Whoa whoa whoa, 118b params, 8b active MOE, long context reasoning, open weights - music to my ears. Hadn't heard of this lab before but I am very excited, will definitely try this out tomorrow - this is a real sweet spot I think in terms of model size and performance.
Laguna S 2.1
11–20 of 98 posts
Re: Laguna S 2.1
#12I love this. Is it possible to give a feel of how this stacks up to the good old Opus 4.5 in coding quality? For me that was the turning point where agentic coding in Claude Code etc became usable. Have we hit that threshold?
Having played with it for like 3 hours now....I'm probably moving from CC to this
Re: Laguna S 2.1
#13Testing it now. At the very least, competitive with DS4-Flash indeed. On my small (and per Sol's words, _very_ semantically dense) C test codebase, it found things that only gpt-5.2 managed to find back in the day, but also made a stupidly incorrect initial observation that a memfd_create()/mmap was used for IPC (funnily enough - sol missed that as well in its review, until I pointed it out). Re: the claims vs deepseek v4 - both flash and pro are expected to get a "general availability" release very soon (i.e. well-"post-trained"), so things can change in a... well, flash, as per usual in the current environment.
Anyways, keep 'em coming.
Re: Laguna S 2.1
#14I love this. Is it possible to give a feel of how this stacks up to the good old Opus 4.5 in coding quality? For me that was the turning point where agentic coding in Claude Code etc became usable. Have we hit that threshold?
Having played with it for like 3 hours now....I'm probably moving from CC to this
I am about 1 hour into using it with pi.dev. Do you have thinking on high? It is doing good but at one point i had to stop it and say 'you're overthinking this' haha
Re: Laguna S 2.1
#15Earlier quoted context omitted.
Having played with it for like 3 hours now....I'm probably moving from CC to this
I am about 1 hour into using it with pi.dev. Do you have thinking on high? It is doing good but at one point i had to stop it and say 'you're overthinking this' haha
What quant are you using?
Re: Laguna S 2.1
#16This is INSANE. How did they do this?
"What we've done in this model is not necessarily add more intelligence, but improve the behaviors that lead to a more capable model: more verification, less taking things for granted, not declaring victory early, and being more persistent.” + https://poolside.ai/assets/laguna/laguna-m1-xs2-technical-re...
Almost like a built-in heavyweight harness.
Re: Laguna S 2.1
#17This is INSANE. How did they do this?
"It went from the start of training to launch in under nine weeks..."
This is pretty impressive.
Re: Laguna S 2.1
#18Incredible. This is definitely the launch of the day. Just crushing Google's releases.
The pricing here is incredible. This is the first US release that's competitive with DeepSeek V4 Flash. Very excited about this.
Re: Laguna S 2.1
#19Testing it now. At the very least, competitive with DS4-Flash indeed. On my small (and per Sol's words, _very_ semantically dense) C test codebase, it found things that only gpt-5.2 managed to find back in the day, but also made a stupidly incorrect initial observation that a memfd_create()/mmap was used for IPC (funnily enough - sol missed that as well in its review, until I pointed it out). Re: the claims vs deepse…
What harness/quant did you use for testing?
Re: Laguna S 2.1
#20Earlier quoted context omitted.
I am about 1 hour into using it with pi.dev. Do you have thinking on high? It is doing good but at one point i had to stop it and say 'you're overthinking this' haha
What quant are you using?