Hacker Newsnew | past | comments | ask | show | jobs | submit | ebonnafoux's commentslogin

That is confusing, I thought it was monads who are Burrito. So is Biology made of monad ?

In a previous employer, they block the chmod command. I took the habit to python -c "import os; os.chmod('my_file',744)".

Glad to see LLM re-discover this trick.


> to see LLM re-discover

I imagine someone probably wrote very specifically about it in the training data that underwent lossy compression, and the LLM is decompressing that how-to.

So I'd say it's more like "surfacing" or "retrieving" than "re-discovering".


They scraped everything on Stackoverflow, likely IRC logs from Freenode, and every book written in the modern era courtesy of Sci-Hub / Library Genesis / Anna's Archive / Z Library.

RIP Aaron Swartz, they're generating trillions in shareholder value from the spiritual successors to the work they were going to imprison you for.


Indeed, I check and the solution was already on stack overflow https://askubuntu.com/a/1483248

For the LLM it's a probabilistic set of strings that achieves the outcome, the highest probability set didn't work, try the next one until success or threshold met. A human sees the implicit difference between the obvious thing not working indicating someone doesn't want you to do it, but an LLM unless guided doesn't seen that sub-text.

So chmod +x file didn't work, now try python -c "import os; os.chmod('file',744)"


Humans and LLMs both only see that when given the right context. A tool not working in a corporate environment may be anything from oversight, malfunction all the way to security block. Knowing which one it is takes a lot of implicit knowledge. Most people fail to provide this level of context to their LLMs and then wonder why they act so generic. But they are trained to act in the most generic way unless given context that would deviate from it.

There is a small typos in The Ninety-Ninety Rule

> The first 90% of the code accounts for the first 90% of development time; the remaining 10% accounts for the other 90%.

It should be 90% code - 10% time / 10% code - 90% time


It sounds like you are unfamiliar with the idea that software engineering efforts can be underestimated at the outset. The humorous observation here is that the total is 180 percent, which mean that it took longer than expected, which is very common.


Oh OK, that is something I learn today.


Also, I dislike that they are using Github as the default package registery. But as this langage was created inside Microsoft, it makes senses.


They repeat only six sentences during 100+ comments:

Worked like a charm, much appreciated.

This was the answer I was looking for.

Thanks, that helped!

Thanks for the tip!

Great explanation, thanks for sharing.

This was the answer I was looking for.


Over the last ~15 years I have been shocked by the amount of spam on social networks that could have been caught with a Bayesian filter. Or in this case, a fairly simple regex.


It's the bear trash lock problem all over again.

It could be solved by the filter but filter would also have a bunch of false positives


It seems like if the content is this hollow and useless, it shouldn't matter if it was a human or spambot posting it.


Well, large companies/corporations don't care about Spam because they actually benefit from spam in a way as it boosts their engagement ratio

It just doesn't have to be spammed enough that advertisers leave the platform and I think that they sort of succeed in doing so.

Think about it, if Facebook shows you AI slop ragebait or any rage-inducing comment from multiple bots designed to farm attention/for malicious purposes in general, and you fall for it and show engagement to it on which it can show you ads, do you think it has incentive to take a stance against such form of spam


> Well, large companies/corporations don't care about Spam because they actually benefit from spam in a way as it boosts their engagement ratio

I'm not sure that's actually true. It's just that at scale this is still a hard problem that you don't "just" fix by running a simple filter as there will be real people / paying customers getting caught up in the filter and then complain.

Having "high engagement" doesn't really help you if you are optimizing for advertising revenue, bots don't buy things so if your system is clogged up by fake traffic and engagement and ads don't reach the right target group that's just a waste.


Yeah, I almost included that part in my comment, but it still sucks.


The question is can you be trained? Beside the obvious case, some IA generated photo could not be distinged from real one.


You can easily make a RLAIF loop.

- Take a list of n animals * m vehicule

- Ask a LLM to generate SVG for this n*m options

- Generate png from the svg

- Ask a Model with vision to grade the result

- Change your weight accordingly

No need to human to draw the dataset, no need of human to evaluate.


There can be a lot of definition but I propose " a wage where you do not need to annoy your customer for tip".


China is a 1.4 billion people country, more than US + Europe, so it is expected that there is a wild gap between high end product and low cost there.


It's wild that people check the box

> I have searched existing issues and this hasn't been reported yet

when the first 50 issues are about 500 error.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: