33a

Ok, yeah that guy was pretty rude. That said I still wouldn't write a whole blog post about how I was wrong, but the other guy was an asshole...

I will still stand by my opinion though that this whole thing was remarkably light on technical substance.

Weirdly anti-intellectual. I'm not sure what the subtle nitpick the expert brought up, but from reading the comments I gathered that they correctly pointed out that appending to a vector is merely amortized O(1), not truly worst case constant time. This is actually kind of a big deal and is an important distinction to make. As a corollary, it means you can't just use a vector as a constant time sequence data structure in a real time application unless you preallocate it.

This is my attempt to deconstruct the idea of a software factory into a few basic components

Maybe the public could pitch in if they decrypted the chain of thought reasoning tokens, but this may be too much to expect from a company whose name starts with "Open".

If they made a low power/mobile version, this could be really huge for embedded electronics. Mass produced, highly efficient "good enough" but still sort of dumb ais could put intelligence in house hold devices like toasters, light switches, and toilets. Truly we could be entering into the golden age of curses.

Goodheart's Law of college admissions

You can probably get any coding agent with this if you put these instructions in the README/CLAUDE.md/AGENTS.md or whatever of your repo.

It's unclear to me if Bob is working as intended or how we should classify these types of bugs. Threat modeling this sort of prompt injection gets murky, but in general don't put untrusted markdown into your AI agents.

A lot of security problems can be solved by moving slower.

Pedestrians on phones, not drivers on phones.

It's actually pretty easy to detect that something is obfuscated, but it's harder to prove that the obfuscated code is actually harmful. This is why we still have a team of humans review flagged packages before we try to get them taken down, otherwise you would end up with way too many false positives.

When we find malware on any registry (npm, rubygems, pypi or otherwise), we immediately report it to the upstream registry and try to get it taken down. This helps reduce the blast radius from incidents like this and mitigates the damage done to the entire ecosystem.

You can call it ambulance chasing, but I think this is a good thing for the whole software ecosystem if people aren't accidentally bundling cryptostealers in their web apps.

And regarding not copying massive trees of untrusted dependencies: I am actually all for this! It's better to have fewer dependencies, but this is also not how software works today. Given the imperfect world we have, I think it's better to at least try to do something to detect and block malware than just complain about npm.