Mealie isn’t bad, but the UI makes it a huge pain to enter recipes. Luckily, the web import often works well, but some websites don’t support the JSON recipe format it requires. I recently setup llama.cpp on my server for the “AI import” feature that closes the gap well enough.

Yeah, I use 3.8 27B and it’s like Sonnet 5 for a lot of tasks. If they’re keeping up with Sonnet, 5.5 is similar to Fable, and it would be pretty nuts if Qwen 4 27B kept pace.

Yeah, don’t buy an overpriced Raspberry Pi; instead, you should buy a more reasonably priced…oh.

I know a lot of people love RoR, but I don’t. I have a long list of reasons, including it being slow, the syntax is weird, and while it’s possible to do compile-time type checking, it feels clunky and bolted on. RSpec especially annoys me with its use of dynamic language features to “cheat” when writing tests instead of creating code that is loosely coupled and testable. Don’t get me started on ORMs.

At work, I’m forced to work in legacy RoR codebases, and honestly, AI coming along and letting me work at a layer of abstraction above RoR was a welcome change. I used to spend the a whole day getting pissed off whenever I had to work in these RoR codebases, and letting a LLM generate the code lets me disconnect, keep my emotions out of it’d and pump out whatever drivel is needed to earn my paycheck for the day.

Yep, I assume that’s the plan, though HuggingFace isn’t the only game in town. Hugging Bay, ModelScope, and I assume a horde of others will fill the void if HF goes downhill.

I run Qwen 3.8 27B, which seems pretty comparable to Sonnet 5 for coding and other tasks. Qwen 3.6 was in the neighborhood of Sonnet 4.6. Qwen 4 27B is supposed to drop in the next couple months and we’ll see how it compares to Sonnet 5.5, which benchmarks at Fable / Mythos level.

If the trend keeps up, not sure how useful those data centers will be when a gaming PC is a few months behind the frontier.

Meh, I’ll stick with In-N-Out if I want a burger and fries. At least their employees are paid better, the food is better quality, and they don’t pull “make number go” up bullshit like this.

Cool, stick with LLMs or NPCs in games and leave living things alone.

Hold me back, Bro! Im super dangerous, yo!

Right? I’ve added hooks in Playwright in the past that save streamed video to disk. The browser already downloaded it, has it in memory, and is playing it, so what difference does dumping it to disk make?

I’m sure a lot of people have been “hit really hard” with the streaming subscriptions they canceled over Disney’s stupid bullshit.

I wonder how much of that proclaimed TAM will be addressed with open models. I’m running Qwen 3.8 27B on my 7900 XTX and have no need to give Anthropic or OpenAI any of my money or data.

I recently learned Netflix and other streaming providers now create content with the assumption of being a “second screen”. They repeat plot points and dumb it down so that people scrolling on their phones and only halfway paying attention can still follow along. We’re down a bad path in general and AI sure isn’t helping. Maybe the next step is AI summaries so people don’t even have to watch the AI slop content in the first place?

Agreed, and elected representatives don’t even need to have a particularly deep understanding in a particular area to make laws that are fair. They don’t have to understand all the math behind gradient descent or transformers to keep big corporations from abusing the tech, just like they don’t need to understand the intricacies of car engines to make traffic safety laws. They do need to consult experts and preferably have data to back up the laws.

I mainly use Mint as my desktop distro, but it’s not lightweight, it’s batteries included. If lightweight is what you want, there are better options.

Well, of course he’s not gonna go away! You give him a dollar, he’s gonna assume you got more!

Hmm, I bet there’s a hidden 50 cent surcharge. Damn it, Loch Ness Moster, I ain’t giving’ you no tree fiddy!

generate their own practice questions, to generate their own essay marking guidelines, and to test themselves on their essay writing

This might be useful for certain high school students who are disciplined enough to use it to enhance their learning instead of doing their work for them, but for every other kid, I definitely would not recommend just putting them in front of ChatGPT and letting them have at it. Parents could perhaps perform the quoted tasks to assist the student, but then again, they’d be taking on the role of a tutor in that case, and many parents would prefer to hire someone for various reasons. AI is also not going to provide the external discipline that some kids need to stay focused and get their work done. So no, AI does not replace tutors.

“Stable genius” would be more apt because the exponential benchmark growth period appears to be over and the term has an ironic meaning from Trump’s own usage that very much applies to LLMs.