Has anyone here really pushed the multimodal stuff with this yet? Been running this on a 4090 for over 24 hours and have been meaning to try out if its able to summarize images well, especially compared to something like qwen3vl on the same hardware

claude opus 4.8 doesnt even come close in terms of understanding how systems actually work or bothering to actually read existing code beyond the most cursory glance. the united states empire is truly over, as are these “premium” “flagship” closed weight Western models. Every so called mainstream “benchmark” publication is a bold faced lie where each company pays off the creators of each major benchmark publisher to tip the scales in their favor. Even when playing dirty, however, openai and anthropic still can’t win.

My thoughts exactly. I believe that in this space there is far too much development time and energy is going into maintaining channels that change on a whim of their publishers. I have been casually observing development commits and code review for all of the work that both Ironclaw and Openclaw have been doing with comm channels and it’s absolutely mind boggling how much work that goes in. I’ve developed a few core communication channels based on open protocols and all of these alone are enough work to maintain and improve as it is. Developing new ones all by myself is not a priority at the moment. I want to focus on things I deem to be more important for agents at this time. I’m not opposed to adding more options in the future either. One of my plans is adding two way voice communication in the future and if that seems feasible with the existing XMPP bridge, I will go that route. Otherwise, I’ll look into other options for this.

I’ve actually been really trying to work on documentation lately, as well as get a lot of the old outdated docs removed/archived. I am still not 100% done but I’ve made a lot of progress with that, especially in this past week. Feel free to take another look at the in repo documentation for now. I’ll also need to further update the main website at some point… there’s at least two broken links and I’d like to add at least one additional page later.