Shipping products with agents. Lead dev @buildersatscale. All-in on DeFi and AI.
Bristol, UK
Joined March 2012
- Tweets4.4K
- Following976
- Followers2.1K
- Likes7.7K
Pinned Tweet
I'm leading Scale on @base again.
New vision. Building at Scale.
The @pzeroai build taught us what agentic systems take. We are not keeping that to ourselves.
It goes in a private builders lounge in the Scale Discord. Deep insights. Group calls. One to ones. Private repo access. Grok bot strategies.
I want the next builders on Base in that lounge.
We lead the agentic era from there.
Most DEX tokens pay you to sit in a pool.
We did that for a long time. It does not give anyone a reason to care about the venue. It gives them a reason to leave when the emissions lose value.
What we are building now is the other way around. You buy SCALE to get through the door. Behind it is a gated Discord on a live venue. It teaches you how to build with agents. We help you run your protocol agentically.
Lockers feel this too. Five people buying that door eat a week of emissions. That is demand the farm never created.
Building at Scale. That is the whole sentence.
7,000 SCALE. That is the door.
Looks like state machines are back on the menu, boys!
What is an implicit state machine?
Your apps are full of state machines, which is the logic that says "when we're in this state, and this event happens, now we're in this state" (given, when, then).
Sometimes those state machines are clearly mapped out (switch statements, reducers, tables/maps, libraries like XState for the more complex ones, etc.) and the logic is explicitly enumerable.
And sometimes it's not. The ad-hoc logic is spread all over the place. That's how developers typically code, and that's how agents typically vibe-code (they learned from you). Those are implicit state machines.
What's wrong with implicit state machines? It's not clear what state transitions are possible, so you might have "allowed" states that should have been impossible without knowing it. Agents make the same mistakes.
You can get all tests passing and your code review agents (even the well-funded ones) can say "LGTM" and you can *still* have very bad bugs because an implicit state machine allowed unexpected or illegal behavior. (Remember the Apple FaceTime bug?)
So yeah, making your app logic explicit is important.
3
281
If your are using agents, being productive and happy with your pace then ignore the noise.
Shipping software beats jumping on the latest hype train.
83
We used to avoid forking to avoid taking on 3rd party responsibility. Now we want to build everything ourselves, has anyone else felt this shift?
1
129
Read between the lines.. Scale V2 is a different beast. New tech, additional contracts, new services, 100x the data.
We have begun our new V2 infra migration on beta, this bring seventeen new services online (yes, this means new features soon).
Please only use scale.farm during this time as we have over 60GB of data to sync across multiple services and contracts.
Thanks
90
Nothing is permanent except change, it's the only universal constant. Short version: adapt or die.
very weird thing happening rn
technical people are sad, they think their skills are now useless
non-technical people are desperately wishing they were more technical so they could use agents better
1
149
It's genuinely wild how many highly respected devs are coming back to state machines in the agentic world.
@DavidKPiano was right all along.
1
104
I am all in on this. I don't people realize how much software interactions are about to change. State machines for flows and generative UI to express them. Massive.
Extremely bullish on generative UI.
Right now software is mostly organized around features, but generative UI would let you organize around intents.
If you're experimenting in this space pls reach out! Here's a flow we're testing out
1
7
267
I've had a similar experience. When a model is released it seems way more capable of making good decisions but deteriorates the more it is used (by all of us).
A model that was working well with solid methods starts to go off the rails.
For those who have been following my takes on AI progress, it may come as no surprise that I agree with @nostalgebraist
1
83
I don't buy the goal of software factories with no humans in the loop. Agents make it cheap to take a bad design much further. I still want someone close enough to the code to notice when we're building the wrong thing, even when everything works.
1
2
158
We are rebuilding SCALE in mutliple ways from the ground up
- data
- defi
- agents
Our new indexer tech is up to 900x faster than a subgraph with fresh restarts in under 6 minutes over millions of transactions. (About 100x faster than envio too)
We will soon expose this tech on beta and some of the features that this unlocks. We have peered deep inside competitors internals and have multiple strategies coming to compete.
Consider this your warning to pay attention over the next six months.
Execution matters. ⚡
We just added 1 WETH + matching $SCALE to give the pool real depth.
This means:
• Minimizing slippage on swaps
• Tighter spreads across the board
• A smoother experience as volume grows
Laying solid foundations while we keep shipping the rest of the v2 product. 🤝
2
63
I haven't seen a single complaint on x about the new @cursor_ai unify update. Has anyone done it? is it true you lose access to the `other models` and they are now PAYG API on top and only grok is included, the docs are super sketchy..
cursor.com/docs/account/pric…
I am hoping that I am misreading the docs.
1
1
144
With billing moving from cursor.com to grok.com it looks like we may lose the cursor brand and it becomes grok.
We knew the party couldn't run for ever but I hoped we would get longer tbh.
1
1
27