[dktoao]

"Our goal should be to give an LLM coding agent zero degrees of freedom"

Wouldn't that just be called inventing a new language with all the overhead of the languages we already have? Are we getting to the point where getting LLMs to be productive and also write good code is going to require so much overhead and additional procedures and tools that we might as well write the code ourselves. Hmmm...

[virgilp]

Actually, no. We always needed good checks - that's why you have techniques like automated canary analysis, extensive testing, checking for coverage - these are forms of "executable oracles". If you wanted to be able to do continuous deployment - you had to be very thorough in your validation.

LLMs just take this to the extreme. You can no longer rely on human code reviews (well you can but you give away all the LLM advantages) so then if you take out "human judgement" *from validation*[1], you have to resort to very sophisticated automated validation. This is it - it's not about "inventing a new language", it's about being much more thorough (and innovative, and efficient) in the validation process.

[1] never from design, or specification - you shouldn't outsource that to AI, I don't think we're close to an AI that can do that even moderately effective without human help.

[nitwit005]

If the LLM generates code exactly matching a specification, the specification becomes a conventional programing language. The LLM is just transforming from one language to another.

[sanxiyn]

Yes, but a programming language with a proverbial sufficiently smart compiler. That is very useful.

[Quekid5]

Try writing an exhaustive spec for anything non-trivial and you might see the problem.

[scuff3d]

Been saying this for a while now. I work in aerospace, and I can tell you from first hand experience software engineers don't know what designing a spec is.

Aero, mechanical, and electrical engineers spend years designing a system. Design, requirements, reviews, redesign, more reviews, more requirements. Every single corner of the system is well understood before anything gets made. It's a detailed, time consuming, arduous process.

Software engineers think they can duplicate that process with a few skills and a weekend planning session with Claude Code. Because implementation is cheaper we don't have to go as hard as the mechanical and electrical folks, but to properly spec a system is still a massive amount of up front effort.

[sn9]

And software isn't as constrained by physics as hardware, which massively expands both the design space as well as how many ways things can go wrong.

[whattheheckheck]

Llm boys discover the halting problem!

[virgilp]

I honestly don't see how this is related? Nothing says "one shot a full system from a perfect specification", I don't think this was ever a goal (or that it will be practical to do so)

[seanw444]

Yeah, precision LLM coding is kind of an oxymoron. English language -> codebase is essentially lossily-compressed logic by definition. The less lossy the compression becomes, the more you probably approach re-inventing programming languages. Which then means that in order to use LLMs to code, you're accepting some degree of imprecision.

[amelius]

Zero degrees of freedom is a step too far.

What you want is correctness preserving transformations. Add to this some metrics such as code size, execution speed.

[rco8786]

Yea this feels like saying “if you give them good enough specs they’ll produce the code you want” which reduces to…writing the code yourself. Just with more steps.