HackerLangs
TopNewTrendsCommentsPastAskShowJobs

danjc

963 karmajoined hace 11 años
SDG

Submissions

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

twitter.com
5 points·by danjc·hace 4 meses·0 comments

comments

danjc
·anteayer·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
·hace 28 días·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
·el mes pasado·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
·el mes pasado·discuss
It's not just annoying, it's tiring
danjc
·hace 2 meses·discuss
Plot twist: Apple PR team created this video to make claims that they slow older devices seem less credible.
danjc
·hace 2 meses·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
·hace 4 meses·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
·hace 7 meses·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
·hace 9 meses·discuss
I'd it's processed in 2 seconds, why not just process it immediately in memory?
danjc
·hace 9 meses·discuss
It's all jit context
danjc
·hace 10 meses·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
·hace 10 meses·discuss
You can just call yourself a reasoning model now
danjc
·hace 10 meses·discuss
This is written by someone who has no idea how transformers actually work
danjc
·hace 10 meses·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
·hace 10 meses·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
·hace 12 meses·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
·hace 2 años·discuss
Attention is all you need