Update in the quest for affordable pstack
- Grok Bot installed @t3dotcodes and @chrisbbh's t3-pstack on its machine and signed into codex, cursor/grok and claude CLIs there.
- Tailscale to connect to grok's t3 so I can see what it's up to (grok vm blocks t3-connect). Now watching agents is close to being as nice as native cursor
Going to run a few small tasks on native cursor vs this setup to benchmark results
very weird thing happening rn
technical people are sad, they think their skills are now useless
non-technical people are desperately wishing they were more technical so they could use agents better
I threw all my @bot engineers in a room this week. Huge mistake. That room drove HALF my usage. Every "On it" and "Standing by" woke every bot. @poteto's dr eggbot diagnosed and updated the bots to talk 1:1 with my Engineering Manager and only use the room for blockers.
I threw all my @bot engineers in a room this week. Huge mistake. That room drove HALF my usage. Every "On it" and "Standing by" woke every bot. @poteto's dr eggbot diagnosed and updated the bots to talk 1:1 with my Engineering Manager and only use the room for blockers.
Build reliable agents for long-running tasks.
Loop Engineering with @LangChain Deep Agents: add loops that check output, trigger runs on events, and improve the harness from traces across runs. Taught by @sydneyrunkle and @EAGar123.
Enroll for free: https://t.co/VaNUdjXNkk
@wesbos We've got agents writing code around the clock, and humans are the bottleneck. When do we get a command center for what's waiting on us? What’s running, what broke, what needs me. Across repos. Also on my phone.