ok first impressions: i unironically think Jack might kill Slack with this
still pretty technical to set up + very early, but the basic idea feels correct:
> right now its a total nightmare for agents to understand what’s happening across Slack, GitHub + a dozen tools
> buzz puts that context, conversation + work history in one place
> add an agent to any old channel and it can instantly read everything that happened
> every agent gets identity + permissions, with every action signed so you know who did what
> each new feature gets a channel where the conversation, code, reviews + decisions stay together
> open source + self-hosted, so your company controls its data, infrastructure + keys
i think the endgame here is basically one home screen for the entire company.
talk to your team, hand work to agents, review what they did, approve it and ship it all in the same place
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.
The token cost to build a production feature is now lower than the meeting cost to discuss building that feature.
Let me rephrase.
It is literally cheaper to build the thing and see if it works than to have a 30 minute planning meeting about whether you should build it.
It’s wild when you think about it.
This completely inverts how you should run a software organization. The planning layer becomes the bottleneck because the building layer is essentially free. The cost of code has dropped to essentially 0.
The rational response is to eliminate planning for anything that can be tested empirically. Don’t debate whether a feature will work.
Just build it in 2 hours, measure it with a group of customers, and then decide to kill or keep it.
I saw a startup operating this way and their build velocity is up 20x. Decision quality is up because every decision is informed by a real prototype, not a slide deck and an expensive meeting.
We went from “move fast and break things” to “move fast and build everything.”
The planning industrial complex is dead.
Thank god.
Visual reminder that Quincy Wilson is a 16-year-old running (and thriving) against grown-ass men in the 400 meters at the Olympic Trials.
Terrific photo by @007TrackFan
54-hole trends at #TheMasters
*27 straight winners have been within 4 shots
*28 of the last 33 winners were in the final group
*Only 1 winner has ever been outside the top-10 (Art Wall in 1959, T-13)