theanonymousone

Are you using Flet? If yes do you think it's mature enough and has a potential to stay long "in the game"?

Do we know if AA and DeepSWE benchmarks are on bf16 or fp8 quantisations?

I believe that will put them in the Pareto frontier.

But I cannot find this "variant" in OpenRouter.

Then it wouldn't be "SearXNG in Rust", would it?

It's not a metadata search engine, it's "meta" search engine.

Nice signal for lack of dominant AI use, it seems :D

At $2/$6, it can be much more "approachable" than K3. Wondering what have they done differently to be able to afford this price (that K3 couldn't, apparently - most other providers offer similar prices to K3 itself).

Please add me

For me at least, it makes way more sense on a DSv4 Flash size and ~10 tps and I would definitely try (or try to try) such a thing.

The concept and the proof of it is great, of course.

A benchmark website to benchmark benchmark websites?

Or a benchmark to benchmark benchmarks?

@dang is that how we call you?

Yes, sorry, I went into anti-procrastination mode after I posted. I hope someone fixes it.

No theoretical reason; It's backward compatibility/internal technicalities, as they mention in the JEP.

Sorry to be pedantic, but I believe this is a major source of confusion: Claude "Code" is not a model.

Yes. It's the one. Honestly I'm wondering too how it chooses articles to post.

I created a channel for myself some time ago, and the only way that I could think of was to put a 12h delay and then count score+comments.

It's on the front page now.

I know two HNTG channel (one "normal", one with summaries. I don't think they "official" in any sense of the word.

I wouldn't call it borderline. If we take the chart seriously (if), it means for every budget, the best performance is achieved by a 5.6 variant.

It's not about the table, unfortunately:

> Users on legacy annual Copilot plans will not receive access to new models and features.

I don't know what MT5, strat, OHLC, or YF are. But I have been loving streamlit since its start in 2019 for exactly being this much intuitive and quick to start with and prototype.

Congrats. Go ahead and have fun.

They say it here: https://docs.github.com/en/copilot/reference/copilot-billing...

But then again they released MAI despite this, so I don't know.

A very sharp slap in the face of those of us who kept our annual plans and didn't ask for s refund: It seems it will not be available to annual subscriptions.

What is meant by a "loop" here? Just repeating the same prompt until you get the desired result? Are subsequent repetitions too close to each other?

Th is really not good advertisement for Claude-Oriented Programming

Dupe? https://news.ycombinator.com/item?id=48590056

Yes. Whenever I tried, I found no reason to use DeepSeek v4 Pro versus MiMo v2.5 Pro, price-wise or performance-wise. Benchmarks also confirm this.

I hope Over-16s be next.

But the huggingface link mentions BF16, F16, and I32?

In OpenRouter, there is an "int4" tag for Moonshot provider of Kimi K2. 7 Code. Isn't that too low, particularly coming from the very developer of the model? Os that a mistake? How is it in their direct API offer?

"You're absolutely right"?

For me it is a tool I avail to an LLM so that it can provide correct answers to a certain category of questions, instead of hallucinating nonsense.