egonschiele

Thanks for the response and it is encouraging to hear that there's more to this project than vibe coding! Sounds like some interesting things were found in the process, and I'm all for vibe coding as a way to learn new things.

Totally fair. The thing is, though, agents often write code in ways I don't expect, and I don't think any human would write, which makes me think that code may also break in a way that no human expects or would have written a test for.

That's fair, I was thinking the same – porting must be simpler, especially if there's already a substantial test suite

It's exciting to see the speed gains. I use TypeScript every day on a large codebase, and it is too slow to run locally. I don't love this change though:

> However, frontier AI models can now do large-scale ports almost independently in a matter of days

> I wrote zero code. Not "barely any". Zero

So we are going to move from a carefully handwritten port to an entirely AI-generated port. I know this is the way the industry is headed, I use coding agents a ton. But I still review their output because they often don't make sound architectural decisions. Maybe this is a sign that my way of working is going away. I'm not sure how to justify that kind of time spent when someone can do the same thing in a matter of days with barely any effort.

I am working on my own language now, I've spent most of this year on it. The idea that someone could just replace it in a matter of days is wild. Wonder how the TS team at Microsoft feels about this.

This feels hard to maintain and keep up-to-date, but I would definitely use it! Great idea.

This takes me back! Right clicking works too, this is awesome. I miss property tables, that was a nice UX. Flash had it too.

This may be my favorite thing I have seen on hacker news. The art is spot on as well.

100% agree. Only thing is, as the last few years have shown, if you don't jump into the cesspit but a majority of your fellow humans do, it affects you anyway.

I've followed Stephen for a while now, and I don't think this is Claude.

I love Stephen's writing, and this is so well written.

> I was very wrong. The grift economy is massive. More disturbing still, it is participatory. A large and growing share of the population now appears willing to devote every waking hour to fleecing their fellow man as a career choice.

I find myself worrying about this a lot. For what it's worth though, the non-grifters, the people interested in building a community, are still out there. To find them, you need to look for groups that add no financial value – join an art club, volunteer locally. When I spend time with those groups, I'm reminded that not everyone's a grifter in real life.

Also, this explorable by Nicky Case is evergreen: https://ncase.me/trust/

There are still swing voters and it is worth fighting for them! Also helpful to just remind people they need to vote. Typically, there is less turnout in midterms.

I have been door knocking in a swing county in Wisconsin, and the first question we ask is, "what is the top issue you care about?" I've had one person say "the environment", and a couple have said, "what's happening in America right now." Almost everyone else answers "cost of living". So if you're waiting for things to change, you will be waiting a while.

Historically, something like 3.5 percent of the population need to be really engaged to make change happen, and the US isn't there right now, because we're all on our computers. The election coming up is an important one, so if you want to do something, start door knocking, become an election judge, sign up to be an observer at the polls, donate money. Indivisible is doing a lot of great, local, on-the-ground stuff, join your local chapter.

Does anyone else feel incredibly nostalgic for the time when Bill Gates and Warren Buffet were the richest people on earth? I remember feeling pretty good about the fact that they were trying to do so much good, and about the giving pledge. Things feel so different now.

> M6 supports up to 32GB of unified memory to multitask across demanding apps and run LLMs on device for secure and private agentic tasks. It also provides up to 170GB/s of unified memory bandwidth — a 10 percent increase over M5 and a 2.5x increase over M1.

Isn't 170GB/s slow for bandwidth?

Care to share a link? This sounds neat

I care about this issue, and Norway of course has built an incredible social democracy. However, Norway is also able to do this because it's just a much smaller country. The U.S. is absolutely massive, both in terms of population and in terms of land area, and it is incredibly diverse. A lot of the problems in the U.S. just go away if you don't have to worry about the same scale or diversity of people. I absolutely want the U.S. to rise up to the AI crisis, and we're having major issues, but in the grand scheme of things, the U.S. still does a good job given the scale of its challenges, and I'm not sure Norway would do better.

I'm guessing (though not sure) the actors are outside the US.

Real bummer of a story.

> He approached me because he was really into startups and wanted to become a tech entrepreneur, and make the big bucks

It's a shame that so much of tech culture has become about money. Money was always a part of it, but living in the Bay in 2010, there was more of a focus on building things. But once people started getting rich, especially off bitcoin, it brought in a whole host of people whose primary passion seemed to be money. We moved out in 2018. Still bums me out, SF was my favorite city, and I hoped to live there for a long time, but the values weren't my values anymore.

As far as I can tell, the paper never actually mentions the companies who aren't publishing papers. Open AI, Anthropic, and hugging face are all specifically mentioned as companies that do publish papers. Just FYI for anyone else who reads "AI's top startups" and immediately assumes OpenAI and Anthropic.

In a similar vein, here's my favorite prompt: "Please review the tests you've written. Will the tests actually test what they're meant to? If the code breaks, will the test fail?" It's amazing how often LLMs will write tests that don't test anything.

Love it! Do you need any technical help?

Neat throwback to Google Summer of Code, when tech felt so much simpler (at least to me). Anyone know anything about CodePath, Social Finance, or the nonprofits listed?

I have been working on this exact problem, and I suppose now is as good a time as any to talk about it.

To make any agent "good", there are two components: the model and the harness. Very few companies can train models, but anyone can build a harness. How much does the harness matter? Can I build a harness that's good enough that I can use open source models with opus level performance? That's the question I've been trying to answer by building better harnesses. None of the existing frameworks have the functionality I need to build a good harness. The features I need are language-level... and so I started building a language called Agency[0].

It's been six months and its going well. Some of the things Agency can do are wild:

- It can pause and serialize execution at any point, making HITL easy

- It has some neat safety capabilities such as handlers[1] and PFA[2]

- You can bundle up any agent as an HTTP or MCP server[3]

- I'm now working on a built-in optimizer to optimize agents (think DSPy).

Obviously, it's a huge undertaking, but having worked with the Agency for six months, I can't imagine going back to another framework. It makes things so easy. I'm working on its built-in agent now [4]. My goal it to get it to be as good as Claude Code, but using open source models. It's still early days, lots of rough edges, but if this sort of thing interests you, I'd love to have a few more people test it out.

[0] https://agency-lang.com

[1] https://agency-lang.com/guide/handlers.html

[2] https://agency-lang.com/guide/partial-application.html

[3] https://agency-lang.com/cli/serve.html

[4] https://github.com/egonSchiele/agency-lang/blob/main/package...

To be clear, they've been saying that all AI needs to take a break. I don't think this single action is going to do much.

It's important to note that thousands of people are giving their time every day for climate change work, doing thankless jobs for very little pay. The fact that the US chose a corrupt man over these people, the fact that millions of people sat out the vote, is a real slap in the face of the people who try to fight this, day after day after day. And many young people seem to have just given up. It's your future, others are fighting for it, join them.

I'm all for people writing their own coding agent harnesses... is there anything different about this one? Its not clear why I'd choose this over pi, opencode, or other existing options

As other comments have said, it would be great to add what this does that existing solutions can't. I see the project has been active since Feb, and has < 150 commits. I'd assume this is still pretty immature. So why use this? I think more explanation is needed.

Why don't all these distro maintainers add their own back doors, and mine crypto off our machines without our knowledge? Surely, there is some legal fine print they can add that would let them do that. There is very little incentive for them to maintain these systems, given how thankless and underpaid the work is.

Congrats to the Zed team! Great to see people continuing to work on important tooling like editors these days.

Warm blue vs cool blue is another interesting social question: https://www.ducktyped.org/p/a-colorful-controversy