A $500 RL fine-tune of a 9B open model beat frontier models on catalog review

himata4113•about 1 hour ago

What I really started to notice is that SOTA models are really good at putting themselves out of the job.

We can see this already with GPT how luna can do 90% of what sol is used for. The only reason why china still bothers 'distilling' models is accurate training data generation, something that oai and anthropic had to spend years collecting while trying to dodge legal challenges.

The more intelligent models get, the more people will offramp to cheaper solutions that get the job done. There's no real benefit to using a sota model when the accuracy is already 99% and I think that is the biggest danger to US labs.

com2kid•42 minutes ago

The upper end is all about coding. If I have terra on extra high write code, Sol will find a plethora of bugs and rip the code apart.

Anything else? Sure use a cheaper model.

majormajor•3 minutes ago

Sometimes that'll turn up real bugs, sometimes just overengineered designs, premature-optimization, and 1-in-a-million possibility "bugs".

And sometimes it's not about the model, it's just about refining the search space. E.g. I've had Opus write tests and GPT 5.5 write the implementation passing all the tests. Then ask about that specific implementation and find some real corner cases. Add those to tests, etc.

But the other fun trick that's been working better and better on the GPT-5.6 series is that even the lower-end models can find the things they didn't think of first when inspecting the already-written output.

I think there's still a bit of hard-to-quantify "creativity" to the bigger models - especially when trying to untangle (a) is this edge case that the model built a complicated way to avoid real/worth worrying about and also (b) even if it is real, is there not a better way to mitigate it? But it might be confirmation bias, in a way that definitely didn't use to be true about GPT-5.3 for planning and Composer 2 for implementation, say.

himata4113•23 minutes ago

You can have sol write code and terra will find a plethora of bugs and rip the code apart. In reality this is just the nature of advisory prompting and why advisor from omp.sh is such a great feature. They get caught as they're being written.

JSR_FDED•about 1 hour ago

I like the 2x2 grid that describes when to fine-tune a model, when to use a frontier model, etc.

From the article it’s not clear how the scorer grades every episode - was it a frontier model that assigned the grade? How does that continue to work as the model that is being fine-tuned becomes better at the task than the frontier model?

nzeid•about 1 hour ago

I didn't read the Ramp article but this reads like a post hoc fallacy. Companies with 2x revenue have money to spend on AI. Companies with 1.15x revenue don't.

sudo_cowsay•about 1 hour ago

What benchmark is it? Is it super niche?

stldev•9 minutes ago

They built their own benchmark and then trained directly against its scoring function.. seems to be the rage, but nothing convincing from the article alone.

A $500 RL fine-tune of a 9B open model beat frontier models on catalog review

⚡ Community Insights

Discussion (5 Comments)Read Original on HackerNews