51–60 of 130 posts
This makes so much sense as to why I've always felt that Opus 4.8 was leagues ahead of GPT 5.5. It's so good at taking underspecified requirements and filling in the gaps with sensible approaches for your project
Tool expectations
> You are a senior SWE-Bench reviewer, make no mistakes. I don't know what a better approach would look like while still remaining feasible, however this approach of telling a LLM to make a subjective judgement seems fundamentally flawed.
This is common in system prompts and frames the responses.
For example, you'd get different responses saying:
1. you are a pirate writing sea shanties about programming;
2. you are a news reporter writing an article on physics;
3. you are a senior software engineer with complete knowledge of PostgreSQL.
For 1 you could get responses along the lines of the Wellerman sea shanty -- "There once was a program that was set to C ...".
The "make no mistakes" bit does look dubious. It would be interesting comparing the results with and without that bit and trying alternative ways of getting the same desired behavior.
> You are a senior SWE-Bench reviewer, make no mistakes. I don't know what a better approach would look like while still remaining feasible, however this approach of telling a LLM to make a subjective judgement seems fundamentally flawed.
The “make no mistakes” admonition does seem pretty silly (it’s been skewered to death on yt), but… it’s easy to imagine how it might work. E.g. it could be interpreted as simply as “check your work”. Of course, no-one seems to be (publicly) doing the comparative measurements that might allow us to reach rational conclusions here.
The advice I've heard is to emphasize the traits you want, not discourage the traits you don't. So rather than saying "make no mistakes" you can do something like you suggested with writing it as "check your work" or "ensure you answer correctly and concisely".
Earlier quoted context omitted.
Most engineers are wrong (I obviously am the true arbiter of taste), but that doesn't mean there isn't better and worse code. "Does it work" glosses over a bunch of things: is it fast, cheap, secure, reliable, easy to understand, easy to modify? And that's just for server software where you've nailed down all the functional requirements. Determining what the functional requirements is it's own question. And all these…
Well actually there is a reasonably objective standard defining software quality criteria on the source code level (ISO 5055). They also define 29 criteria for maintainability: https://www.it-cisq.org/coding-rules/
This "standard" exists for the sake of code analysis vendors to be able to have some sort of shared taxonomy, but also provide a fig leaf of standardization to their products.
(Full disclosure, I'm not a software engineer.)
Earlier quoted context omitted.
I actually really like subjective benchmarks, so long as it's a human (ideally me) grading the results. LLM as judge never made much sense.
The issue is that you can't do unsupervised learning if you require humans.
I'm investigating/experimenting with using traditional NLP (stanza, spaCy, etc.) to try and grade the responses according to different metrics (is the response in first/second/third person?, is it written as poetry, prose, or drama? etc.). I'm also thinking about using information extraction and synonym detection to handle data queries and the like.
Earlier quoted context omitted.
We could call this "generative adversarial network" (GAN) :) https://en.wikipedia.org/wiki/Generative_adversarial_network
This kind of approach would generally still need human guidance, otherwise these models might get stuck in weird niche corners of the problem space that would not be relevant to any real world project.
https://en.wikipedia.org/wiki/Reinforcement_learning_from_hu...
Earlier quoted context omitted.
> Why supply underspecified requirements in the first place? Minimizes effort, is the obvious answer.
Poor trade off, the model is then designing a massive chunk of your solution instead of you. With a good spec, bits of typo’d pseudocode, and slightly more effort than a couple of sentences they can actually produce passable software. I think the reason claude has so much mindshare is exactly because it’s more useful to non-developers who wouldn’t know how to describe what an api call executes to his grandmother. For…
> I think the reason claude has so much mindshare is exactly because it’s more useful to non-developers who wouldn’t know how to describe what an api call executes to his grandmother.
This is exactly the benefit for most people.
Most people don't want to code the app, they just want the app.
Even people like us who do like coding, we can only think of all of these things within a domain that we already know; somebody who writes shaders for games isn't likely to know or care much about the ins and outs of database development or how healthcare privacy law and KYC interact with zero-knowledge proofs.
(Of course, if the AI knows about these things and then completely fails to make use of that knowlege, that's still a fail).
Earlier quoted context omitted.
The issue is that you can't do unsupervised learning if you require humans.
LLMs grading the answers is relying on the LLM knowing the answer and not just hallucinating it. You also have issues if/when the model refuses to answer, or if it gets stuck in a loop (e.g. if running locally with a heavily quantized model). I'm investigating/experimenting with using traditional NLP (stanza, spaCy, etc.) to try and grade the responses according to different metrics (is the response in first/second/t…
And LLMs have gotten good at handling these issues. There is asymmetric difficulty in generating a solution and verifying it correct. And overtime LLMs are getting better and better which allows training on synthetic data to make it better.
Any decent benchmark would use the whole of TRIZ to generate a giant ball of a problem first and watch a AI deduce a optimal solution.