Tested both DS v4 pro 0813 and Grok 4.6 (all from openrouter) on Codex cli. Worked on a same new feature development on my project.
Deepseek 4 pro: Worked for 12m 02s - cost $0.12 - has bug.
Grok 4.6: Worked for 3m 18s - cost $ 1.41 - no bug.
Deepseek 4 pro: Worked for 12m 02s - cost $0.12 - has bug.
Grok 4.6: Worked for 3m 18s - cost $ 1.41 - no bug.
Of course it's significant that your response had a bug and took four times longer, but if you're only going to try once, this isn't real science, it's just vibes.
Not my experience at all.
With smaller models, whenever I see a response that is going into wrong direction, I would just redo that step, and more often that not that brings improvement.
This effect is less pronounced with SOTA, but still there.
I've tried or sometimes be stupid to work on bugs/features and ask with almost identical prompts with same modal and harness set, and yes, they generate totally different results.
Sometimes the output is unusable and even with extended guidance it will still drift away from what I was expecting.
Sometimes the output is just one shot and follows almost whatever I want.
I then be used to work like this, if the model and harness set does not work for one time, I just start a new session and do it again. And currently there is one of my task working like this.
By non-deterministic I think people really mean "chaotic" in the chaos theory sense. Small perturbations in the input lead to wild and unpredictable changes in the output. Even with temperature parameters a fixed PRNG seed could mean an LLM was just chaotic and not technically non-deterministic.
But more literally while LLMs are in theory deterministic (though perhaps not inference providers implementations if there's anything like a race condition affecting how things are rounded when added together) - we use the LLMs in harnesses that aren't. There are very likely races in the terminal outputs, dates both intentionally put in the context and accidentally leaked to the context, things like that.
I guess if we really needed to, we could construct a deterministic agent harness. But in most use cases we probably want some chaotic behavior to increase our chances of stumbling on the desired results.
Thank you for the clarification
Yes.
Your input is part of a batch, and you don't know where in the batch it is. By default batches are not invariant and VLLM only supports invariance at all on some Huwaei Ascend hardware.
See https://docs.vllm.ai/projects/ascend/en/latest/user_guide/fe...
"Would you hand me that item?"
"Please hand me that item"
But when posed to the LLM, they generate different outputs. One character difference in the prompt might be a whole different output. People who aren't programmers mostly don't know that there's any difference. They asked for the same thing, it knows what they want in both cases...but different results.
There is a bit of indexicality in "Would you hand me that item ?"
that might cause it to be interpreted as an actual question rather than a request, and might elicit different responses:
- maybe _I_ would not hand this to you (I'm busy right now), but the person next to me whose hands are free would, so I'd nod to them. However, if you had said "Please hand me that item" I'd put down what I was doing to comply.
- maybe I would not hand _this_ to you (it's not the right tool IMO), but I'd suggest another option. However, if you had said "Please hand me that item" I'd put my doubts aside to comply.
- maybe I would not hand this to _you_ (you're not the one who should be handling it), but I'd do the thing myself or hand it to a more qualified member of the group. However, if you had said "Please hand me that item" I'd trust you enough to comply.
I think this distinction is relevant in that I've found people to sometimes have difficulties understanding how similar LLM prompting is to giving instructions to human colleagues.
I've had a collaborator who though very highly of his own prompting skills (while his prompts were very ambiguous and of the "make no mistakes, erase everything & correct yourself if you find one" variety) and blamed the models for not being "smart enough", and it was very noticeable that his management style for the juniors on his team was similarly unproductive.
Depending on my mental state, status with the person and many other factors each of them may trigger both many different internal thoughts, looks, body expressions and even outcomes.
The multiple back to back LLM calls are done on accumulating context, so if there is a sampling error it could throw the entire session out of whack, because LLM's build on the previous context.
It's actually meaningless to argue, one could simply sample more than 1 times and let the numbers speak for themselves.
I don't disagree that multiple tests increase confidence, but it's not correct to argue that an agent in a loop harness is equivalent to oneshotting
I don’t think single agent loops are good enough.
This is a different thing. Yes, giving multiple example is called "few-shot prompting".
But one-shot vs few-shot benchmarking is different. In this context "one-shot" means "pass at 1 effort" as opposed to "multi-shot". In the literature this is called "pass@k".
Anthropic has a good explanation here: https://www.anthropic.com/engineering/demystifying-evals-for... (search for "pass@k").
In this discussion we are discussing pass@1 (single shot) vs pass@(k>1) (multi shot).
> The multiple back to back LLM calls are done on accumulating context, so if there is a sampling error it could throw the entire session out of whack, because LLM's build on the previous context.
This isn't really true. In an agentic loop the LLM can correct itself via in-context learning.
User Posts can be downvoted but you need over 500 karma to have access to the downvote button. A Submission can not be downvoted.
Submissions can be flagged by anyone and mods/admins can downweight them. (If I’m not mistaken this is common for, say, Flock posts at the moment.)
Curiosity & repetition are two key factors.