Hacker News Reader

But there are thresholds of commercial viability in all of this. DeepSeek's technology gets you over that line with less sophisticated hardware.

There's already some pretty impressive work being done with folks using just a pair of M2 Ultras with r1 in a "home lab" context that goes way beyond what you could previously do with llama.

View on HN

Yes, but the r1 model is shiny and new. I've been using it locally for a day and I'm already finding odd spots. One thing that I've seen it do a number of times is get the correct answer in the thinking tokens, then ignore it, generate thousands more tokens until it reaches it context length then give a wrong answer.

There are things, like doc strings for functions, that llama models give better results for.

Reply on news.ycombinator.com