bugglebeetle

> he framed his part as addressing the challenge not the ethics

I didn’t know that Arendt’s concept of the banality of evil was something people willfully embraced.

OpenAI is now part of the national security state and so is now above anything beyond performative legal vulnerability.

I recently switched to using for some large volume inference with small, fine-tuned models and was surprised how nice and painless things were. vLLM seems to have a lot more gotchas and kludged together stuff once you get outside of anything straightforward.

> Hopefully the anti-trust enforcers

Let me stop you right there…

I’m old enough to remember the heavenly times before people repeated phrases like “the taxi cartel” as if they were original thoughts vs. cooked up by Uber’s comms team.

I forgot this was in effect. I’ve been hitting my weekly rate limits two to three days in because of needing to steer Slopus 5 with Fable. Absurd that they’re being cut further in the face of steep competition from open weights models.

The datalab models are the best ones.

Not exactly. See:

https://alexzhang13.github.io/blog/2026/mgh/

Undoubtedly, the frontier labs are already doing something akin to this as part of their new chip design endeavors.

I haven’t used their platform so can’t speak to this, but super brilliant team and big fans of their work overall!

Tinker is pretty cheap. Prime Intellect if you want more flexibility.

It’s not “deeply weird” but was intentionally legislated to prevent labor from obtaining similar sectorial bargaining power and political influence as they had in Europe. Some entertainment industry unions had already achieved similar stature pre-WWII and were grandfathered in, but the US learned their lesson here and explicitly sought to atomize at the workplace level.

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

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

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.

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

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

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.

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

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

>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.

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.

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.

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.

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).

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.

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

FYFY

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.

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.

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

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

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