drakenot

Give it some time. There is a whole community right now hunting edge cases and submitting and merging pull requests.

Do you watch the movie as a part of this?

For those who use Netbird or Pangolin, I'm trying to understand where it would come in handy over my Wireguard-Easy setup with my phone & laptops configured to connect to my Wireguard network externally.

Is this primarily for multi-user scenarios or complex setups?

Are LLMs going to eventually become the architecture that powers self-driving cars?

Seeing them play Portal and other video games, I'm curious if they will eventually help solve that last N% of self-driving.

For those who are interested in what spawned this project:

https://runemud.com

I had been working on it for a couple years, using it myself. I finally released it recently. It heavily uses an embedded Lua VM to power its scripting engine.

If anyone is interested, I launched a new mud client in 2026:

https://runemud.com

I had been working on it for a couple years, using it myself. I finally released it recently. A number of users are contributing feature requests, testing, etc on the discord as well.

I have zero consumer debt and pay off any credit card at the end of the month.

But I don’t mind work expenses on my personal card? I get reward benefits for a sizable chunk of expenses that I’m directly reimbursed for?

I hope they bring back the former UI that allowed you to explicitly toggle "AI / Agent" mode on/off in a terminal session, and gets rid of the Oz / Cloud Agent stuff.

I don't want this auto-detect agent request. The explicit toggle was perfect.

Thank you for that tip, I'll try that.

I used to like Warp and was a paying customer.

It had a simple UI with a clear button / key combo to toggle the “agent mode”. That, plus the fact it could “warpify” my SSH connections made this a useful utility.

Then a couple months ago they completely changed the UI. It doesn’t work as it once did. My saved prompt templates didn’t work as they did before, the agent toggle was gone (you can now start some ‘/agent’ command but it is much less intuitive) and they seem to be focusing on these cloud agents and code editing.

I want none of these things. I loved a simple terminal that let me still execute sudo, let me ssh into remote machines but still bring Claude and OpenAI models to interact with my session.

I think voice mode uses weaker models, just an FYI relative to the SOTA

It reminds me of the standard counter to the Chinese Room thought experiment: the person inside doesn’t understand Chinese, but the system _does_. The person, the rules, and the lookup tables together form the thing doing the understanding.

How can you tell that you were breached?

Claude Code has gotta be way cheaper for this, right?

I think its the end-to-end, integrated nature of it.

API driven, have "elastic resources", etc, etc. Rather than bolting together various solutions you get to have a "Cloud-like" stack in your own datacenter.

Yes. That is it

This past month Parakeet v3 dropped with a streaming ASR model that is 0.6B params, can run on a CPU and is super good.

I agree that DeepSeek and others have been doing most of the published research for future frontier models.

But I’m not sure we can say they the big US companies aren’t doing foundational research anymore. I suspect a lot of it is just kept unpublished as a result of the intense competitive pressure, which is disappointing.

This is handy for maintaining a resume!

I converted my resume to LaTeX with Claude Code recently. Being able to iterate on this code-form of my document is so much nicer than fighting the formatting with in Word/Google Docs.

I dropped my .tex file into Prism and it makes it nice to instantly render it.

Perhaps concentrated use of Claude Code increases their perceived market value.

It also perhaps tries to preserve some moat around their product/service.

I think that’s more a critique of the modern caricature of stoicism than of Stoicism itself. Classical Stoicism isn’t about suppressing emotions. It’s about understanding your emotions, examining where they come from, and choosing how you respond rather than being ruled by them.

I read the Dbos vs Temporal thing, but can you speak more about if there is a different in durability guarantees?

This from quantizing their Gemini model?

There are a lot of anecdotal reports of quality differences following some Gemini 2.5 Pro releases earlier in the year.

> Presteign did not care for the artists, musicians, and fops Olivia kept about her, but he was pleased to see a scattering of society notables this morning.

> There was a Sears-Roebuck, a Gillet, young Sidney Kodak who would one day be Kodak of Kodak, a Houbigant, Buick of Buick, and R. H. Macy XVI, head of the powerful Saks-Gimbel clan.

- The Stars My Destination

Hilarious. It’s impossible to have an original thought!

Fixed, thanks.

Gary Marcus tends to have pretty shallow analysis or points.

His takes often remind me of Jim Cramer’s stock analysis — to the point I’d be willing to bet on the side of a “reverse Gary Marcus”.

ChatGPT 5> Without adding third-party dependencies, how can I compress a Data stream with zstd in Swift on an iPhone?

(It auto-routed to its thinking model, took 25s)

> Short answer: you can’t. iOS doesn’t ship a public zstd encoder/decoder. The system Compression and AppleArchive frameworks only expose lzfse, lz4, zlib/deflate, and lzma. So with only Apple SDKs, there’s no way to produce zstd-compressed bytes.

> > Two practical paths:

> 1. If zstd isn’t mandatory, use a built-in codec (lzfse or lz4 are fastest) via Compression’s streaming API. Example (pure Swift, no deps) that compresses an arbitrary byte stream: >

> <code example>

> 2. If zstd is mandatory, you must embed zstd yourself. That can mean:

> - Vendoring the official C sources (libzstd) directly into your project and calling them via a tiny Swift wrapper/bridging header

> - Statically linking a prebuilt libzstd.a you compile for iOS

This is why this stuff is going to shift to the user’s AI enabled browser.

Half of the sites already block OpemAI. But if it is steering the user’s browser itself?

The commentary around every Chinese model is incredibly disappointing. Asking about Tiananmen Square isn't some clever insight.

Look at the political leanings that government-backed AIs in the United States will soon be required to reflect: those of the current administration.

I was hoping to hear from people reporting on their utility or coding capabilities instead.