Retro_Dev

Joined 1 year ago

Karma

923

Submissions

110

Member since

May 29

Religious, Linux user, Programmer.

View on Hacker News

Recent submissions

Comment · 42 minutes ago

Yet practice without theory is terrible in both theory and practice.

Comment · 46 minutes ago

> A Brazilian labor court fined two lawyers for hiding a prompt-injection command in a filing designed to manipulate the court's AI review system.

Not having read the article, but I feel this is a risky stand for the court to take. It makes sense that you should stop others from impeding your review system - however you implement it, yet "prompt injection" is hard to define. What is stopping the court from fining people for a "logical argument" in future filings?

Nanbeige4.3-33B – Flagship teacher LLM huggingface.co

4 Retro_Dev 2 days ago 0 comments

Comment · 3 days ago

I like how the plot summary paragraph of the wikipedia article does not contain the letter "e" as well. Somewhat related is Gadsby - another novel without the letter "e" - https://en.wikipedia.org/wiki/Gadsby_(novel)

Interfaces in Zig bradcypert.com

1 Retro_Dev 3 days ago 0 comments

Comment · 13 days ago

I'm a bit confused why people are freaking out about these term changes - Meta scrapes my website already on a fairly regular basis (even with robots.txt). Is the point of this change to justify more intense scraping?

Comment · 15 days ago

It's probably easier to look at the source code than try to decompile it: https://github.com/anthropics/claude-code

Comment · 16 days ago

Comment · 17 days ago

don't give them too many ideas, or my water bill will go up

Comment · 17 days ago

Others can confirm, but I suspect a lot of inefficiencies in large company programming projects are due to multiple people working on the same code - where you ultimately have to let both above and below average programmers work, and fixing bugs or improving existing implementations is more difficult because of company politics or interactions with others.

Comment · 18 days ago

Assuming you literally mean "closed-source" (and not just closed weight), then yes I totally agree - it would be really nice if the training data for some LLM were reliably (and ethically sourced), but more important to our assurance of the model that it is byte-for-byte reproducible by us, as to prevent these "sleeper agents" from appearing.

Comment · 19 days ago

I like using the aria2[0] download utility - I don't think I've downloaded anything bigger than a dozen megabytes through a web browser for the last several years, and this method allows me more protocols, multiple connections, and of course continuing downloads. That said, it's nice someone found a solution to the problem - makes life easier for everyone who doesn't use an external download utility... How do you even go about finding the solutions to bugs like this?

[0]: https://aria2.github.io/

Comment · 24 days ago

my bad - I missed this. 230 million parameters is very small though.

Comment · 24 days ago

> 80+ tok/sec on the smallers models.

how does this compare against existing TPUs? Also, how small is "smallers models?"

Comment · 24 days ago

Excellent idea. Brain surgery would be an ideal use for AI here. Think about how much money we would save if we no longer needed to pay for neurosurgeons, but instead pay the energy cost to run a precise AI-controlled drill, forceps, and suction tube. Better yet, we could massively speed up brain surgery by forgoing tool-assisted LLMs and just have jev-like system-one decision models control the position and function of these tools in real-time. I see no problems here. In the meantime, all those poor students who study so hard to be a good neurosurgeon can instead devote themselves to studying some sort of fungus that takes over mammal brains and makes them want to study fungi... Or wait, is that AI?

https://www.xkcd.com/1664/