Probably made more Bitcoin transactions than you
Joined November 2014
- Tweets 11,943
- Following 1,014
- Followers 1,381
- Likes 19,053
1,186 Photos and videos
Pinned Tweet
3 Nov 2025
Wild how like 99% of people who self identify as Bitcoiner disagree with the one premise Bitcoin is actually built on
3
1
14
1,357
@ClaudeDevs Only 116% of the 5 hour window to get things running. Might have a good 15 mins where I can get some work done before we're back to rate limits
1
77
Jun 5
Running 8 auto mode dev agents concurrently, honestly at the point where I can scale this up to maybe 50 or so
77
May 30
Definitely disagree. 4.8 is (slightly) superior, but you have to evolve with it.
It's more honest. Less avoidant. And workflows are really cool
Too bad they nerf the previous model to hype the next. The last week of a certain model before the nex is released, it's hardly usable
opus 4.5 > opus 4.6 > opus 4.8 > opus 4.7
what anthropic did after opus 4.5 should honestly be a case study in how to ruin momentum
112
May 26
We have this running as a poc with tax authorities and common accounting software integration, including per field disclosure and split payment using stablecoins.
The latter matters as it does at least stop carousel fraud as the seller never holds the tax part.
Triple-Entry Accounting Has Been Misunderstood open.substack.com/pub/singul…
1
6
503
May 26
These "third entry" timestamped audit trails with selective disclosure are abstracted and composable as state machines.
They can be implemented for any use case, such as digital product passports, micro platform compositions or any domain logic really.
1
3
100
May 26
We're currently running this with the Department of Justice for online fraud and the National Office for Identity Data for securing ID photograph audit trails, among others
1
4
101
May 25
4.8 coming soon
claude code monthly subscribers are being served a nerfed version of opus 4.7. i'm convinced now after using cursor on same model.
anyone serious about agentic software development should be on cursor right now.
cursor on opus 4.7 max consistently outperforms claude code on opus 4.7 max.
if it's the same model, why does one feel like the real thing and the other feel like a shit?
206
May 18
I solve this by looping Claude code with codex review against the spec.
Spec is in directories with pre commit hooks blocking changes and instructing Claude to run a separate MR.
By morning I simply have a couple of MRs clearly showing where implementation drifted from spec.
a prompt I've been using a lot recently:
implement <SPEC> and while you do, keep a running implementation-notes.html file (or markdown) with decisions you had to make weren't in the spec, things you had to change, tradeoffs you had to make or anything else I should know
1
211
May 6
Stop filming my house
1
142
Apr 28
People anchor data on BSV
The same chain can run a stateful business services that crosses every trust boundary. Citizens, governments, regulators, supervisors, enterprises, counterparties.
What runtime does that?
Apr 28
It is not a service runtime
What holds your domain's state? What replays the chain into a queryable view?
What turns a class with methods and queries into a deterministic, audit-grade, event-sourced service that survives schema evolution,delegation chains, and operator handover?
3
12
496
Apr 28
The open BSV stack today: a wallet that signs, an overlay that admits and routes by topic, a script template that locks data into spendable outputs, proofs that travel with the transaction...
A complete substrate. It moves coins. It anchors data. It proves inclusion.
Apr 27
Building the tools to onboard every enterprise and government on the BRC stack. Watch me
Should I open source it so you could too?
2
5
35
1,327
Apr 28
It is not a service runtime
What holds your domain's state? What replays the chain into a queryable view?
What turns a class with methods and queries into a deterministic, audit-grade, event-sourced service that survives schema evolution,delegation chains, and operator handover?
1
3
678
Apr 27
Building the tools to onboard every enterprise and government on the BRC stack. Watch me
Should I open source it so you could too?
7
7
42
3,369
Apr 25
Claude /loop on auto mode with codex code review iterating to a specific score is fucking powerful
2
4
230