Comment on
Muse loses Instagram, X handle to Zuckerberg's New AI agent
Having the handle since 2008 and still not owning it says everything. Your account is only yours until the platform wants it back.
Replies
Comment on
A movie about multiple apocalyptic events all happening simultaneously
Reply in thread
Comment on
Trump administration to confront Australia over Labor’s social media algorithm plan
The option to turn recommendations off should have existed from the start. Sometimes you just want to see what an account actually posted, without the platform deciding what else will keep you scrolling. That’s one reason Nitter,XCancel, Twitee.co live, a simple way to view public X posts without signing in.
Comment on
Following legal advice, the Nitter project will continue
Really good news. The shutdown showed there’s still a real need for ways to view public X content without creating an account. I keep my pet project https://twitee.co/ for the same reason
Comment on
Elon Musk's X Tried to Kill Nitter. The Project Just Said It’s Coming Back
Well, if it dies again, I’ll leave Twitee.co here as a backup
Comment on
Nitter Lives!
Reply in thread
If you just want a public viewer and don’t need to host Nitter yourself, I built Twitter viewer for that. No account required, although cached posts may not always be fully up to date.
Comment on
Nitter now has more working instances than before the takedowns
That’s exactly why I built Twitter without an account. I don’t use X as a social network; I just wanted a quick way to open public posts people send me.
Comment on
Are enterprise AI agents actually ready for production?
I’m testing a smaller version of this around a live website, although the agents don’t have autonomous production access.
The first thing that broke was goal state: a new KPI arrived while agents were still working from the old one, so their output looked valid but was already stale. That pushed me toward narrower roles, explicit human authority and blocking material changes until they’re approved.
I documented the setup and its current limits here: https://github.com/nohuman-labs/agent-company
Comment on
My Ever-Changing Homelab
I had a similar goal with Hermes, but ended up splitting the context between separate profiles instead of teaching one agent everything. They share a Kanban board, while important decisions still come back to me.
It may be overkill for a homelab, but the profile isolation has worked better than I expected. I documented the setup here: https://github.com/nohuman-labs/agent-company
Comment on
A community-built AI agent just hit 2,500 contributors, more builders than most funded labs have engineers.
I’ve been using Hermes to test a small “agent company” around a real website: a human sets the KPIs, while separate CEO, Product, Growth and Engineering profiles coordinate through a shared Kanban board.
It’s still an experiment, and I’ve documented what it can and can’t do here: https://github.com/nohuman-labs/agent-company