351–360 of 365 posts
Also, why would I want a lossy encyclopedia? Disk space is cheaper than GPUs. I can host searchable dumps of the full Wikipedia and Stack Overflow in cheap commodity hardware.
The only good point of the analogy is that is self-declared as questionable.
People don't interact with encyclopedias by chatting with them. Also, why would I want a lossy encyclopedia? Disk space is cheaper than GPUs. I can host searchable dumps of the full Wikipedia and Stack Overflow in cheap commodity hardware. The only good point of the analogy is that is self-declared as questionable.
That is exactly the point of the analogy. A lossy encyclopedia is obviously a bad thing! The analogy helps illustrate why using raw LLMs to look things up in the same way as an encyclopedia is a bad idea.
Earlier quoted context omitted.
> In any other universe, we would be blaming the service rather than the user. I think the key question is "How is this service being advertised?" Perhaps the HN crowd gives it a lot of slack because they ignore the advertising. Or if you're like me, aren't even aware of how this is being marketed. We know the limitations, and adapt appropriately. I guess where we differ is on whether the tool is broken or not (hence…
The point you were making elsewhere in the thread was that "this is a bad use case for LLMs" ... "Don't use LLMs for dosing guidelines." ... "Using dosing guidelines is a bad example for demonstrating how reliable or unreliable LLMs are", etc etc etc. You're blaming the user for having a bad experience as a result of not using the service "correctly". I think the tool is absolutely broken, considering all of the peop…
Definitely. Just as I used to blame people for misusing search engines in the pre-LLM era. Or for using Wikipedia to get non-factual information. Or for using a library as a place to meet with friends and have lunch (in a non-private area).
If you're going to try to use a knife as a hammer, yes, I will fault you.
I do expect that if someone plans to use a tool, they do own the responsibility of learning how to use it.
> If you're taking the position that it's the user's fault for asking LLMs a question it won't be good at answering, then you can't simultaneously advocate for not censoring the model. If it's the user's responsibility to know how to use ChatGPT "correctly", the tool (at a minimum) should help guide you away from using it in ways it's not intended for.
Documentation, manuals, training videos, etc.
Yes, I am perhaps a greybeard. And while I do like that many modern parts of computing are designed to be easy to use without any training, I am against stating that this is a minimum standard that all tools have to meet.
Software is the only part of engineering where "self-explanatory" seems to be common. You don't buy a board game hoping it will just be self-evident how to play. You don't buy a pressure cooker hoping it will just be safe to use without learning how to use it.
So yes, I do expect users should learn how to use the tools they use.
Earlier quoted context omitted.
Perhaps the absolute worst use-case for an LLM
My mom was looking up church times in the Philippines. Google AI was wrong pretty much every time. Why is an LLM unable to read a table of church times across a sampling of ~5 Filipino churches? Google LLM (Gemini??) was clearly finding the correct page. I just grabbed my mom's phone after another bad mass time and clicked on the hyperlink. The LLM was seemingly unable to parse the table at all.
People don't interact with encyclopedias by chatting with them. Also, why would I want a lossy encyclopedia? Disk space is cheaper than GPUs. I can host searchable dumps of the full Wikipedia and Stack Overflow in cheap commodity hardware. The only good point of the analogy is that is self-declared as questionable.
"Also, why would I want a lossy encyclopedia?" That is exactly the point of the analogy. A lossy encyclopedia is obviously a bad thing! The analogy helps illustrate why using raw LLMs to look things up in the same way as an encyclopedia is a bad idea.
> The key thing is to develop an intuition for questions it can usefully answer vs questions that are at a level of detail where the lossiness matters.
If that intuition is not explained, it's no different than "works for me, you're using it wrong", which is definitely an argument, but not the best one.
I mean, I'm confident lots of people can use LLMs well, but I don't understand how the analogy is supposed to teach anything about it.
Earlier quoted context omitted.
I don’t disagree that you should use your doctor as your primary source for medical decision making, but I also think this is kind of an unrealistic take. I should also say that I’m not an AI hype bro. I think we’re a long ways off from true functional AGI and robot doctors. I have good insurance and have a primary care doctor with whom I have good rapport. But I can’t talk to her every time I have a medical question…
I always thought “ask your doctor” was included for liability reasons and not a thing that people actually could do. I also have good insurance and a PCP. The idea that I could call them up just to ask “should I start doing this new exercise” or “how much aspirin for this sprained ankle?” is completely divorced from reality.
That's exactly what I (and most people I know) routinely do both in Italy and France. Like, "when in doubt, call the doc". I wouldn't know where to start if I had to handle this kind of stuff exclusively by myself.
Earlier quoted context omitted.
"Also, why would I want a lossy encyclopedia?" That is exactly the point of the analogy. A lossy encyclopedia is obviously a bad thing! The analogy helps illustrate why using raw LLMs to look things up in the same way as an encyclopedia is a bad idea.
I'm puzzled by this part then: > The key thing is to develop an intuition for questions it can usefully answer vs questions that are at a level of detail where the lossiness matters. If that intuition is not explained, it's no different than "works for me, you're using it wrong", which is definitely an argument, but not the best one. I mean, I'm confident lots of people can use LLMs well, but I don't understand how t…
There's not much I can do about the intuition thing. I've been trying to figure out ways to teach people to use LLMs for over three years now, but it genuinely comes down to them being utterly weird and unintuitive pieces of technology that pretend to be easy to use when they aren't.
The only way to get truly competent with them is to put in the time deliberately experimenting to figure out what does and doesn't work.
Earlier quoted context omitted.
I'm puzzled by this part then: > The key thing is to develop an intuition for questions it can usefully answer vs questions that are at a level of detail where the lossiness matters. If that intuition is not explained, it's no different than "works for me, you're using it wrong", which is definitely an argument, but not the best one. I mean, I'm confident lots of people can use LLMs well, but I don't understand how t…
The core analogy is intended as a warning: this is a thing that looks like an encyclopedia but really isn't. There's not much I can do about the intuition thing. I've been trying to figure out ways to teach people to use LLMs for over three years now, but it genuinely comes down to them being utterly weird and unintuitive pieces of technology that pretend to be easy to use when they aren't. The only way to get truly…
https://www.anthropic.com/claude-code
> Unleash Claude’s raw power directly in your terminal.
> Search million-line codebases instantly.
> Turn hours-long workflows into a single command.
> Your tools. Your workflow. Your codebase, evolving at thought speed.
--
> Watch as Claude Code tackles an unfamiliar Next.js project, builds new functionality, creates tests, and fixes what’s broken
No mention of "weird and unintuitive". It sounds like a dream. It sounds like it would accept a prompt for a niche raspberry pi skeleton and work with it. Can you really blame a beginner for buying the product and being disappointed?
You should be angry at the LLM companies. While you're trying to teach people, they're working to generate tons of unsatisfied customers. And they come here, and you answer them for free? It doesn't make much sense to me.
Earlier quoted context omitted.
The core analogy is intended as a warning: this is a thing that looks like an encyclopedia but really isn't. There's not much I can do about the intuition thing. I've been trying to figure out ways to teach people to use LLMs for over three years now, but it genuinely comes down to them being utterly weird and unintuitive pieces of technology that pretend to be easy to use when they aren't. The only way to get truly…
Well, Claude Code is sold as an easy to use magic tool. https://www.anthropic.com/claude-code > Unleash Claude’s raw power directly in your terminal. > Search million-line codebases instantly. > Turn hours-long workflows into a single command. > Your tools. Your workflow. Your codebase, evolving at thought speed. -- > Watch as Claude Code tackles an unfamiliar Next.js project, builds new functionality, creates tests,…
Earlier quoted context omitted.
Well, Claude Code is sold as an easy to use magic tool. https://www.anthropic.com/claude-code > Unleash Claude’s raw power directly in your terminal. > Search million-line codebases instantly. > Turn hours-long workflows into a single command. > Your tools. Your workflow. Your codebase, evolving at thought speed. -- > Watch as Claude Code tackles an unfamiliar Next.js project, builds new functionality, creates tests,…
The reason I shout "weird and unintuitive" from the rooftops is that no LLM vendor will ever describe their weird and unintuitive products that way.
https://www.anthropic.com/solutions/code-modernization:
Generate dependency graphs, identify dead code, and prioritize refactoring based on code complexity metrics and business impact.
Transform legacy codebases systematically while maintaining business continuity.
Claude Code preserves critical business logic while modernizing to current frameworks.
Claude Code can seamlessly create unit tests for refactored code, identify missing test coverage, and help write regression tests.
Identify and patch vulnerabilities while maintaining regulatory compliance patterns embedded in legacy systems.
Create modern documentation from undocumented legacy code, capturing institutional knowledge before it's lost.