It cloned one of the many open source ones available is what you mean.

As long as you give it deterministic goals / test criteria (compiles, lints, tests, E2E tests, achieve 100% parity with existing solution etc) it will brute force its way to a solution. Codex will work for hours/days, even weeks sometimes, until it has finished. A person would never work this way, but since this just runs in the background, there’s no issue with this approach except if you need it fast.

▲

xyzzy_plugh 2 days ago | parent [-]

No, it might figure out the solution but even after many days there's no assurance that it won't get stuck making the same mistakes over and over again, never getting closer to a solution. I've seen this many times.

▲

manmal 2 days ago | parent | next [-]

Getting in a loop does still happen, yes. If you run codex in tmux and let another agent just occasionally check on progress, it can be prevented. That’s not even expensive - checking every 30 minutes suffices. The watchdog agent can then press Esc in tmux and send a message, maybe do some research to get it unstuck etc

▲

minimaxir 2 days ago | parent | prev [-]

Definitely have not seen that with Opus 4.5.

	▲	manmal 2 days ago \| parent [-]
		Neither have I, personally, but I’ve seen reports this can happen on very hard problems, where the goal just cannot be reached from a local optimum. Getting unstuck by trying something new is something a watchdog agent could prompt it.

▲

jama211 2 days ago | parent | prev [-]

To be fair that’s what I’d have done had I had to build it. Use a lot of examples etc and build on what other people have done

▲

koiueo 2 days ago | parent [-]

I assume, the purpose would be to learn how it's done. There's no place for this when you vibecode. And if not learning, what's the point of implementing something that already exists?

When I'm dying of dehydration because humanity has depleted all fresh water deposits, I'll think of you and your stupid NES emulator which is just an LLM-produced copy of many ones that had already existed.

▲

Hammershaft 2 days ago | parent | next [-]

I'm not here to hype LLMs but they don't used an outsized share of fresh water, that's essentially a myth hyped by social media.

https://andymasley.substack.com/p/the-ai-water-issue-is-fake

▲

minimaxir 2 days ago | parent | prev | next [-]

The majority of open source software development is "implementing something that already exists", but with improvements, such as for specific use cases and constraints (like the original NES emulator) or by making it more performant. That's how the ecosystem mutates and grows, and it's worked well for decades.

	▲	lawlessone 2 days ago \| parent [-]
		>The majority of open source software development is "implementing something that already exists" I don't think open office/libre office etc have access to the source code for MS office and if they did MS would be on them like a rash.

▲

delduca 2 days ago | parent | prev [-]

Blame the game, not the player.