Am I an outlier or do you just judge people for weird reasons? I’ve never seen an IDE person judge a terminal person, it’s always the other way around - what’s up with that?

I’m building something using LLMs to scrape websites/socials for unstructured event data from combined text/images and the only way I’ve managed to get 100% consistent results for a reasonable cost is to break the task down into very small pieces that reduce the scope of mistakes significantly.

At present, for reasonable complex tasks, Codex/Claude will happily code you into an expensive corner.

So I was disappointed by what felt like very weak arguments in the article. Basically seems to come down it “it can be abused”. But many things can be abused. The solution is to fix the abuse problem.

I’d like to hear stronger arguments against these devices, so that I’m better informed locally.

We need to revitalize research into capabilities-based security on consumer OSs, which AFAIK is the only thing that solves this problem. (Web browsers - literally user “agents” - solve this problem with capabilities too: webapps get explicit access to resources, no ambient authority to files, etc.)

Solving this problem will only become more pressing as we have more agents acting on our behalf.

[1] https://en.wikipedia.org/wiki/Confused_deputy_problem

8) ChatGPT wouldn’t let me generate a script to crack a password (even though I suspected I knew all but 2 characters in a 16 character password, which makes it highly unlikely I’m randomly trying to hack something)

The stupidest part of this is I could easily do these things myself, I just wanted to save a few minutes.