Hacker News: deskamess

New comment by deskamess in "Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code"

deskamess — Sun, 05 Apr 2026 23:43:33 +0000

Are the Claude Code (desktop) models very different from what Bedrock has? I thought you could hook up VSCode (not Claude Desktop) to Bedrock Anthropic models. Are there features in Claude Desktop that are not in VSCode/cli?

New comment by deskamess in "We replaced RAG with a virtual filesystem for our AI documentation assistant"

deskamess — Sat, 04 Apr 2026 17:29:51 +0000

Interesting... what is the use case for the AI that is querying it? Is it how to develop additional features for integration with your app or do you have some other use case? Code review/audit/debugging/etc. For AI developing against an API I would think an OpenAPI json file would do the trick.

Is the Roslyn method called as part of the build/publish?

New comment by deskamess in "Firm boosts H.264 streaming license fees from $100k up to staggering $4.5M"

deskamess — Sat, 04 Apr 2026 10:59:58 +0000

For a long time I thought my RTX-2060 was just not capable and the other day I did a ffmpeg GPU transcode and was surprised by how well it did. So now I am thinking about putting on some of Google's new Gemma edge models (probably the smallest will work with my 6GB VRAM + 2 GB) setup. I am not a 100% sure what that 2GB is but I think it is borrowing from the system in some manner.

New comment by deskamess in "Claude Code Unpacked : A visual guide"

deskamess — Wed, 01 Apr 2026 13:43:27 +0000

I like the Claude desktop interface. The color scheme, presentation, fonts, etc. Is there a CSS I can find for the desktop version - I assume it's using some kind of web rendering engine and CSS is part of it.

New comment by deskamess in "Boomloom: Think with your hands"

deskamess — Sun, 22 Mar 2026 11:56:51 +0000

Is there a link to US/Canada retailers?

Edit: Never mind. I always find it after asking a question.

New comment by deskamess in "Astral to Join OpenAI"

deskamess — Thu, 19 Mar 2026 19:32:38 +0000

uv has been very useful but I also looking at pixi. Anyone have any experience with that? I hear good things about it.

New comment by deskamess in "Wide logging: Stripe's canonical log line pattern"

deskamess — Thu, 19 Mar 2026 12:30:44 +0000

I see one of your responses that this is a complement to an existing logging system - a one line summary. That works for me.

New comment by deskamess in "Warranty Void If Regenerated"

deskamess — Thu, 19 Mar 2026 12:23:53 +0000

I had no idea it was AI assisted (as another comment put it). However I am fine with this... I would certainly enhance my long form content like the author described. The author mentioned the use of world bible and style guides, and it shows through in the consistency and tightness of the article. And that is key... to take something AI generated (based on a prompt) and rework it systematically in an iterative human-in-the loop. The end result was a great read.

New comment by deskamess in "Wide logging: Stripe's canonical log line pattern"

deskamess — Wed, 18 Mar 2026 17:30:19 +0000

Are there any restrictions on how short the error_slug should be? The meat of some of my errors can be pretty long (for example an ffmpeg error). There are also many phases to a job - call them tasks. Can a canonical log line be a collection of task log lines?

New comment by deskamess in "Rust implementation of Mistral's Voxtral Mini 4B Realtime runs in your browser"

deskamess — Tue, 10 Feb 2026 17:37:34 +0000

Can you use handy exclusive via the cli if you have a file to feed it?

New comment by deskamess in "The $100B megadeal between OpenAI and Nvidia is on ice"

deskamess — Sat, 31 Jan 2026 13:50:23 +0000

Do they have a good multilingual embedding model? Ideally, with a decent context size like 16/32K. I think Qwen has one at 32K. Even the Gemma contexts are pretty small (8K).

New comment by deskamess in "Vitamin D and Omega-3 have a larger effect on depression than antidepressants"

deskamess — Thu, 29 Jan 2026 13:23:29 +0000

It is still prescribed for epilepsy. I am actually hoping for some medication stories if anyone/someone they know has ADHD and epilepsy. It's for a juvenile, but your stories can be for any age. Or pointers to any resources about the combo.

New comment by deskamess in "Dole Kemp 96 Web Site"

deskamess — Wed, 28 Jan 2026 17:00:26 +0000

This makes 50 cookies. I think they are too small (tsp scoop on baking sheet). That's the only mod I would make.

New comment by deskamess in "Kimi Released Kimi K2.5, Open-Source Visual SOTA-Agentic Model"

deskamess — Tue, 27 Jan 2026 17:41:23 +0000

I think there is a book (Chip War) about how the USSR did not effectively participate in staying at the edge of the semiconductor revolution. And they have suffered for it.

China has decided they are going to participate in the LLM/AGI/etc revolution at any cost. So it is a sunk cost, and the models are just an end product and any revenue is validation and great, but not essential. The cheaper price points keep their models used and relevant. It challenges the other (US, EU) models to innovate and keep ahead to justify their higher valuations (both monthly plan, and investor). Once those advances are made, it can be bought back to their own models. In effect, the currently leading models are running from a second place candidate who never gets tired and eventually does what they do at a lower price point.

New comment by deskamess in "Show HN: 22 GB of Hacker News in SQLite"

deskamess — Tue, 30 Dec 2025 21:02:47 +0000

How do you read youtube videos? Very curious as I have been wanting to watch PDF's scroll by slowly on a large TV. I am interested in the workflow of getting a pdf/document into a scrolling video format. These days NotebookLM may be an option but I am curious if there is something custom. If I can get it into video form (mp4) then I can even deliver it via plex.

New comment by deskamess in "Gemini 3 Flash: Frontier intelligence built for speed"

deskamess — Wed, 17 Dec 2025 18:06:11 +0000

Monopolies and wanna-be monopolies on the AI-train are running for their lives. They have to innovate to be the last one standing (or second last) - in their mind.

New comment by deskamess in "LLM from scratch, part 28 – training a base model from scratch on an RTX 3090"

deskamess — Tue, 09 Dec 2025 16:21:18 +0000

I have an old 2060 with 6GB (I think). I also have a work laptop 3060 with 6GB (shared to 8GB). What can I do with those? I dabble a bit here and there but I would like to run my own local LLM for 'fun'.

Thanks!

New comment by deskamess in "Tailscale Down"

deskamess — Thu, 20 Nov 2025 01:16:40 +0000

Yep... cant wait for them 'unwrap' the reason.

New comment by deskamess in "X5.1 solar flare, G4 geomagnetic storm watch"

deskamess — Tue, 11 Nov 2025 22:41:20 +0000

Bad timing for North America Eastern TZ - day break here. Pacific/Mountain TZ should be fine.

New comment by deskamess in "Why JPEG XL ignoring bit depth is genius (and why AVIF can't pull it off)"

deskamess — Mon, 27 Oct 2025 14:05:39 +0000

How far away is JPEG-XL rust version from Google if Chrome is not interested in it?