Press Space to continue
Finding signal on Twitter is more difficult than it used to be. We curate the best tweets on topics like AI, startups, and product development every weekday so you can focus on what matters.
Press Space to continue
Press Space to continue
we took security extremely seriously in building muse. the thing that took the longest before we felt comfortable releasing was security and safety, because we knew the only way people would use it is if they trusted it. read more: https://security.muse.ai
One thing I really like about Muse: I trust its Secrets Store Every time you use an agentic app, you have to make a call. Do you trust how it stores and uses secrets? Passwords, keys, credentials, etc. In the early days of vibe coding, secrets were often stored … literally in plain text by agents. And leaked all across the web. Not great. Today, I just … don’t know. Will some hot startup have a security breach and leak my secrets? Of course. It still happens all the time. Every day. You almost have to assume any startup you give your credentials and secrets to will have a breach. And agents just need … a lot of them to work well. A lot of secrets. Maybe it’s ironic I trust “Facebook” more than 99% of apps with my secrets. But the app seems to have made it part of its core from Day 1, to do it right I mostly trust Muse (for now at least) with my credentials. I’m making a gut call based on experience, but I think they’ve truly put in the work. In the AI Age, I mostly don’t truly most other apps with them. For that reason alone, I’ll probably end use doing more with Muse than other general agents.