MaxLeiter

I (and Claude, codex, etc) have compiled/ran wayland, X11, GNOME, KDE, and Ladybird natively on a jailbroken iPad. Hoping to release more details soon but I have a slop wiki here:

https://xios.maxleiter.com

The C++ documentary released last month was great and featured him a lot: https://www.youtube.com/watch?v=lI7tMxzSJ7w

It's a major rewrite of the slack plugin, with far more functionality and more capabilities. More surfaces will be available in the future

Every channel has its own Claude, and Claude's access is configurable per-channel and per-workspace. Private channels don't leak information to other channels

From the maintainer: https://drewdevault.com/blog/Forking-vim/

HN discussion: https://news.ycombinator.com/item?id=47519308

All credit to the original author. I just had to think of analogues.

This is one reason I think openai releasing a phone makes sense

If they can build an integrated AI assistant (what Siri should be) that can spin up and call agents it will be big (or it will flop but my money is on big if it’s the easiest way to use agents in your daily life)

No, I have a bunch of PRs up and some already merged

We’re aiming for a minimal maintenance release soon, then a larger feature release after.

I’ve been working on modernizing https://thelounge.chat, a self-hostable web based IRC client

Modernizing in two ways: migrating to new JS tooling (webpack -> vite, Node’s built in sqlite, etc) and adopting ircv3 features like emoji reactions, threaded replies, and typing indicators. Trying to bring IRC into the 21st century.

Its easy to contribute to and we have an active irc channel (perks of building an always-on client…) - feel free to join us! #thelounge on irc.libera.chat

Check out the bundle / CPU savings by leaving webpack: https://github.com/thelounge/thelounge/pull/5064

Eh, we’re approaching that world (I am "an AI maximalist", I guess)

But someone with the knowledge to guide an AI will have more success than someone without, at least today. I don’t think that will necessarily be true in a year or two.

Short term: they don’t need devs to build it, it’s already built

Long term: they now have experienced dev(s?) to build their next products and features

I think they key thing here is they "isolated the relevant code"

If the exploits exist in e.g. one file, great. But many complex zerodays and exploits are chains of various bugs/behaviors in complex systems.

Important research but I don’t think it dispels anything about Mythos

FTA:

In 2022, we built Tart, which became the most popular virtualization solution for Apple Silicon, along with several other tools along the way.

from Tart's github:

[Tart is for] macOS and Linux VMs on Apple Silicon to use in CI and other automations

My (naive?) hypothesis is this kind of expertise is why OpenAI chose to acquihire.

Great write-up. I love hardware running software it shouldn’t support

Each page navigation runs a WebGL shader that reads both the old and new page as live textures via the new texElementImage2D() API, then composites them through the selected compiz inspired effect.

You can test it here (must be using chrome canary): https://compiz-web.vercel.app/, or see the demo video on github

LLM generated READMEs hurt my eyes

But maybe there is some cool stuff here. A lot of prolific AI-assisted engineers I know have their own advanced plan modes, and the CEO plan mode in the repo is interesting (although very token heavy)

https://github.com/garrytan/gstack/blob/main/plan-ceo-review...

But then the LLM needs to write its own tools/code for interacting with said service. Which is fine, but slower and it can make mistakes vs officially provided tools

MCPs are great for some use cases

In v0, people can add e.g. Supabase, Neon, or Stripe to their projects with one click. We then auto-connect and auth to the integration’s remote MCP server on behalf of the user.

v0 can then use the tools the integration provider wants users to have, on behalf of the user, with no additional configuration. Query tables, run migrations, whatever. Zero maintenance burden on the team to manage the tools. And if users want to bring their own remote MCPs, that works via the same code path.

We also use various optimizations like a search_tools tool to avoid overfilling context

xcancel link: https://xcancel.com/jxmnop/status/2019251724020772933

My friend and I were able to give claude a (no longer updated) unity arcade game. It decompiled it and created a one-to-one typescript port so it can run in the browser and now we're adding multiplayer support (for personal use, don't worry HN - we won't be distributing it). I'm very excited for what AI can do for legacy software.

v0 actually can directly copy files out of its examples and then apply edits. This saves it from having to write out the long examples verbatim. The rest of your comment is accurate

The comments are pretty good

From @dangs_successor in the first post:

  We've merged several duplicate threads on this topic. Please keep the discussion substantive and avoid personal attacks.

  Also, yes, my username is silly. The previous dang retired in 2031 and I lost a bet.

I think the fact that OpenNext can exist speaks to the opposite

A Next.js project can be deployed to a Docker image very easily [1]. If you want to use a provider that has their own infrastructure setup, then yes you need to do some work (that OpenNext does for you). But that's true of practically any framework deploying to a host that does more than just serve the docker container.

[1] https://nextjs.org/docs/app/getting-started/deploying

If you can point out how we actually lock you in, that would be more constructive than blanket accusations. I recommend reading the linked post

I am obviously bias as a Vercel employee, but I think we actually do a lot to avoid locking our users in. You can read more about our approach here: https://vercel.com/blog/vercel-the-anti-vendor-lock-in-cloud

If that doesn't alleviate your concerns or you disagree, I'd love to hear your thoughts about how we can improve

We changed the link in the post to go direct to the app store, which has more info. Thanks for the feedback

A lot of react native apps do not feel native. Even more are just low quality. Many v0 users were asking us how exactly we did X or Y to make it feel so good, which is what this post is for.

We've added support for opus 4.5 to v0 and users are making some pretty impressive 1-shots:

https://x.com/mikegonz/status/1993045002306699704

https://x.com/MirAI_Newz/status/1993047036766396852

https://x.com/rauchg/status/1993054732781490412

It seems especially good at threejs / 3D websites. Gemini was similarly good at them (https://x.com/aymericrabot/status/1991613284106269192); maybe the model labs are focusing on this style of generation more now.

FYI your code examples were being rendered as a bunch of [Object object], then it fixed itself after a refresh

https://neutron-engine.vercel.app/#code-examples

They still have bias. Not sure its necessarily worse but there is bias inherent to LLMs

https://misinforeview.hks.harvard.edu/article/do-language-mo...