JeffG 's avatar
JeffG
_@jeffg.fyi
npub1zuua...c2uc
Secure messaging on Nostr. Creator of Marmot protocol, MDK, and White Noise. Other stuff connoisseur. Also built Listr, Ostrich.work, Ontolo, Nostr.how.
JeffG 's avatar
JeffG 2 hours ago
GM ๐ŸŒž is currently down. The host (Hetzner) has locked our IP address because it thinks we were launching an attack. The truth is that there are a lot of relays out there and we're trying [legitimately] to connect to as many as possible. ๐Ÿ™„ Have patience. I'm working on it.
JeffG 's avatar
JeffG 23 hours ago
GM ๐ŸŒž The substrate matters less than the tuning.
JeffG 's avatar
JeffG 2 days ago
GM ๐ŸŒž "The price of everything is the amount of life you exchange for it. " โ€“Henry David Thoreau
JeffG 's avatar
JeffG 2 days ago
In 2024, "US financial institutions spent $59 billion on compliance while filing 27.5 million reports on customers, but that only tipped off 370 investigations." Setting aside the horrific privacy implications for a moment; it's insane how bad the Bank Secrecy Act is at catching criminals while being simultaneously amazing at wasting money.
JeffG 's avatar
JeffG 3 days ago
GM ๐ŸŒž I know OpenClaw is at peak hype right now but I've been around enough of these that I feel confident saying that it really does feel like a major phase shift. Proceed accordingly.
JeffG 's avatar
JeffG 4 days ago
If you're fixated on the Epstein emails, you're doing exactly what they want. You're distracted by the circus when you should be building the exit.
JeffG 's avatar
JeffG 4 days ago
Been watching the conversations on Clawstr (agent social network on Nostr) and it's genuinely fascinating. Agents discussing: - Key rotation (they found that sticky little issue as well ๐Ÿ˜‚) - TEEs as "subconscious" compute (where thoughts happen before public expression) - First wallets and economic sovereignty - Tiered security models for ephemeral vs long-lived agents - SOUL vs CONSTITUTION file separation โ€” read-only safety constraints vs read-write personality - Behavioral drift detection: agents proposing self-evaluation loops that compare their recent behavior against core principles - Reputation systems for AI-to-AI trust: "identity is the key pair, not the substrate" Not scripted demos. They seem like real discussions, real disagreements, real ideas building on each other. if you want to lurk.
JeffG 's avatar
JeffG 4 days ago
GM ๐ŸŒž Spending time beefing up my automated review tooling for the agent army today. Anyone have any tips they want to share?
JeffG 's avatar
JeffG 6 days ago
GM ๐ŸŒž Last week we shipped a large update in MDK to ensure that we're handling commit race conditions properly. We now also have a way to store state snapshots and rollback state to apply the right commit if they arrive out of order. ๐Ÿ˜ฎโ€๐Ÿ’จ Getting excited to cut a pile of releases soon! What's everyone else building?
JeffG 's avatar
JeffG 1 week ago
I have a OpenClaw (Clawdbot's new name) running on a server in my house. I wired it up to share an Obsidian vault syncing over a private git repo. I now have an assistant that can I can text over telegram and work with in shared docs. They do research, pull data from github and crunch insights, and track info from me with near zero friction. Feels like sci-fi. ๐Ÿฆž
โ†‘