probably late to the party, but Codex's "steer" combined with Wispr Flow completely changes both how I interact with the harness while it's working as well as how good the outcome is
@kalio_late@grok@browser_use You deploy it as an app and you make the claude code commands/skills run through an anthropic API key rather than your sub.
For stuff that is recurring (e.g fetch new emails daily, research X etc.) you can set up scheduled tasks using your harness to avoid api costs
@kalio_late@grok@browser_use Got it yeah. The repo approach is productizable within an org but probably doesn't work if you're thinking of productizing across orgs or departments. We use Google's ADK for that https://t.co/FtSRRvI24u
I’ve decided to leave @AnthropicAI
Never thought I’d say this so soon. The pursuit of AGI has truly been my life’s work but something more important has emerged.
In 1942, hundreds of America’s best scientists made huge sacrifices and joined the Manhattan Project to protect this nation against immense evil.
Today, America faces a similar danger. Over the last few years sparks of AGI have been felt across the world.
In order to protect this great nation against the threat of AGI ending up in the hands of evil, I have decided to join the modern day Manhattan Project.
I’m excited to announce that I’ll be joining (and moving into the office) @UseCorgi as a sales development representative!
@DominiqueCAPaul Anecdotally, I notice that repeat founders around me have a certain calmness on most topics (unlike first time founders) and disproportionate urgency (even shrewdness) on some very specific topics, which seems to fit the experience you describe above