[Nextgrid]

Trial and error?

Just like it does when given an existing GPL’d source and dealing with its hallucinations, the agent could be operated on a black box (or a binary Windows driver and a disassembly)?

The GPL code helped here but as long as the agent can run in a loop and test its work against a piece of hardware, I don’t see why it couldn’t do the same without any code given enough time?

[dotancohen]

Presumably one would like to use the laptop before the million years it would take the million monkeys typing on a million typewriters to produce the Shakespearean WiFi driver.

Consider that even with the Linux driver available to study, this project took two months to produce a viable BSD driver.

[ssl-3]

This process took two months, including re-appraisals of the process itself, and it isn't clear that the calendar on the wall was a motivator.

The next implementation doesn't have to happen in a vacuum. Now that it has been done once, a person can learn from it.

They can discard the parts that didn't work well straight away, and stick to only the parts of the process that have good merit.

We'll collectively improve our methods, as we tend to do, and the time required will get shorter with each iteration.

[vitorsr]

Seems very promising but then you realize the LLM behind said agent was trained on public but otherwise copyright encumbered proprietary code available as improperly redistributed SDKs and DDKs, as well as source code leaks and friends.

In fact most Windows binaries have public debug symbols available which makes SRE not exactly a hurdle and an agent-driven SRE not exactly a tabula rasa reimplementation.