Ask HN: I had Codex and GPT 5.6 Sol running for 12 days, 870k+ LOC. Now what?

#1

Post by iagooar » Mon, Aug 03, 2026, 7:30 PM UTC

For the last 2 weeks I have been running Codex + GPT 5.6 Sol Ultra non-stop for almost 13 days, working on a huge extension to my SaaS product / business. It used 502,122,866 tokens and created over 870k new LOC.

I have done AI coding of huge features in the range of 50-60k LOC before, which were massive already, we managed to ship them and actually deliver value.

I know this sounds borderline ridiculous, but this time I don't know what to do.

What are the next steps here? It is obviously impossible to review, but it is almost as impossible to actually test. I had put A LOT of work into planning and the workflows and features were spec'ed very precisely and with lots of care and analysis. So far I have only found cosmetic issues, the entire core of the application seems to be working just fine.

I have thought about starting with a user manual / knowledge base for it, to capture the features and have plenty of documentation. But then what? Launch it to production?

Have I passed the threshold of what is humanly possible to do with AI coding, or is there any hope?

Re: Ask HN: I had Codex and GPT 5.6 Sol running for 12 days, 870k+ LOC. Now what?

#2

Post by proc0 » Mon, Aug 03, 2026, 7:41 PM UTC

You need to be able to iterate and extend the codebase, as well as grow it to 100K+.

Personally, I would focus everything on making changes easy to make at large scale. Typically with a human programmer this comes from designing and architecting and coming up with clever solutions that allow new features to be built faster even with a lot mroe lines of code. Maybe AI can do that, but I think it's uncharted territory because the biggest companies use AI with established codebases.

Re: Ask HN: I had Codex and GPT 5.6 Sol running for 12 days, 870k+ LOC. Now what?

#3

Post by verdverm » Mon, Aug 03, 2026, 7:43 PM UTC

Trash bin? ~1M LOC for what? If you cannot review or test it, then why would you trust it?

This is why it's better to stay human in the loop during the process. Sounds like you don't think it should take 1M LOC. It's likely your garden variety slop, even if it "works". Avoid the sunk cost fallacy, Ai lets us throw away more experiments because they are "cheap".

Re: Ask HN: I had Codex and GPT 5.6 Sol running for 12 days, 870k+ LOC. Now what?

#4

Post by iagooar » Tue, Aug 04, 2026, 7:16 AM UTC

verdverm wrote: post #3

Trash bin? ~1M LOC for what? If you cannot review or test it, then why would you trust it? This is why it's better to stay human in the loop during the process. Sounds like you don't think it should take 1M LOC. It's likely your garden variety slop, even if it "works". Avoid the sunk cost fallacy, Ai lets us throw away more experiments because they are "cheap".

So far every single test I've done has worked correctly, I put a lot of work and time into preparation and planning, each workflow was designed, researched and optimized before implementation. The specification was already a massive document, so it is not a one-shot by no means.

I might check it and if it turns out to just be extremely bloated, I will re-write it from scratch. But before I do that, I might as well give it a chance.

Re: Ask HN: I had Codex and GPT 5.6 Sol running for 12 days, 870k+ LOC. Now what?

#5

Post by modgate » Tue, Aug 04, 2026, 8:45 AM UTC

[flagged]