Hacker News Reader

zackifyon AI coding has made CI a bottleneck, so we reworked ours to keep up

I have lxd containers already running that have everything the system needs.

When starting CI it's doing a DB SQL dump replacement which takes 1-2s to prep, self hosted github actions.

Its been very cheap to run OVH cloud with the newest and fastest AMD EPYC CPUs that have high single core speeds. Did this as it was cheaper than GCP spot to have these always on.

I'll run many always on lxd containers that all match with the same stacks. Add another one when needing to parallelize more

zackifyon AI coding has made CI a bottleneck, so we reworked ours to keep up

Our CI has thousands of tests and is done in 2 minutes. Everytime it grows above 3 I add more parallelization and keep it ultra fast. Been working great for our team

zackifyon HarnessTax: How Much Does the Harness Matter for Coding Agents?

I have a couple hundred line TUI that just clones an LXD container and I get all my repos and infra isolated in 5s with pi having isolation to that container. Swap between any instance. Port forward to host all automatic.

Funny to me how stuff is described these days. Seems like some people lack the full understanding of all these different systems and really overcomplicate their harness setups or use super bloated all in one tooling.

zackifyon Show HN: Capsule – Single-file web apps that save their data into SQLite

love this idea!

zackifyon OpenAI Agents API

I just have a slack bot running on a VM that sees a message and invokes pi.

It would be trivial for every request to clone a full lxd container and have all the tools and repos required if I wanted to allow it to do even more.

Not sure why anyone prefers to choose locked in options

zackifyon Muse Spark 1.3

What type of setup do you use? I have very small 4-5k initial context and do one task then clear. I rarely go above 150k context for most things.

zackifyon Corporate America is getting hooked on open-source AI

Yeah what, I'm using flash models and getting a ton of stuff done. 300-400b param size with pi.dev

zackifyon Muse Spark 1.3

I have been using glm 5.3 flash and it feels as good as opus 5. Put a lot of work into it this week (100m tokens). Now I'm curious to try this one. These smaller models are getting very good imo

zackifyon Play Store blocks AuroraStore, hurting GrapheneOS users

It DOES still hurt.

For example the eBay app. Does not allow installing from the play store on grapheneos.

zackifyon Agent memory as a file format

No memory. No web search 99% of the time.

Two agent.MD files that are very small. One on each project. One at parent project level.

Did 30M tokens through glm 5.3 flash today for 52c

Using pi and a few extensions my initial context is always 4k max

zackifyon GLM-5.3-Flash

I ran 30M tokens through for 50c... insanity that this is possible.

and it really is opus 4.8 level.

zackifyon Automating Immersive Reading

Any plans to offer a way to generate audio books on demand. like if i set kokoro, a book auto imports, it can make the file for me for the whole book after some time of local gpu work?

zackifyon GLM-5.3 is now open-weight

Starlink? It's never gone anymore

zackifyon Automating Immersive Reading

Wow I didn't even think about just using on device AI.

I'm going to set this one up and try it with kokoro which has the most natural for small size that I've seen. Wonder if the paperwhite 12th Gen can handle it.

And also setup the main repo for when I have the real audio book. Thanks!

zackifyon Automating Immersive Reading

This is great. Recently got an xteink x3 and jailbroke my kindle, making custom stuff for it.

I couldn't find it exactly in the docs. Sorry if I missed it.

If you align these and then pull onto koreader via opds or other way, will audio work over Bluetooth there too? Along with the highlighting.

zackifyon GLM-5.3 is now open-weight

You do, there's like 20 providers for any model on openrouter. You can also just spin bedrock or gcp and download the weights for later if you're worried. It's never going to make cost sense when the token rate is so low with how expensive ram is

zackifyon Show HN: FnScribe – Open-source, offline dictation for macOS

https://voxtype.io/

https://tryvoiceink.com/

There's so many of these, at this point I've seen 10 clones make the front page each time as if there never existed local only options before.

Also whisper is pretty outdated vs parakeet

zackifyon Tailcat – Like netcat, but over Tailscale’s data plane

super sick, already setup a derp server.

dns node key for fun on one

and two machines that connect, with systemd to keep tailcat serving ssh running

zackifyon Disruption with Some GitHub Services

Can't even run self hosted github actions lol

zackifyon New MCP Roadmap

I think the spec overcomplicates everything honestly. Its not that hard to add a long running auth token and put it in the MCP config as a header to send along and then avoid all the extra special rules.

"Oh no it's a long lived token that's bad"

Put it in a secret manager like 1pw cli and now start an agent...

zackifyon Anthropic IPO valuation hinges on $190-200B 2028 revenue forecast

The world doesn't make sense to me. I use 5.6 Luna. Deepseek v4 flash 0731. And kimi k3. Don't even need claude anymore at their insane prices for anything I do.

zackifyon I turned my RSS feeds into an e-ink newspaper to stop reading on my phone

I have crossink which is awesome on the x3. I find it better with more features on top of crossink.

And then setup home assistant and picture rendering so when a package or person is detected while I'm reading on a jailbroke kindle, it pops up in the corner automatically with the feed so I can see who it is.

Tailscale too.

Having full control of these devices is awesome.

zackifyon Everyone is building LLM routers, we deprecated ours

I just use whatever's cheapest for personal things. Dsv4 flash and got 5.6 Luna are great for the price and I'll use the openrouter benchmark view to compare the overall score.

zackifyon Roblox Officially Supports GrapheneOS

Yeah I use rcs and you can use the pixel camera app if you want??

Rcs had a bug that was fixed recently though

zackifyon I Built a Telegram Client for Pi

I have the llm twean every little piece of pi which is why I love it. And swapping models. Plus not having scroll jank like I got in opencode.

I even tweaked hitting "enter" when nothing is in the input box, it resume the last request. I love having this control and ease to extend and add anything to the ui

zackifyon Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro

Yeah wyoming protocol I think someone even made kokoro Wyoming. I forgot exactly what I did it'd been a little while

zackifyon Every new car sold in the European Union must include a driver monitoring camera

A Tesla can choose to auto lock. Or not lock.

Or not lock in a certain area.

Plus the app is an actual usable thing. Not a crap one that sends notifications about doors being unlocked in a garage that never updates.

Last year I had to take my kia to the dealer just to have connectivity work. Verizon had a change and you couldn't even fix it without going in. Antiquated dealer software updates as well.

zackifyon Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro

I use kokoro with home assistant and its great. I find its the most natural sounding and small too.

I speak over sonos speakers when certain events happen. And use it as my voice assistant.

zackifyon Every new car sold in the European Union must include a driver monitoring camera

After seeing kia evs and having a Tesla. Its the only good EV brand because the software from everywhere else is a complete joke.

Kia will tell me my doors are unlocked when I'm at home.

Tesla has a set home feature. Plus the 50 other annoyances.

Regen doesn't even persist with kia. You have to press the paddle to add it every time you start the car.

All this to say, the only good ux car anymore is tesla. Too bad they leak all recordings and have privacy problems too.

zackifyon GLM 5.2 and the coming AI margin collapse

$6 a month I plan to use deepseek v4 flash mainly which should provide closer to 5x the usage on the cheaper ones but no set number