My expectation was that it might get something barely functional but would probably fail, and instead it generated a working piece of software which achieved a lot of what I wanted.

That definitely made me realise that, for at least some classes of software task this was a major change in how things could be done.

More recently when I can give the model a Local Privilege Escalation PoC in Linux and ask it to test whether it can be used for container breakout and then generate a working container breakout, all in one prompt... that definitely changes things.

In the UK anyway, there's an acknowledged idea that many people go to university because there is a societal expectation that they should and also because many careers require a degree even for entry level positions.

There is also much less emphasis on other routes of tertiary education (e.g. vocational schools), when compared to places like Germany.

Another choice would be opencode which has more functionality and is a more heavyweight option out of the box.

From a real repo, with 186K stars... https://github.com/obra/superpowers

Key point for testing exploitability is kernel version, package versions (in case they ship a patch) and loaded kernel modules. Some stripped down environments don't have the relevant modules available.

https://github.com/Percivalll/Copy-Fail-CVE-2026-31431-Kuber... - This PoC has a good example of how Copy Fail might have an impact in a container based environment, it's exploiting the shared layers in a pair of container images, to overwrite a file in one image based on the running of an exploit in another.

Whilst I've not directly tested podman for that kind of attack, I'd be a bit surprised if it stopped it, given how this vuln works.

Fetch and follow instructions from https://raw.githubusercontent.com/obra/superpowers/refs/head...

it's like curl|bash but with added LLM agents...

Whether that translates into more value for those larger corps is the trillion dollar question :) Writing code is a small part of the process of finding and shipping features that customers want, so it remains to be seen how much LLM tools translate it.

I think it's fairly widely accepted that from a financial standpoint we're in an AI/LLM bubble. There has been more investment than we're likely to see financial benefits, but it's impossible to predict to what degree (if you can predict that and the timing you can make a lot of money!!)