Hacker News: ilnmtlbnmhttps://news.ycombinator.com/user?id=ilnmtlbnmHacker News RSShttps://hnrss.org/hnrss v2.1.1Fri, 11 Sep 2026 13:42:53 +0000<![CDATA[New comment by ilnmtlbnm in "The Deathray: A simple way for an untrusted site to freeze a Mac"]]>Amazing!

I encountered the same type of death freeze when trying (and failing) to run models in browser tabs, but didn't spend much time trying to understand how severe it is.

Hope they don't disable WebGPU...

]]>Thu, 10 Sep 2026 20:00:29 +0000https://news.ycombinator.com/item?id=49649439ilnmtlbnmhttps://news.ycombinator.com/item?id=49649439https://news.ycombinator.com/item?id=49649439<![CDATA[New comment by ilnmtlbnm in "Reasoning models produce fractals when asked to solve hard problems"]]>"reasoning models are dynamical systems with fractal basins"

]]>Thu, 10 Sep 2026 19:50:13 +0000https://news.ycombinator.com/item?id=49649315ilnmtlbnmhttps://news.ycombinator.com/item?id=49649315https://news.ycombinator.com/item?id=49649315<![CDATA[Reasoning models produce fractals when asked to solve hard problems]]>Article URL: https://github.com/GilpinLab/loopscape

Comments URL: https://news.ycombinator.com/item?id=49649314

Points: 1

# Comments: 1

]]>Thu, 10 Sep 2026 19:50:13 +0000https://github.com/GilpinLab/loopscapeilnmtlbnmhttps://news.ycombinator.com/item?id=49649314https://news.ycombinator.com/item?id=49649314<![CDATA[Printing Gaussian Splats]]>Article URL: https://www.patreon.com/DanyBittel/posts/printing-splats-161333338

Comments URL: https://news.ycombinator.com/item?id=48618481

Points: 375

# Comments: 46

]]>Sun, 21 Jun 2026 12:49:02 +0000https://www.patreon.com/DanyBittel/posts/printing-splats-161333338ilnmtlbnmhttps://news.ycombinator.com/item?id=48618481https://news.ycombinator.com/item?id=48618481<![CDATA[An Engineer's Day at Dust]]>Article URL: https://dust.tt/blog/an-engineers-day-at-dust

Comments URL: https://news.ycombinator.com/item?id=47895456

Points: 4

# Comments: 0

]]>Fri, 24 Apr 2026 20:39:07 +0000https://dust.tt/blog/an-engineers-day-at-dustilnmtlbnmhttps://news.ycombinator.com/item?id=47895456https://news.ycombinator.com/item?id=47895456<![CDATA[New comment by ilnmtlbnm in "Show HN: Three new Kitten TTS models – smallest less than 25MB"]]>I've got a cli version that's about 60MB total, no dependencies, including the (nano, for now, will add tiny soon) model -> https://github.com/idle-intelligence/tts-web

]]>Mon, 23 Mar 2026 16:44:35 +0000https://news.ycombinator.com/item?id=47491916ilnmtlbnmhttps://news.ycombinator.com/item?id=47491916https://news.ycombinator.com/item?id=47491916<![CDATA[New comment by ilnmtlbnm in "Show HN: Three new Kitten TTS models – smallest less than 25MB"]]>Not sure I understand what you're asking: there are faster than realtime models that you can use, locally or as APIs.

]]>Mon, 23 Mar 2026 16:41:48 +0000https://news.ycombinator.com/item?id=47491886ilnmtlbnmhttps://news.ycombinator.com/item?id=47491886https://news.ycombinator.com/item?id=47491886<![CDATA[New comment by ilnmtlbnm in "Show HN: Three new Kitten TTS models – smallest less than 25MB"]]>I've been playing with running small models in browser tabs for some time, and finally decided to open some of it.

Added kitten (nano only, for now, will move on to mini) to my "web tts thing": https://github.com/idle-intelligence/tts-web

demo: https://idle-intelligence.github.io/tts-web/web/

]]>Mon, 23 Mar 2026 16:39:05 +0000https://news.ycombinator.com/item?id=47491837ilnmtlbnmhttps://news.ycombinator.com/item?id=47491837https://news.ycombinator.com/item?id=47491837<![CDATA[New comment by ilnmtlbnm in "Unmute: Make LLMs Listen and Speak"]]>low latency speech-to-text -> LLM -> text-to-speech

]]>Tue, 27 May 2025 18:44:38 +0000https://news.ycombinator.com/item?id=44109611ilnmtlbnmhttps://news.ycombinator.com/item?id=44109611https://news.ycombinator.com/item?id=44109611<![CDATA[Unmute: Make LLMs Listen and Speak]]>Article URL: https://kyutai.org/2025/05/22/unmute.html

Comments URL: https://news.ycombinator.com/item?id=44109610

Points: 3

# Comments: 1

]]>Tue, 27 May 2025 18:44:38 +0000https://kyutai.org/2025/05/22/unmute.htmlilnmtlbnmhttps://news.ycombinator.com/item?id=44109610https://news.ycombinator.com/item?id=44109610<![CDATA[New comment by ilnmtlbnm in "MRML is now MIT licensed"]]>From the readme:

"This project is a reimplementation of the nice MJML markup language in Rust."

]]>Sun, 24 Mar 2024 19:25:17 +0000https://news.ycombinator.com/item?id=39809585ilnmtlbnmhttps://news.ycombinator.com/item?id=39809585https://news.ycombinator.com/item?id=39809585<![CDATA[New comment by ilnmtlbnm in "Is anybody still using Windows 95?"]]>Take a look at : https://www.softwareheritage.org/ They've made it their mission to collect and preserve source code.

]]>Wed, 09 Sep 2020 08:25:49 +0000https://news.ycombinator.com/item?id=24418687ilnmtlbnmhttps://news.ycombinator.com/item?id=24418687https://news.ycombinator.com/item?id=24418687<![CDATA[Awesome Engineering Team Management]]>Article URL: https://github.com/kdeldycke/awesome-management

Comments URL: https://news.ycombinator.com/item?id=22222862

Points: 13

# Comments: 2

]]>Mon, 03 Feb 2020 10:05:11 +0000https://github.com/kdeldycke/awesome-managementilnmtlbnmhttps://news.ycombinator.com/item?id=22222862https://news.ycombinator.com/item?id=22222862<![CDATA[New comment by ilnmtlbnm in "Understanding Text with Bert"]]>This is part 2 of a post on "Building a machine reading comprehension system using the latest advances in deep learning for NLP".

It uses HugginFace's BERT PyTorch implementation to do question answering.

Part 1 was submitted here : https://news.ycombinator.com/item?id=20820016

]]>Tue, 10 Sep 2019 14:03:34 +0000https://news.ycombinator.com/item?id=20928281ilnmtlbnmhttps://news.ycombinator.com/item?id=20928281https://news.ycombinator.com/item?id=20928281<![CDATA[Understanding Text with Bert]]>Article URL: https://blog.scaleway.com/2019/understanding-text-with-bert/

Comments URL: https://news.ycombinator.com/item?id=20926501

Points: 7

# Comments: 1

]]>Tue, 10 Sep 2019 09:39:04 +0000https://blog.scaleway.com/2019/understanding-text-with-bert/ilnmtlbnmhttps://news.ycombinator.com/item?id=20926501https://news.ycombinator.com/item?id=20926501<![CDATA[Natural Language Processing: The Age of Transformers]]>Article URL: https://blog.scaleway.com/2019/building-a-machine-reading-comprehension-system-using-the-latest-advances-in-deep-learning-for-nlp/

Comments URL: https://news.ycombinator.com/item?id=20820016

Points: 200

# Comments: 24

]]>Wed, 28 Aug 2019 14:20:56 +0000https://blog.scaleway.com/2019/building-a-machine-reading-comprehension-system-using-the-latest-advances-in-deep-learning-for-nlp/ilnmtlbnmhttps://news.ycombinator.com/item?id=20820016https://news.ycombinator.com/item?id=20820016