congratulations team Conductor!!!
If you are looking for a new cloud agent setup, try brahma.sh. Add its MCP server (brahma.sh/mcp) to your agent and ask it to migrate you over.
DM me, and get free sandbox usage (BYOK for llms) till EOY
I am very excited to share that Conductor is joining Meta!
We have some big, crazy plans for the next interface. If you liked Conductor, you’re gonna love what’s coming.
We’re super excited to work with @natfriedman and @alexandr_wang at MSL to build it. They’ve been on an absolute tear, and I’m convinced MSL has the highest talent density of all the labs.
A huge thank you to our earliest believers @aaron_epstein, @ilyasu, and @nabeel. And to everyone here who tried Conductor, sent us feedback, and prompt requests - you made this so much fun. Thank you ❤️🚂
Choo choo!
Replying to @poteto
@poteto here's a bug report you asked for.
- in grokbot -> plugins, connectors opened datadog connector once and now every connector shows datadog's mcp URL.
Now i understand why my monitoring bills are so highh!!! lolll
Jk.. lets keep shipping! aaanndd testing/verifying
the grok bot team is shipping at a incredible pace! please keep sending us your feedback and bug reports, we will continue working hard on improving and polishing grok bot so it's the best assistant and employee you can hire
6
205
Dang again !!! fable 5.1 said nothing was running. i showed it the evidence. then: "you're right, and i was wrong."
favorite model. still have to check its work everytime now!
1
119
I have a very smart PA now to handle my emails!
Whatta joy.
nope. its not as simple as connecting hermes/claw to the gmail api.
9
819
Trying something a little crazy this weekend:
We’re giving away a few thousand dollars worth of free test generation on Diffie . ai
No signup.
No credit card.
No catch.
Go to our website (link in thread) & describe what you want tested.
Or drop your web app link in the thread and we’ll reply with your test.
If broken down enough, Claude Code (running dangerously) + Opus 4.5 can do any task.
An orchestrator that breaks down tasks. A Validator agent that verifies. And a crew of mini agents doing those tasks.. This looks like the next step
1
169
me in may -> llm write code calling mcps in sandbox
@Cloudflare code mode in september
@AnthropicAI code execution with mcps in november
just have to get chatsiva.com reliable and launched!
Replying to @codeanand
One solution is have the llm to write code calling these two mcps. And that code beings executed in a interpreter. which is what i am building at chatsiva.com
153
Claude Code is recommending that shift from GPT 4.1 to Claude in one of the apps I am building.
I wonder if it was prompted to recommend itself. Or it learnt that Claude is better for this task. hmm
1
110
GEO is going to be way different than SEO.
No more keyword stuffing etc. GPTs gets to the truth by cross checking.
1
2
130
One measure of AI getting better is the sales of books especially (self help) trending down
I see no point in reading 200 pages. when I can ask AI to do that job for me.
Why would I read "Never split the difference" when I can ask ai to negotiate for me
1
3
266
Here is a html page that has Typescript examples of Complex vs Simple
gistpreview.github.io/?cb77d…
gist.github.com/sanandnaraya…
1
226
























