Looking at the progress with DS4 project from Antirez and Colibri, are we probably going in the direction of having a stripe RAID of SSDs instead of RAM to get decent performance without losing a kidney to the RAM mafia? I really hope so.
The motivation that the USA entered WWII was not because they were generous, but because the 3rd Reich was effectively becoming a big European nation, so they had to do something to avoid it. A unified Europe is a thread to the USA and Russia and maybe somebody else too.
I made my own agent harness inspired by OpenClaw, but with internal group messaging between agents and memory sharing confined in agent groups. Plus Telegram integration with multiple agents in one channel using topics: https://bazilion.com/
I don't get how Ive is getting so much praise as a designer, after designing the worst iPhones ever and a Ferrari that looks like a Toyota Prius on steroids.
I understand the need for memory footprint in some situations, but what's the point of seeking performance for a software that mostly calls LLMs and waits?
I’m working on an ATS system that integrates LLMs for helping the recruiter in writing job descriptions, parsing CVs to Markdown, making summaries of CVs and suggest which ones match the best the job offers giving pluses and minus: https://beehive-ats.com/