I know that AI is moving fast, but Mimo 2.5 literally came out four months ago. I literally had to double-check after I read this because it felt like just yesterday.
Also, I'm not sure what the industry standard is right now, but my (self-built) harness automatically exits with an error code whenever it detects similar tool calls being sent or when semantic repetition in the reasoning traces reaches a certain threshold. It's pretty easy to set that kind of thing up.
The article is literally talking about swarm self-coordination, which is an emergent [1] property that preserves and compresses the state while running, otherwise it couldn't do what they claim it to do.
Why would anyone ever need ACP? I'm not trying to be an asshole. I just seriously don't understand the value proposition.
Edit: lol, I don't think ACP is even actively developed anymore. It seems to have been merged into another seemingly pointless standard with an even worse name, A2A. [0]
It's buggier for me than it has ever been before. I don't think that agentic coding always leads to such a buggy mess. I just don't think that the Anthropic front-end software team is very good at agentic coding.
It might be time for the Anthropic devs making 500k a year plus more than that in options to actually write code again? I can’t believe that humans in meat space are reviewing all that code. Maybe that’s why Claude code is feeling a bit bloated and the models are a bit lacking of late is too much of the bot is writing the bot.
> The White House announced this month that it had developed an AI framework, where the most powerful models created by US labs would be tested for safety by the federal government before they could be released publicly. The administration has not made the framework public, and reportedly has no plans to do so.
> The AI framework currently deals only with so-called closed models developed by the likes of Anthropic and OpenAI. But the framework is expected in the coming months to cover open models, too, a White House official tells Inner Loop.
> In short, as soon as open models reach the same “frontier” capabilities as Anthropic’s Mythos-class models and OpenAI’s GPT-5.6, they will be added to the framework and subject to prerelease testing, the White House official says.
For those not afraid to apply some imagination, things could continue in this direction in other fields too. I think this is a glimpse of future compute, in general.
There's got to be a better way of saying this. "A policy is good if it keeps being good after the first time you use it" is the gist that I'm getting, but that's way too simplistic to actually tell you any of the value of dynamic programming.
You ask how Republicans can possibly defend this behavior, I argue both mainstream political parties excuse blatant corruption and borderline evil on a regular basis.
If you would self-identify as a Democrat, ask yourself this: How do you feel about the recent Fauci findings, and the fact he needed a pardon to protect him against ever being prosecuted against potential crimes that are now being discussed in a Senate hearing.
Then `s/Fauci/Trump` and you'll arrive at your answer for Republicans.
I guarantee Trump will copy the template Biden established at the end of his term, and pardon all his cronies and family members on his way out the door in January 2029.
You're not going to get a real response. They're here. They literally just ignore it. It's too inconvenient of a truth. It's much easier to just point fingers at poor immigrants than to actually give a shit about the corruption of rich people.
> You're not going to get a real response. They're here. They literally just ignore it.
But that is the real response. All politicians do some things that you disagree with, so even if you hate some of their behavior, you can still end up supporting them if on balance their policy decisions are more aligned with your interests.
I see what you're saying, but ignoring something is withholding a response by definition.
Generally, I accept slight dissonance with politicians on matters of policy. I don't think it's okay to accept politicians blatantly breaking the law and sneering in the face of culpability.
That's true and what makes poltical topics frustrating and mostly pointless to discuss online.
There's very little incentive to engage with the topic in an intellectually honest way. Most would prefer to only contribute in a way that paints their team in a better light.
I guess that's why any political topics should be avoided on HN. Even with perfect moderation, one can't avoid the biases of individuals selecting when to or not to contribute to a discussion.
It's literally impossible to avoid politics on any forum. Everything is politics. Politicians create the laws that govern society. If you want to associate with other people in that society, you need to be able discuss those laws. There's no escaping it no matter how uncomfortable it makes you feel, and attempting to moderate it out of existence is an exercise in futility.
How on Earth do you imagine that a forum like this would discuss things like AI regulation without discussing politics? Beyond just regulation, there's inflation, tariffs, copyright, immigration... All of these things affect tech workers every day. A forum without politics is an absurd fantasy.
reply