61–70 of 251 posts
Have you all noted that the latest releases (Qwen3 max thinking, now Kimi k2.5) from Chinese companies are benching against Claude opus now and not Sonnet? They are truly catching up, almost at the same pace?
I don't get this "agent swarm" concept. You set up a task and they boot up 100 LLMs to try to do it in parallel, and then one "LLM judge" puts it all together? Is there anywhere I can read more about it?
You can read about this basically everywhere - the term of art is agent orchestration. Gas town, Claude’s secret swarm mode, or people who like to use phrases like “Wiggum loop” will get you there. If you’re really lazy - the quick summary is that you can benefit from the sweet spot of context length and reduce instruction overload while getting some parallelism benefits from farming tasks out to LLMs with different…
Pretty cute pelican https://tools.simonwillison.net/svg-render#%3Csvg%20viewBox%...
Pretty cute pelican https://tools.simonwillison.net/svg-render#%3Csvg%20viewBox%...
Earlier quoted context omitted.
The other realistic setup is $20k, for a small company that needs a private AI for coding or other internal agentic use with two Mac Studios connected over thunderbolt 5 RMDA.
That won’t realistically work for this model. Even with only ~32B active params, a 1T-scale MoE still needs the full expert set available for fast routing, which means hundreds of GB to TBs of weights resident. Mac Studios don’t share unified memory across machines, Thunderbolt isn’t remotely comparable to NVLink for expert exchange, and bandwidth becomes the bottleneck immediately. You could maybe load fragments exp…
Huggingface Link: https://huggingface.co/moonshotai/Kimi-K2.5 1T parameters, 32b active parameters. License: MIT with the following modification: Our only modification part is that, if the Software (or any derivative works thereof) is used for any of your commercial products or services that have more than 100 million monthly active users, or more than 20 million US dollars (or equivalent in other currencies) in mont…
Hey have they open sourced all Kimi k2.5 (thinking,instruct,agent,agent swarm [beta])? Because I feel like they mentioned that agent swarm is available their api and that made me feel as if it wasn't open (weights)*? Please let me know if all are open source or not?
Why is that Claude still at the top in coding, are they heavily focused on training for coding or is it their general training is so good that it performs well in coding?
Someone please beat the Opus 4.5 in coding, I want to replace it.
A realistic setup for this would be a 16× H100 80GB with NVLink. That comfortably handles the active 32B experts plus KV cache without extreme quantization. Cost-wise we are looking at roughly $500k–$700k upfront or $40–60/hr on-demand, which makes it clear this model is aimed at serious infra teams, not casual single-GPU deployments. I’m curious how API providers will price tokens on top of that hardware reality.
Earlier quoted context omitted.
That won’t realistically work for this model. Even with only ~32B active params, a 1T-scale MoE still needs the full expert set available for fast routing, which means hundreds of GB to TBs of weights resident. Mac Studios don’t share unified memory across machines, Thunderbolt isn’t remotely comparable to NVLink for expert exchange, and bandwidth becomes the bottleneck immediately. You could maybe load fragments exp…
People are running the previous Kimi K2 on 2 Mac Studios at 21tokens/s or 4 Macs at 30tokens/s. Its still premature, but not a completely crazy proposition for the near future, giving the rate of progress.
Keep in mind that most people posting speed benchmarks try them with basically 0 context. Those speeds will not hold at 32/64/128k context length.
I guess after Kimi K2.5, other vendors are going to the same route?
Can't wait to see how this model performs on computer automation use cases like VITA AI Coworker.