Hacker News: jetbalsa

New comment by jetbalsa in "Blog ran on Ubuntu 16.04 for 10 years. I migrated it to FreeBSD"

jetbalsa — Fri, 22 May 2026 06:39:33 +0000

I've had a "Get in loser, we are going to Tau Ceti" on my car's bumper ever since the book came out

New comment by jetbalsa in "1024000^2 Blocks, 2B2T Minecraft Server World Download Project, and Discoveries"

jetbalsa — Mon, 18 May 2026 14:55:33 +0000

Ah, The 4chan of Minecraft servers, a silly place.

New comment by jetbalsa in "RISC-V Router"

jetbalsa — Fri, 15 May 2026 17:11:15 +0000

VPN and DNS Packages in OpenWRT eat a good bit of ram. and sometimes can be cheaper for faster speeds needed to higher packet processing.

New comment by jetbalsa in "Ratty – A terminal emulator with inline 3D graphics"

jetbalsa — Mon, 11 May 2026 13:08:45 +0000

I think they are looking for full 2d graphics, bitmaps, sprites and the likes.

New comment by jetbalsa in "How we run iSCSI over the internet"

jetbalsa — Fri, 01 May 2026 16:28:02 +0000

always wanted to see if this was doable using NBD or even RBD over the internet. but I do love the ESP32 device they came up with.

New comment by jetbalsa in "Show HN: GhostBox – Borrow a disposable little machine from the Global Free Tier"

jetbalsa — Fri, 01 May 2026 15:57:19 +0000

I know a guy who gets a bunch of old hardware as a recycler, We made the Shell On Demand Appliance for DEFCON[1] awhile back and would love to expand it, but power/internet would just cost too much. we have the hardware and software to do this. just not the long term recurring

[1] https://forum.defcon.org/node/246908

New comment by jetbalsa in "I cancelled Claude: Token issues, declining quality, and poor support"

jetbalsa — Fri, 24 Apr 2026 18:42:23 +0000

I've been mostly using Kimi has a hacker of sorts, putting it places I want to attach AI directly as their API for their plans are not completely user hostile. Need to do OCR for scanning Magic the Gathering Cards. Sure!, have it attached to X4: Foundations as a AI manager for some stuff. sounds fun. Can't really do that with claude

New comment by jetbalsa in "Hear your agent suffer through your code"

jetbalsa — Fri, 24 Apr 2026 16:47:22 +0000

That or having it start shit posting about your crappy code base on https://moltshit.com

New comment by jetbalsa in "ChatGPT Images 2.0"

jetbalsa — Thu, 23 Apr 2026 20:10:39 +0000

Yep, Its pretty damn good compared to classic OCR and even more lightweight ones as well that I can run locally. the cards just vary too much over time.

New comment by jetbalsa in "An update on recent Claude Code quality reports"

jetbalsa — Thu, 23 Apr 2026 20:09:28 +0000

I'm unsure of the sizes needed for prompt cache, but I suspect its several gigs in size (A percentage of the model weight size), how would the user upload this every time they started a resumed a old idle session, also are they going to save /every/ session you do this with?

New comment by jetbalsa in "An update on recent Claude Code quality reports"

jetbalsa — Thu, 23 Apr 2026 19:56:45 +0000

The cache is stored on Antropics servers, since its a save state of the LLM's weights at the time of processing. its several gigs in size. Every SINGLE TIME you send a message and its a cache miss you have to reprocess the entire message again eating up tons of tokens in the process

New comment by jetbalsa in "An update on recent Claude Code quality reports"

jetbalsa — Thu, 23 Apr 2026 19:54:36 +0000

So to defend a litte, its a Cache, it has to go somewhere, its a save state of the model's inner workings at the time of the last message. so if it expires, it has to process the whole thing again. most people don't understand that every message the ENTIRE history of the conversion is processed again and again without that cache. That conversion might of hit several gigs worth of model weights and are you expecting them to keep that around for /all/ of your conversions you have had with it in separate sessions?

New comment by jetbalsa in "An update on recent Claude Code quality reports"

jetbalsa — Thu, 23 Apr 2026 19:52:02 +0000

The cache is on Antropics server, its like a freeze frame of the LLM inner workings at the time. the LLM can pick up directly from this save state. as you can guess this save state has bits of the underlying model, their secret sauce. so it cannot be saved locally...

New comment by jetbalsa in "ChatGPT Images 2.0"

jetbalsa — Wed, 22 Apr 2026 01:21:45 +0000

Oh god yes, I've been trying to make a LLM Assisted Magic the Gathering card scanner... its been a hell of a time trying to get it to just OCR card names well....

New comment by jetbalsa in "Claude Code's source code has been leaked via a map file in their NPM registry"

jetbalsa — Tue, 31 Mar 2026 18:17:25 +0000

i will note that they really should of used something like ncurses and kept the animations down, TTYs are NOT meant to do the level of crazy modern TUIs are trying to pull off, there is just too many terminal emulators out there that just don't like the weird control codes being sent around.

Show HN: I turned my TV into a '90s Weather Channel with an Android kiosk app

jetbalsa — Sat, 28 Mar 2026 09:50:33 +0000

! wanted to bring back some of that old weather channel vibe and the WeatherStar 4000+ emulator was a great way to get it, but it wasn't really easy to just pull it up on my Shield TV in the morning. So I put together this Android app and figured others might be into it too.

The app is a WebView wrapper around the WeatherStar 4000+ web emulator by netbymatt. It bundles everything locally and injects some JavaScript on top for kiosk features like location detection, settings, and music.

Location chains through GPS first, then falls back to IP geolocation if that's not available. Settings are accessed with a long press and get saved between sessions.

The music comes from the Weatherscan Complete Collection on Archive.org.

Comments URL: https://news.ycombinator.com/item?id=47553114

Points: 4

# Comments: 0

New comment by jetbalsa in "I built a programming language using Claude Code"

jetbalsa — Tue, 10 Mar 2026 17:30:23 +0000

That is why Typescript is the main one used by most people vibe coding, The LLMs do like to work around the type engine in it sometimes, but strong typing and linting can help a ton in it.

New comment by jetbalsa in "I built a programming language using Claude Code"

jetbalsa — Tue, 10 Mar 2026 17:27:32 +0000

I am kind of doing that now. I put Kimi K2.5 into a Ralph Loop to make a Screeps.com AI. So far its been awful at it. If you want to track its progress, I have its dashboard at https://balsa.info

New comment by jetbalsa in "Claude becomes number one app on the U.S. App Store"

jetbalsa — Sun, 01 Mar 2026 00:31:35 +0000

What where you using it for? claude is really good at agentic stuff, Pure coding, I can see codex being better, but for the entire workflow, I'm not sure

New comment by jetbalsa in "Show HN: Terminal Phone – E2EE Walkie Talkie from the Command Line"

jetbalsa — Thu, 26 Feb 2026 15:44:50 +0000

there are ways to help with lag a bit, you can choose the number of hops a HS uses when meeting up. but of course that comes with downsides