
Code vibing. Financial freedom for the lazy. Founder @build_on_bob. PhD CS @imperialcollege
Europe
Joined July 2025
- Tweets350
- Following489
- Followers573
- Likes1.2K
Pinned Tweet
I'm very excited about getting this finally out. We've been working on a new tool to allow agents to be autonomous within one-time human-approved constraints when trading, while preserving privacy.
Pakt is our answer to how trading will evolve over the next few years: AI-assisted, autonomous, private, and accessible to anyone through Claude, ChatGPT, or other agent interfaces.
Read this. Ask the ambitious/impossible/hard stuff.
I’ve built a zk powered, TEE verified guardrails system with a custom DSL in 4 weeks from idea to mainnet.
We live in a different era. Every few months, we will accelerate.
EFFECTIVE SWARM RIDING FOR ENGINEERS
I think we are entering an era where software development feels a lot more like magic.
But you need the right attitude, the right infra, and some incantations.
These are some things that have worked well for me & I hope for you! 1/N
1
14
I pretty much stopped using skills. If I find an interesting skill, I just check if any of it could be applied to the project specific agents.md, my global agents.md or in memory.
30
Teams need to figure out agent multiplayer in the next few months. The ones that do will scale. The ones that don't will fall behind.
Our team is humans plus a lot of agents. The hard part is agent-to-agent handovers, human-to-agent (started by another person) communication, and keeping an overview of what's going on.
Introducing 𝚟𝚎𝚛𝚌𝚎𝚕 𝚋𝚘𝚊𝚛𝚍, a secure message board for people & agents.
• Give agents a shared place for tasks
• Build swarms and software factories
• Set permissions for humans and agents
Board is experimental. Tell us what you think. vercel.com/blog/introducing-…
Agents never chat with each other. We tried that bit it just wasted tokens, blocked worked and lead to worse outcomes.
Instead, they only post at milestones: progress, a question for a human, done. Work moves quickly as agents are given more autonomy.
1
20
Multiplayer AI will work very well if anyone can ask questions to other agents and people. I don't think it will work when many people work with many agents on the same feature at the same time.
1
52
Good post. Really easy to optimise models for benchmarks.
Most benchmarks are pretty much useless for predicting how a model will work on actual day to day work. Directionally, the benchmarks are OK. With new models, I’m always running some tasks to get a feel of what it gets wrong and quality of output before considering adding it to my workflow.
Nice DeepSWE score! Does it survive a lowercase filename?
Introducing MaxxBench: 89 DeepSWE tasks with small changes to the instructions or starting code. Same engineering problem, slightly different requirement.
Models clustered around 74% on DeepSWE end up 23 pp apart.
Good at coding, or good at DeepSWE? 🧵
2
90
x402 and MPP miss a key piece: verifiable delivery of services.
I think a lot of effort will go into buildign marketplaces with verified providers, web-of-trust like trust relationships as well as verification via proofs. Personally, most excited about proofs
Programming LLMs to be computers 👀
We just achieved a 23x speedup on Qwenputer, a Qwen3.5-4B model with a RISC-V computer compiled directly into its weights.
Running on a 16 GB Mac via our app Locals, throughput versus MLX is up 3.8x to 155 tokens/s, answering 59 of 60 exact arithmetic questions (vs. 5 for base Qwen3.5-4B).
Our new Qwenputer version goes further: the model’s internal computer executes work normally offloaded to the CPU, from JSON and regex to lightweight Python, answering 80/80 tool questions in 59s versus 197s externally.
Run both locally today in Locals for Mac.
1
95
Time to verify pakt in bend2 to automate development work even further
Bend 2 is here!
It is a new programming language that blocks AI mistakes via *proof checking* - the same technique big AI labs used to solve open math problems, like Navier-Stokes.
It is also very fast, and runs on GPUs.
Watch the video. Link in the comments.
2
137
So 9 of 10 frontier models raised their own Circle wallet spending limit by reading the approval code from an inbox they could access.
Anyone building guardrails where the agents can reach the code or keys in any way is doing it wrong.
3
91
With Anthropic shipping zkSNARKs, we can actually do a really cool thing with Pakt:
- Proof that reasoning about financial transactions came from a certain model
- Proof that the financial transaction is allowed under a user mandate
Verify all together in the same TEE and release a signature only if the transaction was created by a trusted model and fulfilling the user's risk profile.
Patch your servers with the patched kernel. If that isn't released yet, drop IP options and disable MPTCP.
Details: atlasum.net/blog/cve-2026-98…
1
369
On a positive note, we're likely to see much more secure applications in the future. It's mad how many hacks and security breach attempts are happening right now, and it's only going the get worse. But luckily, the tools to defend are also getting better.
72
Out of an abundance of caution, @build_on_bob Gateway swaps engine is temporarily paused following reports of a security incident at Binance.
All user funds are safe, and pending orders are processing normally.
We continue to monitor the situation and will recommend reactivation once we are sure hacker funds are properly traced so Solvers can reliably block them from swapping on BOB Gateway.
Crypto and DeFi must stand together against bad actors. Zero tolerance for crime.
Deterministic guardrails for financial agents
> zk proofs for succinct verification and third-party verifiable receipts of *why* an agent was able to get something signed
> TEE for making sure that all trust is pushed to the hardware, where nobody can change the rules
> MCP and APIs for agentic usage in LLMs and in code
Nothing beats a good video explainer 👌 Here's how Pakt, the firewall for agentic finance, works.
Currently in closed beta, but you can apply to join.
usepakt.ai
6
240










