Hacker News: notsylver

New comment by notsylver in "Can you instruct a robot to make a PBJ sandwich?"

notsylver — Fri, 13 Mar 2026 04:43:21 +0000

This feels like a buzzfeed quizz for developers. If you think about each step long enough you can't really get a wrong answer

New comment by notsylver in "The path to ubiquitous AI (17k tokens/sec)"

notsylver — Fri, 20 Feb 2026 14:35:11 +0000

I always thought eventually someone would come along and make a hardware accelerator for LLMs, but I thought it would be like google TPUs where you can load up whatever model you want. Baking the model into hardware sounds like the monkey paw curled, but it might be interesting selling an old.. MPU..? because it wasn't smart enough for your latest project

New comment by notsylver in "I tried building my startup entirely on European infrastructure"

notsylver — Fri, 20 Feb 2026 09:46:46 +0000

You might be confused with their new-ish US datacenter? Hetzner is still European-owned.

New comment by notsylver in "Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed"

notsylver — Thu, 12 Feb 2026 14:30:26 +0000

I feel like cursors solution is still the best answer. Let the model suggest edits in whatever format it prefers using as few "extra" tokens as possible and have a small model figure it out. I don't use cursor anymore but when I did it was impressive how consistently it worked, I think there was a single time it failed. 70b might be overkill though...

New comment by notsylver in "When internal hostnames are leaked to the clown"

notsylver — Thu, 05 Feb 2026 06:14:06 +0000

I think people are misunderstanding. This isn't CT logs, its a wildcard certificate so it wouldn't leak the "nas" part. It's sentry catching client-side traces and calling home with them, and then picking out the hostname from the request that sent them (ie, "nas.nothing-special.whatever.example.com") and trying to poll it for whatever reason, which is going to a separate server that is catching the wildcard domain and being rejected.

New comment by notsylver in "Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete"

notsylver — Thu, 22 Jan 2026 11:09:30 +0000

I've been waiting for something like this for ages. Cursor making me pay $20/month when all I use from it is autocomplete was always a little annoying, especially as they changed the UI to push agents more and it got in the way. I was even considering doing it myself but wasn't sure about gambling on models small enough to run locally being smart enough to do anything useful.

I threw together a vscode extension to run it and while the extension is rough, the model seems decent. I'm trying to keep my expectations contained, in the past local models have been absolutely terrible for inline completion, this seems much better already. I hope this kicks off more competition.

New comment by notsylver in "[dead]"

notsylver — Thu, 15 Jan 2026 14:54:04 +0000

This really needs some examples or a demo that doesn't require signing in. As-is this is just a pricing page with a sign in button and no information on what it actually does?

New comment by notsylver in "AirPods libreated from Apple's ecosystem"

notsylver — Sun, 16 Nov 2025 06:06:22 +0000

It seems to let you access head tracking data, so now I'm really curious if it would be accurate enough to use with games (eg, microsoft flight sim/arma 3/euro truck simulator 2 head tracking). There is probably a lot of other interesting use cases for it too, but I'm stuck with windows for now so :(

DeepSeek-ocr.rs: Rust implementation of DeepSeek-OCR

notsylver — Wed, 29 Oct 2025 16:33:25 +0000

Article URL: https://github.com/TimmyOVO/deepseek-ocr.rs

Comments URL: https://news.ycombinator.com/item?id=45749244

Points: 5

# Comments: 0

New comment by notsylver in "BERT is just a single text diffusion step"

notsylver — Mon, 20 Oct 2025 17:21:31 +0000

I've really wanted to fine tune an inline code completion model to see if I could get at all close to cursor (I can't, but it would be fun), but as far as I know there are no open diffusion models to use as a base, and especially not any that would be good as a base. Hopefully something comes out soon that is viable for it

New comment by notsylver in "Gemini 2.5 Flash Image"

notsylver — Tue, 26 Aug 2025 16:23:06 +0000

I tried a dozen or so images. For some it definitely failed (altering details, leaving damage behind, needing a second attempt to get a better result) but on others it did great. With a human in the loop approving the AI version or marking it for manual correction I think it would save a lot of time.

This is the first image I tried:

https://i.imgur.com/MXgthty.jpeg (before)

https://i.imgur.com/Y5lGcnx.png (after)

Sure, I could manually correct that quite easily and would do a better job, but that image is not important to us, it would just be nicer to have it than not.

I'll probably wait for the next version of this model before committing to doing it, but its exciting that we're almost there.

New comment by notsylver in "Gemini 2.5 Flash Image"

notsylver — Tue, 26 Aug 2025 16:07:24 +0000

I didn't do any videos, just pictures, but considering how little I found for pictures I doubt you'll find much

New comment by notsylver in "Gemini 2.5 Flash Image"

notsylver — Tue, 26 Aug 2025 16:02:44 +0000

I scanned everything into 48-bit RAW and treat those as the originals, including the IR scan for ICE and a lower quality scan of the metadata. The problem is sharing them - important images I manually repair and export as JPEG which is time consuming (15-30 minutes per image, there are about 14000 total) so if its "generic family gathering picture #8228" I would rather let AI repair it, assuming it doesn't butcher faces and other important details. Until then I made a script that exports the raws with basic cropping and colour correction but it can't fix the colours which is the biggest issue.

New comment by notsylver in "Gemini 2.5 Flash Image"

notsylver — Tue, 26 Aug 2025 15:15:39 +0000

I digitised our family photos but a lot of them were damaged (shifted colours, spills, fingerprints on film, spots) that are difficult to correct for so many images. I've been waiting for image gen to catch up enough to be able to repair them all in bulk without changing details, especially faces. This looks very good at restoring images without altering details or adding them where they are missing, so it might finally be time.

New comment by notsylver in "Vanguard hits new 'bans-per-second' record"

notsylver — Mon, 25 Aug 2025 00:43:36 +0000

If CV cheats are good enough that people are using them (and then getting banned), and other people are willing to pay >$1000 for "undetected" cheats (that still get them banned)... wouldn't making custom hardware that is just a capture card and USB keyboard+mouse running one of those CV models that sends the inputs back over a "real" keyboard work?

New comment by notsylver in "Node.js is able to execute TypeScript files without additional configuration"

notsylver — Sun, 17 Aug 2025 14:05:24 +0000

I have tried fully switching to bun repeatedly since it came out and every time I got 90% of the way there only to hit a problem that couldn't be worked around. Last I tried I was still stuck on some libraries requiring napi functions that weren't implemented in bun yet, as well an issue I forget but it was vaguely something like `opendir` silently ignoring the `recursive` option causing a huge headache.

I'm waiting patiently for bun to catch up because I would love to switch but I don't think its ready for production use in larger projects yet. Even when things work, a lot of the bun-specific functionality sounds nice at first but feels like an afterthought in practice, and the documentation is far from the quality of node.js

New comment by notsylver in "I want everything local – Building my offline AI workspace"

notsylver — Sat, 09 Aug 2025 02:02:29 +0000

You already need very high end hardware to run useful local LLMs, I don't know if a 200gb vector database will be the dealbreaker in that scenario. But I wonder how small you could get it with compression and quantization on top

New comment by notsylver in "OpenFront: Realtime Risk-like multiplayer game in the browser"

notsylver — Fri, 11 Jul 2025 09:29:07 +0000

I'ts fun, I think it needs queues for different game modes because with 150 players you almost always get horded by neighbours. Being able to queue for a team game would make it a bit easier to learn I think

New comment by notsylver in "GitHub Copilot Coding Agent"

notsylver — Tue, 20 May 2025 06:07:29 +0000

I've had this too, especially it getting stuck at the very end and just.. never finishing. Once the usage-based billing comes into effect I think I'll try cursor again. What local models are you using? The local models I tried for autocomplete were unusable, though based on aiders benchmark I never really tried with larger models for chat. If I could I would love to go local-only instead.

New comment by notsylver in "Viral ChatGPT trend is doing 'reverse location search' from photos"

notsylver — Sat, 19 Apr 2025 06:27:52 +0000

I showed the model a picture and any text written on that picture and asked it to guess a latitude/longitude using the tool use API for structured outputs. That was in addition to having it transcribe the hand written text and extracting location names, which was my original goal until I saw how good it was at guessing exact coordinates. It would guess within ~200km on average, even on pictures with no information written on them.