Henry Farrell nailed it in early 2018, calling this Philip K Dick's future, with the invasion of fake humans. https://www.bostonreview.net/articles/henry-farrell-philip-k...

These people believe in nothing. They offer nothing. They detest that other people have these "virtues", more than smirking deceitful nonsense. Vengeful destruction of the world, letting their fakeness take over and ruin meaning: that's the revenge. Lovely recent short 2 min video, Ruminations on that DHS penguin tweet is succinct & to the point, on the weird suicidal Werner Hertzog penguin meme that has been making rounds, and how these memes so embrace anti-meaning. https://youtu.be/c7WqVx9x89s

Here here. Code has uniquely an incredible volume of data. And incredibly good ways to assess & test it's weights, to immediately find out of its headed the right way on the gradient.

> And incredibly good ways to assess & test it's weights

What weights are you referring to? How does [Claude?] code do that

I spent some time trying to understand what OpenCode.nvim gave me, could do for me. It felt mostly like ways to take nvim things and inject them into OpenCode. Which was fine I guess. I'm probably underselling it, but I was hoping for more, and it never really clicked. https://github.com/nickjvandyke/opencode.nvim

I find myself spending much more time in OpenCode than in nvim these days. With mcp-neovim-server, it's super easy to keep vim open & ask OpenCode to show me, to open files, go to lines. This didn't require any nvim tweaking at all, it's just giving the LLM access to my nvim. It is absolutely wild how good glm-4.7 has been at opening friendly splits, at debugging really gnarly wild nvim configuration problems that have plagued me for years. It knows way way way more nvim than I do, and that somehow surprised me. https://github.com/bigcodegen/mcp-neovim-server

Definitely interest in the ACP angle. I feel like we're in a weird spot where ACP is this protocol where the thing you do use talks to the headless thing you don't ever see. I'd love to know or see more than that. These connections feel 1:1, but I want to see human interaction in every agentic system, not for there to be this me -> ide -> ACP agent flow with the ide intermediating all, being the sole UI. It should be able to do that yes!! But I also want an expectation that there can be multiple forces "driving" an ACP service.

I've watched the video now. It's still not crystal clear to me architecturally is going on, but it does seem like a fairly robust emacs shell experience that wraps the agent flow. I really enjoy the idea of having this overlayed compose buffer, that is your editor style input. I'd love to know how that is wired to the agents; is that input sent over ACP? Is that just sending to the shell? This compose buffer feels like it may be a broader emacs pattern. One I'd love to see in nvim! Years ago I had a plugin that would take the selection or current line and send it to a buffer. That was my very crude compose buffer.

It's frustrating how much we need coverage like this. Because the us keeps trying to end the war by giving Russia a huge amount of what it wants.

Russia Russia Russia was correct correct correct. Watching the US attempt a pratfall of democracy to rival the fall of communism is the best returns on investment Putin could ever have hoped for. The USA bring hostile to Ukraine & constantly trying to adopt Russian terms & Russian framing is bonus. https://www.yahoo.com/news/articles/trump-peace-plan-written...

The world direly needs good accounting like this article, to keep the delusional disreality of these Russian-agent madmen at the White House from demolishing Ukraine.

This effort is the abandonment. This is ChromeOS bring shut down, this is the one taking over the many.

Zx is great. Really easy scripting!

This article used Dax instead which also looks fine! Https://github.com/dsherret/dax

There is also Bun shell built-in library, that I liked. https://bun.com/docs/runtime/shell

Agreed I was looking for this comment. Bun shell is amazing although I had trouble having it be written by LLM's sometimes (not always) but overall Bun shell is really cool.

One of my projects actually use bun shell to call some rust binary in a website itself and I really liked this use case.

N-gate was so good. http://n-gate.com/hackernews/

It would be amazing to refine / fine tune a model on n-gate somehow.

It is good, but it's a very specific voice and take. AI has more range. (And, more stamina!)

Still, did this guy die/get executed because he was speaking the truth? A modern day Giordano Bruno?

Still, the number of people who referenced N-gate in these posts seems flattering.

Storngly agreed. Or ask it to explain the implications of using different ownership models. I love to ask it for options, to what if scenarios out. It's been incredibly helpful for learning rust.

I just threw in SIMD processing on a whim to an existing library.

It wasn't a regular structure that needed one operation or two again and again, it was this irregular object that needed each field each operation to be carefully picked. Assessing what instructions were going to help me do which fields how would have been hard hard hard. Hours of analysis, would have gotten stuff wrong. Would have been so frustrating.

I could just ask for, and I got it.

This is a very specific kind of example. But smart people who know what they want but don't have endless time to go chase every idea themselves will, I think, find great joy getting the AI to go out and land some amazing improvements.

And there's so many projects like zerobrew that just would never be attempted. We can make whole systems, see their performance, and if it's not good, change the stack and generate a new version of the app, a new attempt, with far less effort. We will try many more things.

Kinda all very very obvious to the actual excited doer folks.

Good for you champ.

this feels like such a line in the sand, where github is Extend Embrace Extinguishing the value of git.

pr's themselves already, in my view, are an example of github not playing particularly well amid git. it leave so much want as this thing that is about git, but isn't in git, isn't tracked there, that is purely held by github & not git. it's been convenient but it's bad for growth innovation possibility and coordination.

the agents tab feels so so so crucial, is such the tale of the project. this is enormous interesting helpful stuff. but it's being managed purely by github, is not part of the repo, and that's a huge lost opportunity for all. this feels too far to me!

we see some early work such as the Git AI Standard v3 maybe starting to create some common protocols & systems for using git, for enriching git. on git, in a compatible way. agents tab is technically very cool & so useful, but this is the wrong direction, further entrenching & self-dealing for github, and i am not down for this microsoftization of such a core vital open source system. https://github.com/git-ai-project/git-ai/blob/main/specs/git...