Really interesting. The crazy changes in opus 4.6 really make me think that Anthropic is doing library-level RL. I think that is also the way forward to have 'llm-native' frameworks as a way to not get stuck in current coding practices forever. Instead of learning python 3.15, one would license a proprietary model that has been trained on python 3.15 (and the migrations) and gain the ability to generate python 3.15 code.
I found DeepSeek R1 (better for questions) and V3 (better for prose) to be very willing to discuss sex with a simple system prompt, as well as being very pleasant in articulation.
I guess, I prefer them because they are almost SOTA and very large.
Not through the official interface though. Needs to be hosted by a third party.
OpenRouter has a generous free tier for both.
I just saw that there is an abliterated version as well. Not sure how to try it though.
Oh yeah I was mainly thinking about smaller models because I want to run them locally. Not just because of the abliteration. I just want everything personal to run locally only. I don't trust any of the cloud companies.
I agree, if you don't like a key feature of a library, like tailwind-based styling which is meant to be customized, then that library is probably not for you.
The form component is more the exception for its complexity but forms are also very complex on the web.
Being a wrapper on top of Radix is kind of the point. You can't build a nice-looking MVP in an afternoon with Radix - you need one afternoon just to style every state of button - but with shadcn you can. Their experiment is to give you the ability to still spend an afternoon styling the button later without having to hack around a complex library. Your ability to rewrite it even away from tailwind is exactly the point. Ever tried rewriting MUI to use tailwind?
I've looked into the available options of parsing PDFs, including pypdf, which is what is being used here, a while ago and it's not good. While I haven't testing equations specifically, it think it's fair so assume that the results will be subpar especially complex ones.
I guess, this could be an application of the agent model. I've seen multiple LLMs recently trained specifically on LateX parsing. One model would recognize from the parsed PDF garbage that there is probably an equation there and call a different want to parse it.
Thank you for the idea to recognize the garbage to then use a different flow for the image of the equation from the pdf. Still left with an image to LaTeX problem, but maybe the state of the art has improved in the past years.
Another aspect is css class reuse. Inline styles are not preprocessed so each inline style is a 1:1 increase in bundle size. In large applications this can be significant. Imagine having hundreds of popups each with 50 lines of css. It adds up.
I've read it like this: They differentiate themselves from OpenAI/Anthropic/other major players by being in the EU and (more) open-source; they differentiate themselves from other European competitors by being as good as OpenAI.
I think it's a fine proposition given the early market and their team, as long as this hypothesis holds true for years to come,
> we believe that most of the value in the emerging generative AI market will be located in the hard-to-make technology, i.e. the generative models themselves,
If you read the memo carefully, they do claim to be open-source at the beginning, but then switch to explaining that they will make money off closed-source models for their customers.
So, not more open-source than what OpenAI is doing.
Ok, so they're aiming for a more "spray & pray" kind of GTM, challenging the incumbents based on the premise that it'll be EU based.
This basically then boils down to: "ChatGPT got x users in a week, and we want to do the same for EU.", without a clear path to profitability or guarantees.
So it's effectively a humongously risky bet by EU VCs?
I think that the investors are mainly betting on the team expertise to train models as good as the one of OpenAI but with an open source approach (the main differentiator), which according to the founders would open up a bigger market opportunity for them.
> So it's effectively a humongously risky bet by EU VCs?
isn't it supposed to be VCs job to bet on risk proposition with the hope of a 100x return?
VCs keep lecturing candidates on making sure that they have paying customers on the radar from day one, so no, that does not look like a reasonable VC bet.
I don't get why nobody is talking about this. I'm starting to suspect it only effects a subset of all AirPods Pro and is covered by this replacement program even though it's not really tasted clearly.
AirPods Pro even compared to the the non-Pros have awful microphones.
I agree. You can make a better case for “writing in a corporate context requires humility,“ e.g., someone choosing to post in public slack channel instead of talking to everyone individually.
