[Racing0461]

unpopular opinion: llm responses being wrong is still valuable to me since it gives me a better jumping off point to exploring than nothing at all. especially with something like coding that can easily be back-propagated due to something not compiling/not working as intended. could be harmful in other areas tho.

[gremlinsinc]

yeah, if the LLM gives me 2 truths that are beyond the documentation, like an edge case or maybe an example in a better describes way for me to grok, and one false thing, usually the false thing is so bad i can tell it's false or it's truthy but the value from the two truths exceeds the negative value of the falsehood.

Generally speaking though you can also cut back on hallucination by asking for a source from a second LLM or using good retrospections and adding system messages to ensure if it doesn't know an answer to say so and not make one up.

Really, I think hallucination is the wrong word bullshitting or gaslighting might be better. You're asking it something and it thinks you want an answer any answer so if it doesn't know it makes it up. Similar to people who confess to crimes they didn't do because of distressful interrogation tactics.

[gavinhoward]

Author here.

My docs will include tutorial links at the top, and those tutorials will focus on accomplishing common tasks.

I believe that's a good jumping off point.

[circuit10]

You can’t realistically cover every use case. With an LLM you can say something like “Make me a program that sets up an SDL window with the title ABCD that has a 396x224 RGB565 framebuffer and moves around a red square using the WASD keys by using a loop to fill in pixels in that framebuffer and then quits when it reaches the right edge of the screen” and it has a reasonable chance of making something that works or at least is easy to adjust into something that does. Just because sometimes it might not work the first time isn’t a good reason to try to stop people from using it entirely

[gavinhoward]

I would bet good money that, as a use case becomes more niche, an LLM's output becomes more wrong. If that's true, your assertion would be wrong.

[circuit10]

It does become more wrong, yes, but blocking it isn’t going to help it get any better. The idea that everything an LLM does can be replaced by documentation isn’t true

[gavinhoward]

> The idea that everything an LLM does can be replaced by documentation isn’t true

An LLM is false value, so I'm not worried about that.

[circuit10]

How is it false? I’d say an LLM is like the output you’d get if you forced someone to write something with a strict time limit and without being allowed to go back and edit things or look anything up - likely to be wrong about anything that needs deep thought, but not entirely useless for simple things that are just tedious like boilerplate code

[niederman]

I can promise you your tutorials will offer far fewer jumping-off points than an LLM.

[gavinhoward]

I can promise you that my fewer tutorials will be correct, not incorrect. An incorrect jumping off point is worse than none at all.

[Racing0461]

> An incorrect jumping off point is worse than none at all.

incorrect.

[gavinhoward]

How so?