Hacker News: bugglebeetle

New comment by bugglebeetle in "Anthropic's Safety Superpower"

bugglebeetle — Mon, 15 Jun 2026 15:33:48 +0000

See OpenRouter’s recent announcement on a model fusion setup, which they now support via API:

https://openrouter.ai/blog/announcements/fusion-beats-fronti...

New comment by bugglebeetle in "DeepSeek makes the V4 Pro price discount permanent"

bugglebeetle — Sun, 24 May 2026 15:56:05 +0000

Use their API directly, this is an openrouter issue. I ran something like 5 billion tokens through them directly recently without any bumps in the road.

New comment by bugglebeetle in "Local AI needs to be the norm"

bugglebeetle — Mon, 11 May 2026 05:44:48 +0000

Anthropic serves quantized versions of their models and you can run q8 locally.

New comment by bugglebeetle in "Local AI needs to be the norm"

bugglebeetle — Mon, 11 May 2026 02:30:30 +0000

The frontier Chinese open source models are already at this level, GLM-5.1 and Kimi K2.6 specifically.

New comment by bugglebeetle in "Claude Code refuses requests or charges extra if your commits mention "OpenClaw""

bugglebeetle — Thu, 30 Apr 2026 16:56:54 +0000

Deepseek has demonstrated that there is no reason for it to actually lose money. The awful business practices and monopoly tactics of the frontier model labs in the US are the problem.

New comment by bugglebeetle in "If America's so rich, how'd it get so sad?"

bugglebeetle — Thu, 23 Apr 2026 16:52:45 +0000

As Benjamin noted, “Christianity’s history is essentially that of its parasite […] capitalism.”

New comment by bugglebeetle in "Why Switzerland has 25 Gbit internet and America doesn't"

bugglebeetle — Mon, 06 Apr 2026 06:28:55 +0000

If you ever heard them talk about each other, you would definitely assume as much.

New comment by bugglebeetle in "Why Switzerland has 25 Gbit internet and America doesn't"

bugglebeetle — Mon, 06 Apr 2026 00:26:02 +0000

>homogenous country

Tell me you know nothing about Switzerland without telling me you know nothing about Switzerland. Try asking a German Swiss what they think about a French Swiss or either about the Romansch.

New comment by bugglebeetle in "'The Secret Agent': Exploring a Vibrant, yet Violent Brazil (2025)"

bugglebeetle — Tue, 17 Mar 2026 19:28:00 +0000

Bacurau is one of the best movies I’ve seen in recent memory and Pictures of Ghosts tells an amazing story about the history of Recife’s relationship to cinema.

New comment by bugglebeetle in "Qwen3.5 Fine-Tuning Guide"

bugglebeetle — Wed, 04 Mar 2026 21:40:30 +0000

Unfortunately, this looks to only cover the larger MoE models. I imagine the smaller models are what most people would target. 9B just dropped two days ago, so not surprised it’s not explicitly documented, but does use a hybrid mamba architecture that I expect needs some special consideration.

New comment by bugglebeetle in "Ireland rolls out basic income scheme for artists"

bugglebeetle — Thu, 12 Feb 2026 16:17:52 +0000

Ireland’s affordability problems are almost exclusively centered around its housing crisis and they need to just commit themselves to over-supply induced wealth destruction for the landlord class and older generations. Thankfully, there demographics also support such a move.

New comment by bugglebeetle in "GLM-OCR – A multimodal OCR model for complex document understanding"

bugglebeetle — Wed, 11 Feb 2026 16:50:43 +0000

I tested this pretty extensively and it has a common failure mode that prevents me from using: extracting footnotes and similar from the full text of academic works. For some reason, many of these models are trained in a way that results in these being excluded, despite these document sections often containing import details and context. Both versions of DeepseekOCR have the same problem. Of the others I’ve tested, dot-ocr in layout mode works best (but is slow) and then datalab’s chandra model (which is larger and has bad license constraints).

New comment by bugglebeetle in "GitHub Actions is slowly killing engineering teams"

bugglebeetle — Fri, 06 Feb 2026 08:00:31 +0000

Yeah, do crons even work consistently for GitHub Actions? I tried to set one up the other day and it just randomly skipped runs. There were some docs that suggested they’re entirely unreliable as well.

New comment by bugglebeetle in "Vibe coding kills open source"

bugglebeetle — Mon, 26 Jan 2026 14:17:26 +0000

> I remain convinced that if you write code then your product will sooner or later turn into a buggy mess.

FYFY

New comment by bugglebeetle in "AI Destroys Institutions"

bugglebeetle — Fri, 16 Jan 2026 11:09:51 +0000

Everyone who tells the story of the reformation leaves out that Martin Luther also used this new technology to widely disseminate his deranged anti-Semitic lies and conspiracies, leading to pogroms against Jews, a hundred years of war across Europe, and providing the ideological basis for the rise of Nazism.

New comment by bugglebeetle in "Claude Cowork runs Linux VM via Apple virtualization framework"

bugglebeetle — Thu, 15 Jan 2026 19:46:40 +0000

Tried this the other day and the setup on this is super cumbersome and requires you to constantly rebuild your entire dev and Claude Code environment every time you use a new container, including whitelisting URLs for package managers and the like.

New comment by bugglebeetle in "ACM Is Now Open Access"

bugglebeetle — Thu, 01 Jan 2026 16:05:52 +0000

This is lame, but always remember that OpenAlex exists and is completely free:

https://openalex.org/works?page=1&filter=primary_location.so...

New comment by bugglebeetle in "How AI labs are solving the power problem"

bugglebeetle — Wed, 31 Dec 2025 20:47:45 +0000

It’s called “Semi” analysis for a reason. Dylan Patel is the Jim Cramer of industry reporting for this sector.

New comment by bugglebeetle in "Show HN: Use Claude Code to Query 600 GB Indexes over Hacker News, ArXiv, etc."

bugglebeetle — Wed, 31 Dec 2025 09:31:09 +0000

Seems very cool, but IMO you’d be better off doing an open source version and then hosted SAAS.

New comment by bugglebeetle in "Professional software developers don't vibe, they control"

bugglebeetle — Tue, 30 Dec 2025 21:23:10 +0000

Nah, I don’t miss at all typing all the tests, CLIs, and APIs I’ve created hundreds of times before. I dunno if I it’s because I do ML stuff, but it’s almost all “think a lot about something, do some math, and and then type thousands of lines of the same stuff around the interesting work.”