981–990 of 1001 posts
Earlier quoted context omitted.
It's a force multiplier. Think of having a secretary, or ten. These secretaries are not as good as an average human at most tasks, but they're good enough for tasks that are easy to double check. You can give them an immense amount of drudgery that would burn out a human.
What drudgery, though? Secretaries don't do a lot of drudgery. And a good one will see tasks that need doing that you didn't specify. If you're generating immense amounts of really basic make work, that seems like you're managing your time poorly.
Using them to replace core competencies will probably remain forbidden by professional ethics (writing court documents, diagnosing patients, building bridges). However, there are ways for LLMs to assist people without doing their jobs for them.
Law firms are already using LLMs to deal with large amounts of discovery materials. Doctors and researchers probably use it to summarize papers they want to be familiar with but don't have the energy to read themselves. Engineers might eventually be able to use AI to do a rough design, then do all the regulatory and finite element analysis necessary to prove that it's up to code, just like they'd have to do anyway.
I don't have a high-level LLM subscription, but I think with the right tooling, even existing LLMs might already be pretty good at managing schedules and providing reminders.
You can get your HN profile analyzed by it and it's pretty funny :) https://hn-wrapped.kadoa.com/ I'm using this to test the humor of new models.
You can get your HN profile analyzed by it and it's pretty funny :) https://hn-wrapped.kadoa.com/ I'm using this to test the humor of new models.
> Your obsession with data extraction makes me wonder if you're secretly a web scraper that gained sentience and is now posting on HN.
> You talk about AI automating tedious tasks so much that I'm surprised you haven't built an AI to write your HN comments for you yet.
Those are great. Well done! That it can just read your entire comment history gives it great potential for a whole new dimension of humor.
Here is a user script to replace HN profiles with this improved version.
Earlier quoted context omitted.
No need for thinking, that question can be found discussed and explained many times online and has almost certainly been part of the training data.
The fact that all the models I’ve tried except the thinking ones get it wrong suggests not. They get caught up in the idea that adding milk first cools it fastest and can’t escape from that
People making up their own benchmarks for these things has confirmed one thing for me: The bias that people think they mostly have original thoughts is extremely strong. I find if I have a “good” idea someone has probably already thought of it as well and maybe even written about it. About 0.01% of the time do I have an idea that one may consider novel and even that’s probably my own bias and overstated. This example just confirms that these models don’t really seem to reason and have a really hard time doing the basic generalization they can with fewer examples.
The cost is absurd (compared to other LLM providers these days). I asked 3 questions and the cost was ~0.77c. I do like how this is implemented as a bash tool and not an editor replacement though. Never leaving Vim! :P
That 0.77 can save hours of work though, fighting with or being misdirected by other LLM. And, relative to hourly rate, or a cup of coffee, it's incredibly insignificant, if just used for the heavy questions. My LLM client can switch between whatever models, mid conversation. So I'll have a question or two in the more expensive, then drop down to the cheaper for explanations/questions that help me understand. Rewind…
Earlier quoted context omitted.
> My estimate is that 80-90% of the code was written by AI Nice! It is entirely reasonable both to do that and to be excited about it. …buuut, if that’s what you’re doing, you should say so. Not: “no lines of code directly written, just directing the AI” Because those (gluing together AI code by hand and having the agent do everything) are different things, and one of them is much much MUCH harder to get right than t…
I don’t think this is a fair take. For self driving cars, you care about that because safety is involved and the reliability of the AI is the product itself. For OP, the product is the product, how they got there is mostly irrelevant. We don’t really care what IDE they used (outside of being a tooling nerd).
AI is hard; edge cases are hard. AI sucks at edge cases.
Between AI for cars and AI for software the long tail of edge cases that have to be catered for is different, yes.
...but I'm sure the same will apply for AI for art (e.g. hands), and AI for (insert domain here).
Obviously no analogy is perfect, but I think you have to really make an effort to look away from reality not to see the glaringly obvious parallels in cars, art, programming, problem solving, robots, etc. where machine learning models struggle with edge cases.
Does the tooling they used matter? no, not at all.
...but if they've claimed to solve the 'edge case problem', they've done something really interesting. If not, they haven't.
So, don't claim to have done something really interesting if you haven't.
You can say "I've been using AI to build a blah blah blah. It's great!" and that's perfectly ok.
You have to go out of your way to say "I've been using an AI to build blah blah blah and I haven't written any of it, it's all generated by AI". "no lines of code directly written" really? Why did you mention that? You got the AI to write your software for you? That sounds cool! Let's talk! Are you an AI consultant by any chance? (yes, they are). ...but.
No. You didn't. You really didn't. I'm completely happy to call people out for doing that; its not unfair at all.
Too many AI grifters out there.
Earlier quoted context omitted.
I like to make up my own tests, that way you know it is actually thinking. Tests that require thinking about the physical world are the most revealing. My new favourite is: You have 2 minutes to cool down a cup of coffee to the lowest temp you can. You have two options: 1. Add cold milk immediately, then let it sit for 2 mins. 2. Let it sit for 2 mins, then add cold milk. Which one cools the coffee to the lowest temp…
Yes absolutely this! We're working on these problems at FlyShirley for our pilot training tool. My go-to is: I'm facing 160 degrees and want to face north. What's the quickest way to turn and by how much? For small models and when attention is "taken up", these sorts of questions really send a model for a loop. Agreed - especially noticeable with small reasoning models.
Earlier quoted context omitted.
Moving a function or class? Yes. But moving arbitrary lines of code into their own function in a new module is still a PITA, particularly when the lines of code are not consecutive.
So is moving a function or class possible? What actions you need to take to accomplish that? Thanks