HackerLangs
TopNewTrendsCommentsPastAskShowJobs

danjc

963 karmajoined 11 lat temu
SDG

Submissions

LLM Doesn't Write Correct Code. It Writes Plausible Code

twitter.com
5 points·by danjc·4 miesiące temu·0 comments

comments

danjc
·przedwczoraj·discuss
It would be great if we could have AI that wasn't trying to emulate a human. When it expresses emotion, we should see that as a bug that needs to be fixed.
danjc
·28 dni temu·discuss
Even if they could practically restrict access to US citizens only, I would expect them not to - it would be hard to regain that once lost and they need a global market for growth.
danjc
·w zeszłym miesiącu·discuss
As much as it's true that a novice will generally use AI to build a sloppy mess, I've also had success unsloppifying through some careful prompting.
danjc
·w zeszłym miesiącu·discuss
It's not just annoying, it's tiring
danjc
·2 miesiące temu·discuss
Plot twist: Apple PR team created this video to make claims that they slow older devices seem less credible.
danjc
·2 miesiące temu·discuss
A browser plugin that scores webpage content based on how likely it is to have been AI-generated would be quite useful.

Browser vendors can't build this.
danjc
·4 miesiące temu·discuss
I've been waiting for someone to say this. An agent will generally produce far more code than technically necessary for the task. It's a kind of over engineering which makes it increasingly harder to wrap your head around the codebase.
danjc
·7 miesięcy temu·discuss
The issue is provenance. We need cameras and phones to digitally sign photos so we can easily verify an unadulterated image.

You also want to be able chain signing so that for example a news reporter could take a photo, then the news outlet could attest its authenticity by adding their signature on top.

Same principle could be applied to video and text.
danjc
·9 miesięcy temu·discuss
I'd it's processed in 2 seconds, why not just process it immediately in memory?
danjc
·9 miesięcy temu·discuss
It's all jit context
danjc
·10 miesięcy temu·discuss
It looks like true 0-temperature (i.e. determinism) will happen. Here's some good context: https://thinkingmachines.ai/blog/defeating-nondeterminism-in...
danjc
·10 miesięcy temu·discuss
You can just call yourself a reasoning model now
danjc
·10 miesięcy temu·discuss
This is written by someone who has no idea how transformers actually work
danjc
·10 miesięcy temu·discuss
I think you've nailed it there. OpenAI are at a point where the risk of continuing to hedge on mcp outweighs the risk of mcp calls doing damage.
danjc
·10 miesięcy temu·discuss
Once you notice characters aren't eating, you'll never not see it again.

Related, where they're drinking coffee from a disposable cup, you can almost always tell it's empty by how they handle it.
danjc
·12 miesięcy temu·discuss
What's missing here is tool use.

For example, if the llm had a compile tool it would likely have been able to correct syntax errors.

Similarly, visual errors may also have been caught if it were able to run the program and capture screens.
danjc
·2 lata temu·discuss
Attention is all you need