So I don’t have much evidence on the quality of the output of Opus 5.5 yet. It does seem like it’s fixed the disaster of yappy and overthinking Opus 5. The one thing that I have noticed is that it’s light years faster than any previous Opus model. Anyone else seeing that too?

@Jeff Van Leenen put in the work and got this weeks leaderboard! Now here's the thing, he already has Lifetime VIP, so his chosen friend gets the reward instead! ⏰ The 7-day clock resets. Next Monday someone new takes the top spot. 🎯 How it works: - 📝 Post things worth reading - 💬 Help people in the comments - 🛠️ Share what you're building, what's working, what's breaking - ❤️ Engage with what others are putting out there The leaderboard tracks all of it. 🎁 The prize, depending on where you're at: 🆓 Free member? You get lifetime Premium, free ⭐ Already Premium? We convert your Premium so you stop paying 👑 Already VIP? We convert your VIP so you stop paying Either way, you stop paying.

It’s taken me a while to get around to get properly started with this, but after yet another session where I wanted to punch myself in the face after the model just ran off and did whatever it wants, I’ve bitten the bullet and am dealing with my seven month old second brain system. My second brain system works really well generally so I haven’t needed to take on Hermes or anything but I just wanted to surface where I could choose which process I wanted to run when (in addition to the scheduled ones). So I’m creating a Slack app where I can press a button to run a process on demand (ie runs a folder). I’m really happy so far, working kn something simple. For my film club, when I programme a film, I just press the button, tell it which film, then it goes to The Movie Database and pulls all the images and logos into a folder on my laptop so I can do my human pass on which ones I want to use. Now that works, I can build up all my other processes. It may have taken me a while to got into it, but I’m on my way :)It’s taken me a while to get around to get properly started with this, but after yet another session where I wanted to punch myself in the face after the model just ran off and did whatever it wants, I’ve bitten the bullet and am dealing with my seven month old second brain system. My second brain system works really well generally so I haven’t needed to take on Hermes or anything but I just wanted to surface where I could choose which process I wanted to run when (in addition to the scheduled ones). So I’m creating a Slack app where I can press a button to run a process on demand (ie runs a folder). I’m really happy so far, working kn something simple. For my film club, when I programme a film, I just press the button, tell it which film, then it goes to The Movie Database and pulls all the images and logos into a folder on my laptop so I can do my human pass on which ones I want to use. Now that works, I can build up all my other processes. It may have taken me a while to got into it, but I’m on my way :)

Anyone knows if there is a way to clean my gmail account , I have been using it since forever and have important stuff linked with it .

I've got a project running locally: ICM workspace, Claude CLI as the coding/execution agent. Local tests are solid and I've already demoed progress to the client. Now I need to take it to production, and I want to get the deployment right before I bolt on a frontend, databases, logging, and alerts. My current plan (Azure): - Container App running the FastAPI backend + Claude CLI - Azure Files mounted as the working folder for the agent's session/workspace - Managed Identity for auth (no stored secrets) - Container Registry for the image - Foundry for the base LLM Has anyone deployed something like this in production? Not looking to over-engineer this, just want the deployment shape to be sound before I layer the rest of the product on top.