Remix clone Hacker News

Good point in the post about confidence - most people equate confidence with accuracy - and since AIs always sound confident, they always sound correct

▲

kibwen a day ago | parent | next [-]

There's a reason the "con" in "con man" stands for "confidence". Turns out the illusion of confidence is the easiest way to hack the human brain.

	▲	jfengel a day ago \| parent [-]
		Except that's not what "confidence man" means. It means that you gain their confidence/trust, then betray it. A con man often uses the illusion of confidence to gain trust, though that's not the only way. The reverse also works: gain their trust by seeming unconfident and incapable, and thus easily taken advantage of.

▲

rglover a day ago | parent | prev | next [-]

Yep. Last night I was asking ChatGPT (4o) to help me generate a simple HTML canvas that users could draw on. Multiple times, it spoke confidently of its not even kind of working solution (copying the text from the chat below):

- "Final FIXED & WORKING drawing.html" (it wasn't working at all)

- "Full, Clean, Working Version (save as drawing.html)" (not working at all)

- "Tested and works perfectly with: Chrome / Safari / Firefox" (not working at all)

- "Working Drawing Canvas (Vanilla HTML/JS — Save this as index.html)" (not working at all)

- "It Just Works™" (not working at all)

The last one was so obnoxious I moved over to Claude (3.5 Sonnet) and it knocked it out in 3-5 prompts.

▲

numpad0 16 hours ago | parent | next [-]

IME, it's better to just delete erroneous responses and fix prompts until it works.

They are much better at fractally subdividing and interpreting inputs like a believer of a religion, than at deconstructing and iteratively improving things like an engineert. It's waste of token count trying to have such discussions with an LLM.

▲

Aeolun a day ago | parent | prev | next [-]

4o is almost laughably bad at code compared to Claude.

▲

dullcrisp a day ago | parent | prev [-]

To be fair, I wouldn't really expect working software if someone described it that way either.

▲

rglover a day ago | parent [-]

Those are not my prompts. Those were the headings it put above the code it generated in its responses.

Even if my prompt was low-quality, it doesn't matter. It's confidently stating that what it produced was both tested and working. I personally understand that's not true, but of all the safety guards they should be putting in place, not lying should be near the top of the list.

	▲	mattgreenrocks a day ago \| parent [-]
		Intellectual humility is just as rare with AI as it is with humans.

▲

morkalork a day ago | parent | prev [-]

The number of times I've caught chatgpt passing off something borked with perfect confidence is growing but what's truly annoying is when you point it out and you get that ever so cheerful "oh I'm so sorry teehee" response from it. It's dumb stuff too like a formula it's simplified based on a assumption that was never prompted.