News for hackers. Stuff that matters.
Re:Step 3.5 Flash: Fast Enough to Think. Reliable Enough to Act by Havoc on Thursday February 19, 2026 @04:26AM (#47071791)
>first model that has really broken into the anglosphere.

Do you know of a couple of interesting ones that haven't yet?

Re:Step 3.5 Flash: Fast Enough to Think. Reliable Enough to Act by kristopolous on Thursday February 19, 2026 @04:31AM (#47071828)
doubao (bytedance) seed models are interesting

Keep your eye on Baidu's Ernie https://ernie.baidu.com/

Artificial analysis is generally on top of everything

https://artificialanalysis.ai/leaderboards/models

Those two are really the new players

Nanbeige which they haven't benchmarked just put out a shockingly good 3b model https://huggingface.co/Nanbeige - specifically https://huggingface.co/Nanbeige/Nanbeige4.1-3B

You have to tweak the hyper parameter like they say but I'm getting quality output, commensurate with maybe a 32b model, in exchange for a huge thinking lag

It's the new LFM 2.5

Re:Step 3.5 Flash: Fast Enough to Think. Reliable Enough to Act by admiralrohan on Thursday February 19, 2026 @07:38AM (#47073127)
Never heard of Nanbeige, thanks for sharing. "Good" is subjective though, in which tasks can I use it and where to avoid?
Re:Step 3.5 Flash: Fast Enough to Think. Reliable Enough to Act by kristopolous on Thursday February 19, 2026 @07:40AM (#47073140)
it's a 3b model. Fire it up. If you have ollama just do this:

ollama create nanbeige-custom -f <(curl day50.dev/Nanbeige4.1-params.Modelfile)

That has the hyperparameters already in there. Then you can try it out

It's taking up like 2GB ram on my mac mini

my test query is always "compare rust and go with code samples". I'm telling you, the thinking token count is ... high...

Here's what I got https://day50.dev/rust_v_go.md

I'm going to go try this on a pi. I'll report back.

Re:Step 3.5 Flash: Fast Enough to Think. Reliable Enough to Act by Havoc on Thursday February 19, 2026 @08:05AM (#47073307)
Thanks!