Remember when @posthog called their shot 2 yrs ago on $100M ARR by 2026 and people thought their 7% MoM growth assumption was crazy/naive?
Just checked and…they’re on track!
Can’t become a generational company without generational ambition 🔥
@brian_lovin@ridd_design "I'm doing my best to stay open-minded+curious, study new tools and patterns every day, avoid tribalism about apps and models, and focus my attention on making the highest quality software possible." 🎯
Introducing Latent Briefing, a way for agents to quickly share their relevant memory directly. Result: 31% fewer tokens used, same accuracy.
Multi-agent systems are powerful, but can be wildly inefficient. They pass context as tokens, so costs explode and signal gets lost. We built an algorithm that allows agents to communicate KV cache to KV cache.
@nikitabier feature idea: allow users to search for a post that they've seen in the past. Am constantly reminded of posts I've read, but never bookmarked (usually in the last week). Would probably make the time I spend feel even more valuable if my timeline had memory
OpenAI partnering w Cerebras is the most underrated thing to happen this year. Cerebras is the fastest inference provider in history. Like 50-100x faster. Every response is fucking *instant*.
Now imagine running Codex CLI with a SOTA coding model at 5K tokens/sec...
https://t.co/QOypmpo7Xp
Appreciate the grounded POV!
Seems like the main reason Claude Cowork isn’t as useful is that knowledge work isn’t local like your codebase is. A lot of jobs live in the browser/cloud and requires MCP/extra gymnastics to get the right context. Just isn’t as elegant of an experience unless your work context is local