>The consumer version of Guided Learning is already available within Gemini, and can enable cheating. In a reporter’s test, it produced a detailed essay in response to an Advanced Placement history prompt.

I don't envy trying to stop cheating in an AI world, but when a student gets to the AP History level, if they want to cheat they'll know how to do it, with or without using a Google product with their school login.

Best you can do is guide them down the "correct" path, which itself is going to be harder and harder with AI generated content out in the wild.

It does (or at least arguably should be) if you also want to have a social safety net.

But they don't want a social safety net

If you are a legally operating company in the US just saying it's banned is enough, the threat of enforcement is enough pressure.

You and I obviously can just use a VPN, but 99% of usage is likely as part of a company.

Presumably, legally operating companies aren't the dominant threat though. So banning open weight models doesn't solve anything.

Not if you realize the real threat to be solved is threat to shareholder value.

ding ding ding

> If you are a legally operating company in the US just saying it's banned is enough, the threat of enforcement is enough pressure.

Is there precedent for the US actually "banning" software? I know for example the Kaspersky ban and tiktok ban, but both of those were either banning the sales or banning the service. IIRC neither made the actual software illegal.

What is an example of a specific software being illegal to possess? What is an example of a specific software being illegal to use if it is not used to break other laws (copyright, etc.) or talks to banned service providers?

Closest thing I can think of is restricting the export of cryptography in the 90's, but that was not even close to what you are suggesting.

Correct it’s 7% chance on kalshi, and those 7% of people are just wrong. I know everyone likes to larp that the US is some kind of dictatorship, but lol, lmao as they say. Also on the “how” side so far we have “they will just announce that “they” are banned, hilarious.

The problem is, as anyone trying to address security concerns in claude can attest to, the guardrails trigger even when trying to address real bugs. Good cyber defense requires an understanding of the offense.

How you avoid the "fix my code" attack, the code being someone else's code, I do not know. But nerfing the model doesn't seem like the best path forward either.

This is not about guardrails, it's just not post-training the model on tasks that specifically relate to cyber-offense. It's a very lightweight intervention, and it makes the model less of a target for bad actors.

claude code "auto-mode" uses a smaller sonnet-like model for classifying, which means it's basically dumb, and the harness biases it into denials

If the one other competitor didn't allow it, then would we be allowed to complain in your mind?

This argument is terrible, we're lucky the one other competitor, for now, allows installing what you want or people like you would argue everything is fine.

If nobody makes the product you want, that is called a business opportunity.

I'll happily give it a try, if you can give me a small loan, say 100 million dollars.

I said it was a business opportunity. Not necessarily a business opportunity for you personally. But if a gap in the market did exist, it would be an opportunity for Microsoft, or Meta, or Dell, or... I hear Firefox wanted to build a phone...

Okay, and now let's finish the thought: why don't Microsoft, Meta, Dell and co. invest in this space?

What is up with this attitude in this thread? AI has taken off programming basically this year, the end of last at best. The first truly capable LLM, ChatGPT, isn't even 4 years old yet.

Just a crazy amount of doom and gloom all around this thread.

It's kind of weird to say it's "taken off" recently. Yes what we have today is far better than half a year ago and solving new real use cases, but that was far better with more uses than we had half a year before that, etc, for years now. On their best usecases LLMs were already enormously useful years ago, and it's still very spiky.

As a user of software I see no improvements. What I see is that I need to download software more often, it brings more features I don't need and it has been as buggy as ever (if not more). And I can say that about Operating System I use, social networks, games, etc.

Exactly. Where are the results? If AI is really producing value at 20X the rate software engineers produced it earlier, we should be seeing 20X the number of software projects released now. Or they should be getting made 20X faster. Or they should be 20X better. Or the projects should have 20X fewer bugs. But none of this seems to be happening. The only thing that seems to be happening is we're making the same crappy shit, but with 20X fewer people.

In other words, it's taken a highly enjoyable and lucrative vocation from vast swathes of workers - a lot of which make up this sites audience! - and instead concentrated more productive power in the hands of a few megacorps.

You gave your own example for the doom and gloom.

It has made it far more accessible to a lot more people. Being “highly enjoyable” and “lucrative” is why people try to gatekeep it.

The fact that the means of this capability is in a few hands does suck. But I’m increasingly optimistic that it’s going to be commoditized through open weight models and performance improvements. There is enormous demand for innovations on these fronts.

It hasn't made it more accessible to anyone. It's destroyed it. Who still writes code?

You’ve got to understand that coding isn’t the point for a lot of people. It’s just the thing in the way of making stuff and solving problems.

I do understand that.

That's my point, in fact. We're losing the profession just so the annoying guy that would pester you with his stupid app idea can now shit it out himself, lighting the planet on fire in the process.

I'm a rare individual that has consistently made choices to earn less money in order to have more enjoyment. I would clock fewer hours than they wanted me to during college for my internships, I left a FAANG to go back to startups, I quit a startup to work on volunteer work and try to bootstrap a business.

At multiple jobs I've noted that I felt the pay should have been less. Not so that the employers could take a bigger slice of the pie (in fact, my preference is to be in an anarchist co-op, but I understand that's a wild take and might be terrible in practice). My hope was that we could filter for people that genuinely want to do the work and take on fewer people that were there for the money. At the same time more money is more better. And I like having money. It's complicated.

As I've said many times before, I didn't come to Silicon Valley to get paid. I came here to make computers do cool things alongside other people. I need income to do that, but I try to make sure I'm in a situation where the income isn't something I need to think about all of the time. If you're doing mercenary work that's not possible.

I think being able to accomplish more from places that are a fraction the cost of Silicon Valley will also help achieve the goal of doing things for reasons other than the money.

I think the amount of protectionism we’ll see could be absolutely enormous. Not only do incumbent corporations not want to lose share, incumbent countries won’t want to share either.

Definitely. For now I'm making friends with lots of very capable people - it's not as easy to do that outside of a hub like SF.

> I think the amount of protectionism we’ll see could be absolutely enormous because corporations aren’t capable of altruistic attitudes.

On some fronts they will be powerless to stop the changes. I look forward to drinking the tears of IP owners when breaking through their DRM and recovering their source code is just a matter of sharing a model ID, prompt, and hyper parameters. Reverse engineer NVidia's firmware and drivers. Decompile and port Nintendo's latest console's operating system. We may soon find ourselves in a world where tasks like that are achievable in a few days on consumer hardware.

It took a long time for internet to transform society. Its still not fully baked in. These models that we have right now are transformational.

I have no idea if anthropic can actually make money at their subsidized subscription rates (you can easily hit your monthly cost in one 5 hour session if you price out the tokens through the api), but if subscriptions didn't exist, I do think everyone would be on deepseek 4.1 and just not look back.

Imo deepseek 4.1 (and a lot of the cheaper models, Luna is similar) show the issues in benchmarks. At this point.

In actual day to day development the differences are a lot harder to spot. Maybe deepseek is worse, but I asked it to run until it was able to launch itself and verify it worked as expected, and it did. Maybe it wasted some turns, idk, but when it said it was done, it was done.

I have no doubt there's things it's worse at, but what percentage of development is truly novel?

Personally I find this shocking. I don't think our application is that complicated, (typescript full stack graphql reactnative etc) but deepseek 4.1 flash is a bumbling fool, junior-level at best, who takes a very long time to make a very big mess. Opus 5.5 one shots truly impressive code in 5 minutes, while deepseek 4.1 flash takes 20 minutes to do horribly. I simply don't understand how folks claim they get good engineering out of it. Maybe we still care enough about the fundamentals to notice the mess ...

Are you using OpenRouter? I’m honestly surprised open model labs haven’t been calling them out, but heaps of providers either silently serve heavily quant versions, or don’t have inference set up correctly and don’t run the model properly.

Was a night and day difference going directly to deepseek api

In this case, I was using Hugging Face inference set to one of a few American providers. For my professional work, I do not use Chinese inference.

I'm in the same boat, I guess I had this naive idea that unsolved math problems would mean something if they were solved. But it seems like a lot of them at least were more thought experiments than anything else.

Kids on HN have built their whole personalities around math, and now, they are discovering that "problem solving ability" has nothing to do with solving problems.

Interesting claim. That's true for old models that simply have no way to explain, LLMs however can. [1]

[1] https://dev.to/natcher/researchers-develop-method-to-train-l...