the same thing it used to? I personally feel confident in helping people move their config to Nix, so I would say yes. But it's a big question. > Do you fact check all the stuff AI tells you? How certain are you, you are learning correct information? Well, usually I have a more or less testable setup so I can verify whether the desired effect was achieved. Sometimes things don't work, which is when I start reaching for the docs or source code of for example the library I'm trying to use. > Struggling through unfamiliar topics, making mistakes and figuring out solutions by testing internal hypotheses is a big part of how deep, explanatory knowledge is acquired for human brains. I don't think this is lost. I iterate a lot. I think the claude code author does too, did they have something like +40k-38k lines of changes over the past year or so. I still use github issues to track what I want to get done when a solution is difficult to reach, and comment progress on them. Recently I did that with my struggles in cross-compiling Rust from Linux to macOS. It's just easier to iterate and I don't need to sleep overnight to get unstuck. > since these systems are fundamentally poisoned by their own talk, _I_ feel like this goes into the overthinking territory. I think software and systems will still die by their merits. Same applies to training data. If bugs regularly make it to end users and a competing solution has less defects, I don't think the buggy solution will stay any more afloat thanks to AI. So, I'd argue, the training data will be ok. Paradigms can still exist. Like Theory of Modern Go discouraging globals and init functions. And I think this was something that Tesla also had to deal with pre modern LLMs? As in not all drivers drove well enough that they wanted to use their data for trsining the autopilot. I really enjoyed your reply, thank you. | | |
| ▲ | jijijijij 3 hours ago | parent [-] | | I understand your use case and the benefit experienced, but quite frankly, I don't think that's easy to generalize or extrapolate to common problems justifying the expenses of this technology. Having a compiler or any kind of easy, fast formalized "sanity" check is a huge privilege of coding work when it comes to AI usage, something missing in almost every other industry. But even in tech the full extent of such capabilities is rather limited to a few programming languages etc.. Outside of those, confidence in understanding, vouching for the output is limited without actually RTFM. I mean, move fast and break things, but I don't think the quality of knowledge gain is comparable to doing it the hard way. Side note: I also think, prospectively, it's really bad, if pressure for efficiency on the tech stack used is reduced by making any mess seemingly manageable by AI interfacing (which is insanely inefficient and wasteful in someone else's backyard). Dev "pain" and productivity pressure are needed to improve ergonomics and performance, driving innovation. Why would nix improve, if it can be managed through a chat interface? Similarly, the whole human communication quirk of writing prose with each other becomes utterly meaningless, if expansion and compression of information is expected to happen through AI interface intermediaries anyway. A prose letter is formality and subtext of respectful human interaction, which becomes worthless/offensive, if done by a mindless machine. And if the need for prose vanishes, the AI overhead is fantastical, ridiculous compared to effectively sending the prompt information bits directly to the recipient (without expansion and compression in-between). Nothing makes me wanna scream more than LLMs talking with each other, no matter the language. That's just insanely stupid. If there is not value in formality and indirect communication, we can just cut that and use a trivially simple and amazingly efficient protocol for information exchange. > _I_ feel like this goes into the overthinking territory. I think software and systems will still die by their merits. Same applies to training data. If bugs regularly make it to end users and a competing solution has less defects, I don't think the buggy solution will stay any more afloat thanks to AI. But where is the training data coming from? I also think this is fallaciously extrapolating from prior tech innovation and questionable market narratives (considering the tech oligopoly). These models are not like lego, can't be tuned or adjusted like that, there is nothing linear about them. And if you spend all that investment money on manually fine-tuning answers, the tech itself does not warrant the cash, to begin with. That's not AI, that's just a lot of effort. The pyramids are also evidence of laborious human hubris and great expense, a sight to behold, but hardly a technological revolution with great ROI. I don't think refeeding model degradation is comparable to bad human input as with autopilot (besides, as if that's actually working/solved :D). Thing is, frequency of faulty human information is probably rather constant, while AI slop is exploding, drowning available total human crafted content (again, the scenario is AI wide adoption). And that's not even considering unique feedback mechanism, not fully understood. Who is gonna put out handcrafted, thoroughly thought out training content anymore, when the skill of learning itself atrophied widely? And who is gonna do it for free? Or who is gonna pay for it, when you also have to pay for the absurd energy and resource expenses at some point? Keep in mind, AI, in contrast to human intelligence, does not gain functional understanding and relies statistical tricks from crunching stupid amounts of data. One thought-out piece of code sufficient for you to get cooking, means nothing to the machine. To train these things, you need massive input. Again, where is all that clean data coming from? How much are you willing to pay for an AI service to help you a little with nix? If there was no refeeding degradation, we would have escape velocity and AGI. In that case, all bets are off and money becomes meaningless anyway. The expenses, the investments don't make sense. Nothing of this shit makes sense :D |
|
|
|
|
|
| ▲ | skzo 17 hours ago | parent | prev | next [-] |
| That's a brilliant analogy, I had the same experience with Huel and AI Assistants |
|
| ▲ | mawadev 16 hours ago | parent | prev [-] |
| Why do I feel like I've just read a covert advertisement? |
| |
| ▲ | cons0le 15 hours ago | parent | next [-] | | Sometimes I feel like the people here live on a different planet. I can't imagine what type of upbringing I would have to have, to start thinkinkg that "eating food" is an engineering problem to be solved. This might be a controversial opinion, but I for one, like to eat food. In fact I even do it 3 times a day. Don't yall have a culture that's passed down to you through food? Family recipes? Isn't eating food a central aspect of socialization? Isn't socialization the reason people wanted to go to the office in the firt place? Maybe I'm biased. I love going out to eat, and I love cooking. But its more than that. I garden. I go to the farmers market. I go to food festivals. Food is such an integral part of the human experience for me, that I can't imagine "cutting it out". And for what? So you can have more time to stare at the screen you already stare at all day? So you can look at 2% more lines of javascript? When I first saw commercials for that product, I truly thought it was like a medical/therapeutic thing, for people that have trauma with food. I admit, the food equivalent of an i.v. drip does seem useful for people that legitimately can't eat. | | |
| ▲ | AstroBen 14 hours ago | parent | next [-] | | I like eating, I just don't like spending so much time and decision fatigue on prep. I'm probably the target audience for Huel but I don't actually think it's good for you 90% of meals aren't some special occasion, but I still need to eat. Why not make it easy? Then go explore and try new things every now and then Treating food as entertainment is how the west has gotten so unhealthy | |
| ▲ | anttiharju 7 hours ago | parent | prev | next [-] | | > I can't imagine what type of upbringing I would have to have, to start thinking that "eating food" is an engineering problem to be solved. I was really busy with my master's degree, ok? :D | |
| ▲ | johnisgood 12 hours ago | parent | prev | next [-] | | I like satisfying my hunger (my goal most of the time when it comes to food), but making food is not a hobby to me. That said, cooking is often a nice, shared experience with my girlfriend. | |
| ▲ | xnorswap 15 hours ago | parent | prev | next [-] | | I'm with you on this one, the idea of trying to "optimise" away lunches and break time to cram in more "study time" seems utterly alien. | |
| ▲ | pixl97 11 hours ago | parent | prev [-] | | I'm a foodie, I love food and cooking and the eating experience. This said, I know people that food is a grudging necessity they'd rather do without. At the end of the day there's a lot of different kinds of people out there. |
| |
| ▲ | anttiharju 14 hours ago | parent | prev | next [-] | | I mean I don't think I'm giving a particularly favorable view of the product | | |
| ▲ | jerf 12 hours ago | parent [-] | | I expect AI ads to start with blindingly obvious overwhelmingly excited endorsments, but it won't take long for that to show up in the metrics that won't work very well past the initial intro, and they'll get more subdued over time... but they're always going to be at least positive. The old saying "there's no such thing as bad publicity" is wrong, and the LLMs aren't going to try to get you to buy things by being subtly negative on them. If nothing else, even if you somehow produced a (correct) study showing that does increase buying I think the marketers would just not be able to tolerate that, for strictly human reasons. They always want their stuff cast in a positive light. | | |
| ▲ | anttiharju 10 hours ago | parent [-] | | heh. I think I've seen an adtech company use AI influencers to market whatever product a customer wanted to sell. I got the impression that it initally worked really well, but then people caught on to the fact it was just AI and performance tanked. I don't actually know whether that was the case but that's the vibe I got from following their landing page over time. |
|
| |
| ▲ | jennyholzer4 15 hours ago | parent | prev [-] | | [flagged] |
|
