This makes sense, although it's not well described here.
Formal methods, as in proof of correctness, have been around for decades (I was doing that stuff in the 1980s) but pushing the proofs through was too laborious. The seL4 verification effort reportedly used over a decade of people time.
The idea is that if you have a formal specification of what you want to happen, you can get a LLM to do the struggling with the proof system to get it right. It's a good task for an LLM, because there's feedback from the prover.
I'd like to see more non-trivial examples of this. People keep republishing verifications of greatest common divisor or stack algorithms, which was done decades ago.
Problem is, usually describing the problem you want to solve *correctly* using formal tool is a task as hard (and often, equivalent to) the implementation. That said, having a formal description is useful
For some problems, yes. Formal specification is particularly useful in two cases. 1) The problem is simple but an efficient implementation is hard or bug-prone. Examples are garbage collection, file systems, sorts, databases, and tree updating.
2) The inverse of the problem is simpler than the forward operation. Examples include matrix inversion and parsing.
I find some of the most interesting, and catastrophic failures in my agent fine-tuning come from the clamping down of non-determinism. It is totally the correct approach, but must be handled delicately. The non-deterministic core remains, but now under bimodal pressure.
Thanks, fixed. The runtime[1] and the scripts[2] are the practical ones. I am separating the old repo[3] into submodules since submodule recursion became smooth in Beagle.
This is a very interesting introduction to a blog post, but... I'm somehow missing the actual blog post. How does this stuff work in practice? What are some concrete examples? How does one get from JavaScript tokenizing things in a commit hook to validating that the LLM didn't disable tests it didn't agree with, or any other helpful property?
I'm seeing tons of blog posts which seemingly amount to having AI write code. It would have never occurred to me to repeatedly invoke an LLM to do what a simple script could, but I guess I shouldn't be too surprised. 20 line bash scripts replacing entire enterprise software stacks was a meme even in the 90s.
I’ve got a test that checks to see if “Logger” has been imported anywhere in my Elixir project, and if it finds one it prints out an explanation of why this project shouldn’t use Logger and what it should do instead. (Which is— emit OpenTelemetry events.)
Basically what I’ve been saying since OldJob forced LLMs down our throats and pegging performance to usage metrics: why the fuck are we handing deterministic processes to probabilistic systems when it should be the other way around (using probabilistic systems to design deterministic ones)?
LLMS should be abstracted out of a process as soon as practicable, replaced with deterministic processes or procedures. Otherwise you’ve built the world’s most fragile process at the mercy of token cost, vendor hostility, geopolitics, and model deprecation.
Thats the best description I have heard of the problem so far. I ran into this recently where I automated a ton of stuff and got essentially threatened by leadership for not using AI. My system produces the same output 100% of the time, is free, and scales plus is reliable. Doing what they wanted with an LLM was fragile, didn't always produce the same output and was subject to costs. I don't think they could wrap their brains around it.
> got essentially threatened by leadership for not using AI.
This sounds made up or your workplace is rather odd to say the least. Maybe english isn't your first language and "threatened" is not the correct word?
Humans aren't deterministic. Determinism is a red herring. There are lots of other problems with agentic programming, but this is not at the top of the list.
Nondeterminism doesn’t scale. Humans created compounded value and scale by making systems to bound their own nondeterminism. Compilers, type systems, conveyor belts, factory robotics — deterministic structures that amplify human creativity with constraints.
I agree with the humans aren't deterministic, but I feel like that wasn't the scope of the original commentator. Humans are not deterministic, yes. Neither are LLMs. Both should be phased out of processes that need to be deterministic. What do you think?
I don't think processes have to be deterministic. Results should be, in the following sense: Both humans and LLMs should write software that is well-written, well-tested, well-documented, and that meets the spec. But this still leaves a lot of room for creativity (or rolling dice).
This makes sense, although it's not well described here.
Formal methods, as in proof of correctness, have been around for decades (I was doing that stuff in the 1980s) but pushing the proofs through was too laborious. The seL4 verification effort reportedly used over a decade of people time.
The idea is that if you have a formal specification of what you want to happen, you can get a LLM to do the struggling with the proof system to get it right. It's a good task for an LLM, because there's feedback from the prover.
I'd like to see more non-trivial examples of this. People keep republishing verifications of greatest common divisor or stack algorithms, which was done decades ago.
might be relevant: https://martin.kleppmann.com/2025/12/08/ai-formal-verificati...
Yes. I should have cited that. He has this right.
Problem is, usually describing the problem you want to solve *correctly* using formal tool is a task as hard (and often, equivalent to) the implementation. That said, having a formal description is useful
For some problems, yes. Formal specification is particularly useful in two cases. 1) The problem is simple but an efficient implementation is hard or bug-prone. Examples are garbage collection, file systems, sorts, databases, and tree updating. 2) The inverse of the problem is simpler than the forward operation. Examples include matrix inversion and parsing.
Makes sense, I have had the biggest wins with AI by attacking nondeterminism whenever possible.
BTW, you should probably fix the Beagle link on your homepage: https://replicated.live/beagle/
I find some of the most interesting, and catastrophic failures in my agent fine-tuning come from the clamping down of non-determinism. It is totally the correct approach, but must be handled delicately. The non-deterministic core remains, but now under bimodal pressure.
Thanks, fixed. The runtime[1] and the scripts[2] are the practical ones. I am separating the old repo[3] into submodules since submodule recursion became smooth in Beagle.
[1]: https://github.com/gritzko/jab
[2]: https://github.com/gritzko/beagle-ext
[3]: https://github.com/gritzko/beagle
This is a very interesting introduction to a blog post, but... I'm somehow missing the actual blog post. How does this stuff work in practice? What are some concrete examples? How does one get from JavaScript tokenizing things in a commit hook to validating that the LLM didn't disable tests it didn't agree with, or any other helpful property?
I am the author. I am trying to limit one post to one page. Most people here are reading reasoning all day, I am afraid. Might get tired.
I also aspire to make one post a day. To be continued.
> Most people here are reading reasoning all day, I am afraid. Might get tired.
This is well-observed.
Thanks! I actually find human-written text very refreshing compared to what I have to read all day. I'll stay tuned.
I'm seeing tons of blog posts which seemingly amount to having AI write code. It would have never occurred to me to repeatedly invoke an LLM to do what a simple script could, but I guess I shouldn't be too surprised. 20 line bash scripts replacing entire enterprise software stacks was a meme even in the 90s.
I’ve got a test that checks to see if “Logger” has been imported anywhere in my Elixir project, and if it finds one it prints out an explanation of why this project shouldn’t use Logger and what it should do instead. (Which is— emit OpenTelemetry events.)
Basically what I’ve been saying since OldJob forced LLMs down our throats and pegging performance to usage metrics: why the fuck are we handing deterministic processes to probabilistic systems when it should be the other way around (using probabilistic systems to design deterministic ones)?
LLMS should be abstracted out of a process as soon as practicable, replaced with deterministic processes or procedures. Otherwise you’ve built the world’s most fragile process at the mercy of token cost, vendor hostility, geopolitics, and model deprecation.
Thats the best description I have heard of the problem so far. I ran into this recently where I automated a ton of stuff and got essentially threatened by leadership for not using AI. My system produces the same output 100% of the time, is free, and scales plus is reliable. Doing what they wanted with an LLM was fragile, didn't always produce the same output and was subject to costs. I don't think they could wrap their brains around it.
> got essentially threatened by leadership for not using AI.
This sounds made up or your workplace is rather odd to say the least. Maybe english isn't your first language and "threatened" is not the correct word?
I love the way you put this. Are there any sites or forums or places where people discuss/hash this out?
I've genuinely never considered it from this angle before.
Humans aren't deterministic. Determinism is a red herring. There are lots of other problems with agentic programming, but this is not at the top of the list.
Nondeterminism doesn’t scale. Humans created compounded value and scale by making systems to bound their own nondeterminism. Compilers, type systems, conveyor belts, factory robotics — deterministic structures that amplify human creativity with constraints.
I agree with the humans aren't deterministic, but I feel like that wasn't the scope of the original commentator. Humans are not deterministic, yes. Neither are LLMs. Both should be phased out of processes that need to be deterministic. What do you think?
I don't think processes have to be deterministic. Results should be, in the following sense: Both humans and LLMs should write software that is well-written, well-tested, well-documented, and that meets the spec. But this still leaves a lot of room for creativity (or rolling dice).