Hacker News: skolos

New comment by skolos in "Rune: A native GPU-rendered Rust UI framework for macOS, Windows, Linux and web"

skolos — Fri, 06 Nov 2026 18:42:08 +0000

What is benefit of GPU-rendered UI? In regular 2d apps where I can select enable/disable GPU rendering, disabling doesn't make app feel slower, but it drastically reduces RAM and VRAM usage (VRAM is the one I care about, as I run local models). Why so many UI frameworks brag that they are GPU-rendered?

Claude Ultra drops 5-hour limits

skolos — Tue, 03 Nov 2026 11:59:06 +0000

Article URL: https://www.online-tech-tips.com/anthropic-claude-code-five-hour-limit-removed-ultra/

Comments URL: https://news.ycombinator.com/item?id=50350904

Points: 1

# Comments: 0

New comment by skolos in "Bidirectional charging during grid outages"

skolos — Mon, 02 Nov 2026 02:26:11 +0000

If you have free night charging plan you can recoup quite faster. My system paid off for itself in 3 years - although I designed and set it up myself, so it was about 3x cheaper than through contractors (and yes I'm in US and I pulled permits to do this).

New comment by skolos in "I went to Mexico to test-drive the cars Americans can’t buy"

skolos — Thu, 29 Oct 2026 19:43:50 +0000

You mean 2.25MW chargers: https://electrek.co/2026/09/30/chinas-2250kw-chargers-are-al...

New comment by skolos in "fheroes2: A recreation of Heroes of Might and Magic II game engine"

skolos — Sun, 25 Oct 2026 18:33:15 +0000

Maybe civ 5 is more reactionary than strategic, so simple strategy that doesn't look too much into future works reasonably well. Or maybe civ is more mainstream and models absorbed more knowledge about strategies that work reasonably well.

New comment by skolos in "fheroes2: A recreation of Heroes of Might and Magic II game engine"

skolos — Sun, 25 Oct 2026 15:07:44 +0000

I just started live streaming another game - now played by Muse Spark 1.3 (much cheaper than Opus 5.5):

https://www.youtube.com/live/jRi9cdo95As

New comment by skolos in "fheroes2: A recreation of Heroes of Might and Magic II game engine"

skolos — Sun, 25 Oct 2026 12:31:16 +0000

Interesting that this is on front page. I thought HOMM is quite niche right now. I'm still spending some time on HOMM3 and recently created mcp for Claude Code (with opus 5.5) to play it - you can look at short playthrough here: https://www.youtube.com/live/uU-vvTOZFQY

It is not good at it! And very slow! I tried to improve, teach strategies, write some analysis scripts, etc. Did not help much.

Running Two 27B Models on a Single RTX 5090

skolos — Tue, 13 Oct 2026 14:52:30 +0000

Article URL: https://blog.kvit.app/posts/two-27b-models-on-single-rtx5090/

Comments URL: https://news.ycombinator.com/item?id=50072677

Points: 3

# Comments: 0

Diablo 2 in VR

skolos — Tue, 13 Oct 2026 01:50:13 +0000

Article URL: https://github.com/bearstonem/d2r-pcvr

Comments URL: https://news.ycombinator.com/item?id=50065570

Points: 8

# Comments: 0

New comment by skolos in "AI coding agents generate more code, but not more software"

skolos — Mon, 12 Oct 2026 18:33:00 +0000

My experience is that agents are decent in coding a feature, solving a bug - doing specific well defined task. They are very bad at judging UI/UX and user flows through app. Like really, really bad. They can quickly put together vibe coded app but make it usable takes a lot of extra manual work.

Did anyone solve this problem? Any good approaches?

New comment by skolos in "Whistle: Speech to Text in 16.9 MB"

skolos — Fri, 09 Oct 2026 12:46:26 +0000

By the way - Opus refuses to help you with setting this up - I used grok to drive this.

New comment by skolos in "Whistle: Speech to Text in 16.9 MB"

skolos — Fri, 09 Oct 2026 12:22:52 +0000

qwen3-asr-1.7b and parakeet both allow context/hotwords to bias transcription

New comment by skolos in "Whistle: Speech to Text in 16.9 MB"

skolos — Fri, 09 Oct 2026 08:54:10 +0000

Here's how to root echo show 8 1st gen: https://xdaforums.com/t/unlock-root-twrp-unbrick-amazon-echo...

New comment by skolos in "Whistle: Speech to Text in 16.9 MB"

skolos — Fri, 09 Oct 2026 08:52:11 +0000

responds within 1-2 seconds including 0.5 second waiting for silence as a trigger to start processing.

New comment by skolos in "Whistle: Speech to Text in 16.9 MB"

skolos — Thu, 08 Oct 2026 23:08:34 +0000

I confirm this as my experience as well. Parakeet did not perform well for me (English with heavy accent). Whisper large is much better. But once we get to model of this size look at qwen3-asr (1.7b parameters). I'm quite happy with how it performs (both transcription quality and speed on rtx5080). By the way the model is also available on openrouter and very/very cheap. Performance is reasonable (<1s response), but some requests are delayed (>10s)

New comment by skolos in "Whistle: Speech to Text in 16.9 MB"

skolos — Thu, 08 Oct 2026 22:43:31 +0000

Just ran some tests on my phrases:

- my whistle setup (tested can run on echo show with <1s response): 206 correct out of 208

These were not tested on echo show yet - on my pc for now:

- Vosk small, phrase grammar: 184/208

- Speech-to-Phrase 1.4.3 (Kaldi): 118/208

- suggested sphinx: 63/208 and on some examples took 13s on i7 14700k pc

looks like my customized whistle works better for me than these alternatives. But more testing wouldn't hurt.

New comment by skolos in "Whistle: Speech to Text in 16.9 MB"

skolos — Thu, 08 Oct 2026 21:39:16 +0000

It is all custom made and not very reproducible. I'm working on reproducible setup and once it is done will publish it here: https://blog.kvit.app

Claude Isn't Allowed to Write Me Prose

skolos — Thu, 08 Oct 2026 21:28:06 +0000

Article URL: https://blog.kvit.app/posts/agent-not-allowed-to-write-prose/

Comments URL: https://news.ycombinator.com/item?id=50012565

Points: 1

# Comments: 0

New comment by skolos in "Whistle: Speech to Text in 16.9 MB"

skolos — Thu, 08 Oct 2026 20:23:19 +0000

Interesting that this is here. I used whistle (and bunch of other things) to take ownership of my echo show. It now doesn't dial to Amazon at all - it does all processing locally with its own CPU and connects to my homeassistant for home automation. My initial setup involved qwen asr (1.7b model) running on rtx 5080. Compared to that, whistle was really bad (out of 170 messages, qwen recognized correctly 168, whistle - 70), but I adjusted whistle to work like jev - instead of free form transcription it recognizes only select set of templates (I trained tiny network with 10,000 generated utterances to translate whistle final state to probabilities within templates). The precision went up to 164/170 - almost matching qwen. By the way - I'm speaking with heavy accent.

Claude Isn't Allowed to Write Me Prose

skolos — Wed, 07 Oct 2026 03:45:41 +0000

Article URL: https://blog.kvit.app/posts/agent-not-allowed-to-write-prose/

Comments URL: https://news.ycombinator.com/item?id=49987880

Points: 6

# Comments: 0