Know what I love in a good build system? Nondeterminism! Who needs coffee when you can get your thrills from stochastic processes. Why settle for just non-repeatable builds when you can have non-repeatable build failures!
Would a smart AI accept such foolishness? I doubt it. It'll still use something deterministic under the hood - it'll just have a conversational abstraction layer for talking to the Product person writing up requirements.
We used to have to be able to communicate with other humans to build something. It seems to me that's what they're trying to take out of the loop by doing the things that humans do: talk to other humans and give them what they're asking for.
I too am not a fan of the dystopias we're ending up in.
Would it, or would it rewrite / refactor the logic every time. I'd expect the logic to remain as it for months, but then change suddenly without warning when the AI is upgraded.
I personally find this pretty concerning: GitHub Actions already has a complex and opaque security model, and adding LLMs into the mix seems like a perfect way to keep up the recent streak of major compromises driven by vulnerable workflows and actions.
I would hope that this comes with major changes to GHA’s permissions system, but I’m not holding my breath for that.
Know what I love in a good build system? Nondeterminism! Who needs coffee when you can get your thrills from stochastic processes. Why settle for just non-repeatable builds when you can have non-repeatable build failures!
Would a smart AI accept such foolishness? I doubt it. It'll still use something deterministic under the hood - it'll just have a conversational abstraction layer for talking to the Product person writing up requirements.
We used to have to be able to communicate with other humans to build something. It seems to me that's what they're trying to take out of the loop by doing the things that humans do: talk to other humans and give them what they're asking for.
I too am not a fan of the dystopias we're ending up in.
Would it, or would it rewrite / refactor the logic every time. I'd expect the logic to remain as it for months, but then change suddenly without warning when the AI is upgraded.
1 reply →
What I'm hearing is we need to invent LLM-based compilers.
Time to launch LLMLLVM.
It's just translation right? Llm's are pretty good at that..
I personally find this pretty concerning: GitHub Actions already has a complex and opaque security model, and adding LLMs into the mix seems like a perfect way to keep up the recent streak of major compromises driven by vulnerable workflows and actions.
I would hope that this comes with major changes to GHA’s permissions system, but I’m not holding my breath for that.