[gdiamos]

They will hire anyone who can produce a model better than GPT5, which is the bar for fine tuning

Otherwise, you should just use gpt5

Preparing a few thousands training examples and pressing fine tune can improve the base LLM in a few situations, but it also can make the LLM worse at other tasks in hard to understand ways that only show up in production because you didn’t build evals that are good enough to catch them. It also has all of the failure modes of deep learning. There is a reason why deep learning training never took off like LLMs did despite many attempts at building startups around it.

Andrej karpathy has a rant about it that captures some of the failure modes of fine tuning - https://karpathy.github.io/2019/04/25/recipe/

[criemen]

> They will hire anyone who can produce a model better than GPT5, which is the bar for fine tuning

Depends on what you want to achieve, of course, but I see fine-tuning at the current point in time primarily as a cost-saving measure: Transfer GPT5-levels of skill onto a smaller model, where inference is then faster/cheaper to run. This of course slows down your innovation cycle, which is why generally this is imo not advisable.

[gdiamos]

I agree this is the main case where it makes sense.

But a recent trend that cut into the cost savings is that foundation model companies have started releasing small models. So you can build a use case with qwen 235B, then shrink down to 30B, or even all the way down to 0.6B if you really want to.

The smaller models lose some accuracy, but some use cases are solvable even by these smaller and much more efficient models.

[kgwgk]

> but it also can make the LLM worse at other tasks

The problem is easily avoided by not using it for other tasks.

[gdiamos]

Users often found it hard to know exactly where the boundaries are.

This is a reason why general purpose models shine. You don’t have to carefully characterize a task and put guard rails around it.

[kgwgk]

There is also a reason why you don’t have general purpose applications. Most users understand that Excel is for data tables and Paint is for images even though some people have fun playing with the boundary and creating Excel paintings.

[gdiamos]

This is exactly the intuition that leads to excitement about fine tuning.

However, I personally think that this intuition applies to products and interfaces, not to AI.

Intelligence and learning is general. Intelligence without generalization is memorization, which seems to be less useful in practice.

[kgwgk]

What people use are products and interfaces, not "AI".

[fragmede]

Interesting you bring up Excel. ChatGPT's chat interface is going to be Excel for the AI era. Everyone knows there's a better interface to be had, but it just works.

[kgwgk]

In the pre-AI era Excel was not « the » interface. Most people didn’t use Excel at all!

[yunwal]

It’s quite easy to produce a model that’s better than GPT-5 at arbitrarily small tasks. As of right now, GPT-5 can’t classify a dog by breed based on good photos for all but the most common breeds, which is like an AI-101 project.

[gdiamos]

Try doing a head to head comparison using all LLM tricks available including prompt engineering, rag, reasoning, inference time compute, multiple agents, tools, etc

Then try the same thing using fine tuning. See which one wins. In ML class we have labeled datasets with breeds of dogs hand labeled by experts like Andrej, in real life users don’t have specific, clearly defined, and high quality labeled data like that.

I’d be interested to be proven wrong

I think it is easy for strong ML teams to fall into this trap because they themselves can get fine tuning to work well. Trying to scale it to a broader market is where it fell apart for us.

This is not to say that no one can do it. There were users who produced good models. The problem we had was where to consistently find these users who were willing to pay for infrastructure.

I’m glad we tried it, but I personally think it is beating a dead horse/llama to try it today

[mountainriver]

There are tons of problems this simply doesn’t apply to. In the limited API world this may be true but agents are far from reliable

[yunwal]

I mean, at the point where you’re writing tools to assist it, we are no longer comparing the performance of 2 LLMs. You’re taking a solution that requires a small amount of expertise, and replacing it with another solution that requires more expertise, and costs more. The question is not “can fine tuning alone do better than every other trick in the book plus a SOTA LLM plus infinite time and money?” The question is: “is fine tuning useful?”

[gdiamos]

Fair didn’t seem to matter to users who just wanted to build solutions with reasonable time and budget

[echelon]

If your customers can't fine tune, do it for them instead.

[gdiamos]

How can you hire enough people to scale that while making the economics work?

Why would they join you rather than founding their own company?

[CaptainOfCoit]

> How can you hire enough people to scale that while making the economics work?

Once you (as in you the person) have the expertise, what you need all the people for exactly? To fine-tuning you need to figure out the architecture, how to train, how to infer, pick together the dataset and then run the training (optionally setup a pipeline so the customer can run the "add more data -> train" process themselves). What in this process you need to hire so many people for?

> Why would they join you rather than founding their own company?

Same as always, in any industry, not everyone wants to lead and not everyone wants to follow.

[gdiamos]

llm.finetune(data) is a leaky abstraction

Read Andrej’s blog that I linked earlier in the thread if you want to understand why.

[echelon]

> How can you hire enough people to scale that while making the economics work?

Pick the right customers.

> Why would they join you rather than founding their own company?

The network effects of having enough resources in one place. For having other teams deal with the training data, infrastructure, deployment, etc.

[gdiamos]

I think you are saying to go after the very high end of the market.

That’s fair, one market segment of this is sometimes called sovereign compute.

Another common model that I have seen is to become the deepmind for one very large and important customer.

I think this works.

[Der_Einzige]

Yup! That's why civit.ai doesn't exist right?

They'll pay for anyone that can personalize models to be meaningfully diverse.