@Factwireai @poteto @bot

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!

Even fable 5.1 cant be blindly trusted yet

I like my suppandi

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.

when i click on hermes

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

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!

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