691–700 of 828 posts
Can we also have "helpdesk mode"? Right now when you ask an LLM to solve some problem, it immediately responds with many steps, whereas as a user I want to go through it step by step. It would be nice if the LLM provided the solution in that way. This also makes it less cumbersome to tell the LLM where the solution went wrong.
Earlier quoted context omitted.
>big chunk of time spent studying is actually just searching. This is a good thing in many levels. Learning how to search is (was) a good skill to have. The process of searching itself also often leads to learning tangentially related but important things. I'm sorry for the next generations that won't have (much of) these skills.
Searching is definitely a useful skill, but once you've been doing it for years you probably don't need the constant practice and are happy to avoid it.
Earlier quoted context omitted.
The anti cancer diet absolutely works if you want to reduce the odds of getting cancer. It probably even works to slow cancer compared to the average American diet. Will it stop and reverse a cancer? Probably not.
I thought it was high fiber diets that reduce risk of cancer (ever so slightly), because of reduced inflammation. Not fruity diets, which are high in carbohydrates.
I'm confused. My kid does this on my ChatGPT account all the time. What is new here? I cannot emphasize how good a teacher ChatGPT is, until it misinforms (and human teachers also do). And it also stays open to questioning without making the student feel stupid for asking. The good part is that ChatGPT will accept a mistake, but a human teacher will get annoyed. The only thing I keep reminding my kid is to keep the B…
Earlier quoted context omitted.
> How are you supposed to spot errors if you don't know the material? By noticing that something is not adding up at a certain point. If you rely on an incorrect answer, further material will clash with it eventually one way or another in a lot of areas, as things are typically built one on top of another (assuming we are talking more about math/cs/sciences/music theory/etc., and not something like history). At that…
It absolutely does not work that way. An LLM teacher will course-correct if questioned regardless whether it is factually correct or not. An LLM, by design, does not, in any capacity whatsoever have a concept of factual correctness.
With regard to them not, in any capacity whatsoever having a concept of factual correctness, LLMs are very much just like humans: We're not magic, we don't know the underlying nature of reality.
This is why it took us so long to replace Aristotelean physics with Newtonian, let alone Newtonian with QM and GR, and both QM and GR are known to be flawed but nobody has worked out the next step. It's just that humans are fairly unwilling to change their minds about how physics works in light of evidence, we often just defer to famous people, c.f. to Aristotle, then to Newton, then to Einstein.
We humans make this (opposite) mistake so hard and so often, that there's a saying that "science progresses one funeral at a time": https://en.wikipedia.org/wiki/Planck%27s_principle
I could also have thrown into this list miasma, phlogiston, that Columbus definitely wasn't the only person who knew it was round and just got lucky with the existence of the Americas after having gotten the size of both Earth and Asia catastrophically wrong, or phrenology.
An underrated quality of LLMs as study partner is that you can ask "stupid" questions without fear of embarrassment. Adding in a mode that doesn't just dump an answer but works to take you through the material step-by-step is magical. A tireless, capable, well-versed assistant on call 24/7 is an autodidact's dream. I'm puzzled (but not surprised) by the standard HN resistance & skepticism. Learning something online 5…
... your "AI" is also trained on the above incorrect, outdated or hostile content ...
Earlier quoted context omitted.
My favourite story of that involved attempting to use LLM to figure out whether it was true or my hallucination that the tidal waves were higher in Canary Islands than in Caribbean, and why; it spewed several paragraphs of plausibly sounding prose, and finished with “because Canary Islands are to the west of the equator”. This phrase is now an inner joke used as a reply to someone quoting LLMs info as “facts”.
This is meaningless without knowing which model, size, version and if they had access to search tools. Results and reliability vary wildly. In my case I can’t even remember last time Claude 3.7/4 has given me wrong info as it seems very intent on always doing a web search to verify.
A not-so-subtle example from yesterday: Claude Code claiming to me yesterday assertion Foo was true, right after ingesting the logs with the “assertion Foo: false” in it.
Can we also have "helpdesk mode"? Right now when you ask an LLM to solve some problem, it immediately responds with many steps, whereas as a user I want to go through it step by step. It would be nice if the LLM provided the solution in that way. This also makes it less cumbersome to tell the LLM where the solution went wrong.
It’s just text though right? Just perform step 1, if you have any issues say “I had this issue at step 1”. Also you can ask it to give one step at a time.
One problem with LLMs giving so many steps at once is that the first step scrolls from the screen and I have to stop the LLM, scroll back and find the first step. The UX could be much improved here (with little effort, I believe).
Earlier quoted context omitted.
>When I have a vague idea, it helps me narrow down the correct terminology for it so the opposite of Stack Overflow really, where if you have a vague idea your question gets deleted and you get reprimanded. Maybe Stack Overflow could use AI for this, help you formulate a question in the way they want.
Maybe. But, it's been over a year since I used StackOverflow, primarily because of LLMs. Sure, I could use an LLM to formulate a question that passes SO's muster. But why bother, when the LLM can almost certainly answer the question as well; SO will be slower; and there's a decent chance that my question will be marked as a duplicate (because it pattern matches to a similar but distinct question).
Furthermore the LLM might give an answer but probably not explain with the best skills available why the answer is the way it is. This is of course something that varies with StackOverflow but there it is at least possible that somebody with deep technical knowledge decides a question is worth answering deeply.
Earlier quoted context omitted.
> Learning something online 5 years ago often involved trawling incorrect, outdated or hostile content and attempting to piece together mental models without the chance to receive immediate feedback on intuition or ask follow up questions. That trained and sharpened invaluable skills involving critical thinking and grit.
And also taught people how to actually look for information online. The average person still does not know how to google, I still see people writing whole sentences in the search bar.
Search engines have gotten way better at handling complete sentences in recent years, to the point where I often catch myself deleting my keyword query and replacing it with a sentence before I even submit it, because I know I will be able to more accurately capture what it is I am searching for in a sentence.