ctolsen

I’ve been using it a lot and it’s performing really well. Not GLM 5.3 levels but it beats Deepseek for my use. I’ve used it on long running coding tasks, though mostly prototyping, but it’s done a great job at very low cost.

ADHD is highly treatable with medication, and any other intervention is at best mild mitigation. So how many? Amongst people with ADHD, basically nobody.

Sun and proper sleep is certainly helpful for people with ADHD but the likelihood of them getting that is vastly increased if they’re medicated correctly.

400 million is pocket change. For all intents and purposes the US is no longer supporting Ukraine.

GLM 5.3 is very impressive and definitely better, but it also at least 4x the price.

On that note I’ve been subbing in MiMo-2.6-pro when cost is an issue, which is super cheap and also performing really well.

I find this stuff so annoying. The way you deal with these people -- abusive snowflakes -- is that you say no. We've appeased and appeased and we get nothing in return, Europe is carrying the entire financial burden for supporting Ukraine (which was a reason to try to keep the US happy) and we just get more tariffs every time Trump has a tantrum.

When people step over the line, tell them to fuck off. This is true in personal relationships and international relations alike. Sometimes there is more nuance but in situations like this it's clear that nothing else works.

European countries detain and deport immigrants who are illegally present all the time. The level of it can be discussed, but what's happening in the US is that they've detained hundreds of citizens and deported immigrants who are present legally because they said something the people in charge didn't like. I'll skip that part, thanks.

To add some practical results to that: the Data Retention Directive[1] was struck down by a bunch of national constitutional courts before being completely annulled by the EU Court of Justice.

1: https://en.wikipedia.org/wiki/Data_Retention_Directive

In the US you just get thrown in immigration detention for a few weeks instead.

Me too, but it’s kind of expensive. Would be nice if they included some API usage in their subscription.

Diesel prices are high because of the Americans, blaming them is entirely correct.

Durability and parallelism aren't that hard, and you won't be needing frontier models for much of this stuff. The parameter efficiency of models is increasing rapidly. I don't see why a (near-)future device wouldn't be capable of running a perfectly capable personal assistant.

Opus 5.5: $4/$20

Deepseek 4.1: $0.02/$0.60

Just to illustrate how cheap the Corolla is in your analogy. Also Opus output would be $50 without competition.

Depends what you do. I enjoyn hosting big parties because I spend a lot of time cooking for them, which I love doing and everyone appreciates. Then I have the opportunity to interact as much as I want.

Agreed, and if you look at the public information about various attacks the individual vectors are not particurarly sophisticated. The Huggingface incident for example had agents in a sandbox that was about as useful as a wet paper bag, and the attacks on remote infrastructure were basically enabled by bad sanitation. None of the techniques are novel.

These are not hard problems to fix, nor should anyone find it acceptable to have them be so prevalent. A determined human attacker could easily exploit defects like the agents found. Bad input sanitation, SSRF attacks, exploiting stupidly implemented token verification... all techniques that have been widely known for decades and there should be no excuse for publishing software that is riddled with exploits that enable the use of them.

> My update for you since then: even an air-gap will be inadequate, there's multiple known ways around them.

Fair, and I will grant that a capable model (or human) could in theory break out of near anything.

My point is that this incident is not evidence of that. There is zero skill visible in the setup of the sandbox. Nobody messed up a critical detail, they didn’t even start to consider what the details were.

I doubt most people "blind to the possibility" would imagine that what we’re measuring against is the equivalent of benchmarking burglar skill based on how easily they can break through an unlocked door.

> Now we know that.

Don’t know about you but it’s pretty obvious to me that you would need more than what OpenAI did. It was not remotely adequate to lock in even a human attacker.

You can find people who say all sorts on the internet, but this case is not much evidence against what you linked. "Zero-day" makes it sound novel, but the breakout patterns here are based on very common exploits and there’ll be plenty of examples in training data.

Part of the toolchain had full internet access. Agents had access to Artifactory, Artifactory could do whatever it wanted. So even locking that down to certain external sites would have stopped this particular attack.

Don’t let software inside the sandbox access the internet on request. Have a package repository with approved software the agents might want, and push to it over a channel that is ingress only. I can imagine ways of breaking out of this, and come up with a lot more to mitigate, but this would be fairly basic stuff that’d be vastly superior.

Right, that’s basically what I’m saying. There’s not zero use for an attack like this, but it’s not a likely situation.

Said another way: if Artifactory was somehow a common gatekeeper between grounded techy teenagers and their access to internet porn, this would have been found ages ago.

Why would it be getting attention? There’s an enormous amount of garbage software out there, and not an endless supply of researchers. Especially tooling like this, used internally where it’s assumed that security is the job of something else. It’s far from the first time serious but simple vulnerabilities have gone unnoticed for a long time. And the use case of having this be your way to the internet is probably rare, so nobody has tried very hard (or tried but never told anyone).

I’ve looked at the CVEs a bit more and it’s just very clearly a pattern of systemic issues with validation, be it URLs or tokens.

It just shouldn’t be that hard to believe that OpenAI just didn’t care very much and thus did a crap job. The whole model of the sandbox is terrible, so why would they bother thinking about the implementation much?

So like I said: unscrutinised and riddled with issues.

It’s very much solvable, they just don’t care.

> Are "half skilled human operators" "easily" able to find zero-day vulnerabilities in a sandbox with only one line to the internet (the commercial package registry cache proxy)?

Yes. It’s a fairly simple SSRF attack as far as I can tell. One of the first things I’d try. Especially considering that I would already be armed with the information that I have no internet access except through a thing that downloads things off the internet for me.

Calling it zero day makes it sound elusive. It’s a bug in closed software that has like 40 CVEs this year alone. Tools like that, especially in internal networks, don’t get much scrutiny and are often riddled with issues.

My biggest takeaway from this is just how godawful the sandboxing is. The stuff written up in OpenAIs report says more about lack of extremely basic sysadmin skills than anything else.

I’m not that surprised about models with endless compute being capable of this, I’m more surprised that a company with the resources they have apparently can only create a sandbox that a half skilled human operator could have broken out of easily.

I particularly enjoy the Asterix-adjacent naming scheme.

And the local drug dealer says he's a sovcit but is still somehow in jail. What's your point?

The ICC claims rights in territories where the sovereign power in that territory has signed and incorporated a treaty that grants those rights. ICC jurisdiction is domestic law.

If that's a talking point it's a stupid one. The Rome Statutes are only valid in territories that have agreed to be bound by them.

Definitely a little better.

https://gist.github.com/ctolsen/b2883e7cbf5e4357fa04366019e6...

If we go with AA's benchmarks Qwen 3.8 27B is already slightly below Luna level which is in itself impressive, but with this compression it should be just slightly more below Luna level and could run on my old GTX 1070 that I'm now tempted to fire up. That's kinda nuts even allowing for small-model problems that I'm sure I'd see quite clearly.