hmmm @trq212 @bcherny @ClaudeDevs how did I hit my 5-hour limit on my 5x plan in like 5 minutes? I have only hit my 5-hour limit on my 20x plan once. My 5x plan constantly hits 5-hour limits but this seems like a bug...?

Most memorable parts of this interview with @bcherny : - Boris casually mention that he has "thousands" of agents running during the night... - Boris saying he almost exclusively uses Claude Code on the phone now - Coding will become the new literacy, just like reading and writing

AI is coming for taste and judgment Claude Code's @bcherny: "We have this tendency to think....here's a thing the agent can't do yet, this must be a thing it can never do. But the rate of progress is so quick that something like taste, the agent will be able to do quite soon" co-lead @_catwu says you can see the jump in the models directly. The front-end apps Claude builds have gotten visibly nicer between Sonnet 3.5 and Opus 4.7, and you no longer need to handhold the agent.

Everyone after Opus 5.5 drops from @AnthropicAI Honestly, this is the first frontier model I think is actually seriously good. The way it thinks is next level, whatever @bcherny and the team are feeding it, fair play.

My YC Startup School 2026 recap video. Thank you again, @ycombinator, for bringing so many ambitious and thoughtful people together. Built entirely by Opus 5 from my own photos and recordings. (Thanks to @bcherny !!!)