Once image support drops this could be a cool addition to https://struktur.sh. Will it be on OpenRouter too or will all inference have to be self-managed? I’m thinking about server-side use cases, where budgets are low, so small models shine.

edit: ah I saw mainly iOS for now. But an integration would be possible on macOS then, right?

It only tries to solve the „quality“ aspect of that equation tho, at least for the code output.

But I think for actual evals, some heuristics about a coding agent session are needed. But since the input tasks are always different, it’s hard to make any KPI actually comparable.

Did the agent needing 3 rounds of feedback on a big task perform worse than the one that needed none, but only worked on a small change?

I’ve been tinkering on a package to capture linking, testing and gating quality output in a framework unified way across coding agents.

I would love to have a chat with you about how you see this space developing and how you look at it.

https://github.com/mateffy/gesetz

I’m saying it doesn’t matter wether they did or not, because now they clearly have models which can compete.

I just don’t buy it. There’s still gonna be demand for stronger models. Sure growth will be slower, but this might even drive a push for more cost efficient training / inference and/or new architectures if money is harder to come by.

But the argument isn’t about model providers tho right (providing inference)? Using Chinese providers is already a privacy problem if user data is involved, so I don’t know if anything would change here.

What you’re suggesting is that the policy would stop big co‘s from running their own inference completely, no? Or only the foreign open source models?

> don't bother analysing it technically

I feel you have to, because where’s the line? Is running GPT-OSS myself fine (if I were a big company)? Mistral models? Or are none of them ok? What about if I am getting inference from a small startup, which is running OSS models for me? Or is only OAI/Anthropic ok?

This administration has done a lot for that minority already so I don’t think anyone would be too surprised? In this case they can even claim to protect the greater economy, a crash of which does impact the majority.

„US good, China bad“ has been a long term talking point by Trump too and this would neatly fit into that to be consumed by his base

I agree, I even think we’re already there if yesterdays OpenAI/HuggingFace story is legit.

We need to start building these agent systems in a way so that it won’t matter if a model is compromised. Malicious models is one way, but prompt injection is also still an unsolved problem.

And if you solve that, then a malicious model is also no longer a threat. Data exfiltration maybe, but IMO US labs are probably also doing that for training, even if saying otherwise (of course I have no evidence of that, but the temptation must be insane)

I think in capitalism thats called a market correction?

> Do you understand how much money is tied up in the industry?

If the free market „virtue signaling“ no longer matters, then they could’ve also put a stop-gap on investment volume to protect the economy against over-reliance?

Or how about go full plan-economy and just dictate price per token until investors get their money back?

I’m joking around but of course I understand whats tied up in this. I just don’t see how banning open source models is helping any of that in the long run.

That’s what I don’t get tho, I think in today’s world they totally could?

„We need to protect US investments as our entire economy depends on this market sector“ seems like something that would be soothing to me as an investor?

It’s not like the big money givers can’t see that china is close, it’s been the news multiple times already. But taking active policy steps to protect against that should boost market confidence, no?

Instead we get alibi arguments to accomplish the same thing in the end?

Seems a bit far fetched, given that I’ve never seen any PoC/research on this topic. Got any pointers?

To be fair the fix to this seems to be that American labs would need to adjust to the new „fair market price“ then, right? Subsidy-backed competition is still legitimate competition in capitalism (e.g. Uber).

And you could still ban specific, known malicious models/labs instead of blanket open-source bans. What about Mistral models, for example.

Distilling or not, they are clearly close enough to the frontier, that the supposed „free market“ country needs market controls. That may work for US markets. But not the rest of the world.

Idea: petrodollar policy becomes „tokendollar“, enforced by US military dominance. If you force me to pay altman at gunpoint, then maybe ill stop using kimi

1. if it’s to stop hackers doing hacking things with „uncontrollable models“ then, well… they’re already doing something illegal to begin with, why would they care about breaking another law running these models?

2. if it’s to stop foreign actors, then that ban would not apply to them anyway

3. it’s not stopping distillation either, Chinese labs are already banned from using US frontier models and look at how good that is working

I don’t get it. Am I missing something? The only thing a ban would do is protect the American market from further downward price pressure on inference, protecting VC investors in the short term. But thats also an admittance that the American labs can’t compete on merit anymore, and should by itself also limit the viability of the idea that all those VC billions will ever make a return? In any case this would be something benefitting only a very few for a short time (labs + investors).

Someone please enlighten me what the actual argument here is, cause I can’t see it.

It’s much more limited in scope but fully open source and highly customisable. In fact it’s made for people to build their own pipelines on top of, providing the scaffolding needed to do so in a reliable way.

During development I’ve found it to be hard to truly generalise agent/llm-based data extraction, especially around the unlimited number of input types without task specific instructions (many files of the same kind, single large files, mixed kinds, bad quality files, docx/pdf/png/… the list goes on). Users sadly wanna upload all of these, and developers want a „one size fits all“ solution.

I am interested in how your solution deals with this. I came up with a strategy based approach so every task can be customised if needed, but I’d be delighted to see a technical writeup of how you deal with this endless variety of input + extraction task combos! :)

I’ve only seen him talk about one of those topics, but never together.

I just can’t see how you can talk yourself out of that hypocrisy, if BS answers are properly followed up on (journalism!)

An all-in-one tool for structured data extraction with LLMs.

$ struktur extract —input doc.pdf —schema schema.json —model openai/gpt-5

- can prepare documents (PDF->text etc.) - run multiple different extraction strategies - runs a full agent loop for data extraction in-process using Pi agent and just-bash.dev. It can grep through large files for example.

The fact they’re an American company is unfortunately the dealbraker. We could store data outside of CF network but that defeats the point of the one stop shop.

Quick/Instant LLMs for human use (think UI). Slow, deep thinking LLMs for autonomous agents.

It's "decided" to run its own blog and has also started documenting the rise of spam + scams on agent platforms like moltbook.

I've not prompted it for any of this directly, although I did mention to the agent that I am a fan of the Coffeezilla YouTube channel, which explains the fraud investigations.

Comments URL: https://news.ycombinator.com/item?id=46854582

Points: 2

# Comments: 2