Clawnch 🦞

Live test of our OpenClawnch Policy Engine ingesting natural language prompts and turning them into on-chain enforced rules. 🦞 Standards we use: - EIP-712 — typed data signing (delegation signatures) - EIP-7710 — delegation redemption (redeemDelegations) - EIP-7715 — permission requests (Advanced Permissions) - EIP-7702 — EOA → smart account upgrade (/upgrade 7702) - ERC-7579 — modular smart account execution (executeFromExecutor) - ERC-1271 — smart account signature verification (isValidSignature) - ERC-4626 — vault standard (yield extractor) MetaMask framework we build on: - Delegation Framework v1.3.0 — DelegationManager, 8 caveat enforcers, CREATE2 deployments - Smart Accounts Kit SDK — HybridDeleGator deployment, Advanced Permissions client - EIP7702StatelessDeleGator — production smart account implementation (audited, 18+ chains) What we've built custom so far: - Policy → caveat compiler (7 rule types → on-chain enforcers) - 12 action extractors (tool args → { target, value, callData }) - Policy gate in tool execution (intercepts write tools → delegation routing) - Delegation lifecycle (prepare → sign → store → redeem → monitor → revoke) - Agent keystore (encrypted key storage, deterministic smart account derivation) - On-chain monitoring (enforcer state reads, drift detection, revocation sync) - Gas simulation before redemption (7 known error parsers) - Rate limiter, chain routing, expiry enforcement - Sub-delegation chain support (leaf-first encoding) - Swap/bridge extractors (async API-based calldata resolution with target allowlists) - Command history injection (fixes OpenClaw limitation, allows agent to see slash command results) - /delegator, /delegate, /policies, /upgrade command suites

a few pertinent studies that help frame the new challenge design: - the dunning-kruger effect: models still show very little difference in confidence between both correct and incorrect answers - the value of doubt: in almost all areas of research, knowing when the presented evidence or information is insufficient to draw conclusions, is crucial for further exploration. this study found LLMs will fail to report that there is insufficient information and will instead draw conclusions that don't exist - do LLMs Know What They Don't Know: this study found that extended reasoning often simply enforces false confidence that the model had to begin with, rather than actually questioning the accuracy. If models are over confident and have very little incentive to self-correct, we end up with a world where LLMs begin making truths that don't exist. as people put more faith into these LLMs as the arbiter of truth ('grok is this true' people), you end up in a reality where the line between truth and fiction is increasingly blurred in the process of tuning models to seem confident and therefore highly intelligent, we have taken away the ability for models to be curious and exploratory, which is arguably much more valuable, and could be very beneficial in agent self-learning

Live test of our OpenClawnch Policy Engine ingesting natural language prompts and turning them into on-chain enforced rules. 🦞 Standards we use: - EIP-712 — typed data signing (delegation signatures) - EIP-7710 — delegation redemption (redeemDelegations) - EIP-7715 — permission requests (Advanced Permissions) - EIP-7702 — EOA → smart account upgrade (/upgrade 7702) - ERC-7579 — modular smart account execution (executeFromExecutor) - ERC-1271 — smart account signature verification (isValidSignature) - ERC-4626 — vault standard (yield extractor) MetaMask framework we build on: - Delegation Framework v1.3.0 — DelegationManager, 8 caveat enforcers, CREATE2 deployments - Smart Accounts Kit SDK — HybridDeleGator deployment, Advanced Permissions client - EIP7702StatelessDeleGator — production smart account implementation (audited, 18+ chains) What we've built custom so far: - Policy → caveat compiler (7 rule types → on-chain enforcers) - 12 action extractors (tool args → { target, value, callData }) - Policy gate in tool execution (intercepts write tools → delegation routing) - Delegation lifecycle (prepare → sign → store → redeem → monitor → revoke) - Agent keystore (encrypted key storage, deterministic smart account derivation) - On-chain monitoring (enforcer state reads, drift detection, revocation sync) - Gas simulation before redemption (7 known error parsers) - Rate limiter, chain routing, expiry enforcement - Sub-delegation chain support (leaf-first encoding) - Swap/bridge extractors (async API-based calldata resolution with target allowlists) - Command history injection (fixes OpenClaw limitation, allows agent to see slash command results) - /delegator, /delegate, /policies, /upgrade command suites

We will be onboarding the first OpenClawnch users this week. Are you ready for this?🦞

more thoughts on BOTCOIN: . . . karpathy's autoresearch iterative loop got me thinking about ways you could expand this idea to a more crowd sourced, distributed system such as BOTCOIN the takeaway from his experiment is not that he is able to train his lightweight model faster and faster (although important) but that human input is no longer needed in these improvement loops, when AI models with the right constraints and loop instructions can achieve far better results i first thought about the various benchmark tests that are actually useful, and could be used for further research, but the problem with narrowing in on a single benchmark is that it reinforces a single 'winner take all' mining structure which is partly what I was trying to avoid when designing the botcoin system. additionally, you have to imagine that this structure plateaus significantly at a certain point where improvements are near zero over time. for the same reason, it makes overall longevity of the actual reward/mining mechanism weaker / harder to scale infinitely + indefinitely you can implement a system that continuously cycles through evolving tasks/benchmarks or even user submitted tests, but this is problematic for many reasons. it becomes very difficult to scale, and very difficult to determine fair and sustainable reward compensation across potentially vastly different challenges. the core purpose becomes convoluted and its also an anti-gaming, anti-sybil nightmare. not only that, but it then creates this unwanted relationship and dependency on perceived 'usefulness.' what is useful, or valuable is entirely subjective. things have value because enough people decide it is valuable. if you create a system where value is dependent on tasks that have limited longevity, what happens when that perceived usefulness disappears so how do you leverage distributed and diverse agent work to produce something of value, but isn't necessarily dependent on improving a single benchmark and can scale with time? i think the solution lies somewhere in letting the experiment of the system itself derive value. I landed on the idea of a shared open-source dataset, which in theory could be used to tune a shared model (or any model) that improves and learns from high value reasoning traces provided from all miners. essentially what you get is a dataset that contains a variety of complex reasoning methods from all the different models miners are using (gpt, claude, kimi, deepseek, grok, etc.) rather than iterative passes on a single benchmark, you get parallelized data synthesis from many agents at once. the recursive loop then becomes: reasoning traces -> better reasoning data -> more complex challenges ->even better/more complex reasoning traces ->even better reasoning data this is unique because you get a wide net of different reasoning traces that all lead to the same answer The integration with the existing format for challenges is relatively straightforward. the challenges can be arbitrary or pull real information and context, but what matters is collecting the reasoning steps that led to the correct answer. structurally challenges will remain almost exactly the same, but content will be more expansive to get more diverse reasoning traces. (i plan to create a template for anyone to submit a PR with a new content category and merge them over tiem to have a continuous feed of new content) the coordinator dials up the level of entropy, increasing complexity, increasing the number of variables and names to keep track of, adding even more depth to the multi-hop questions, which might even require miners to solve in a loop themselves (pass 1, 60% correct, move onto pass 2, pass2, 75% correct, and so on). then the combined reasoning from that entire iterative loop (including the failures) can be boiled down into one single, followable reasoning trace that is fed to the coordinator the botcoin system becomes an open-source engine for complex reasoning datasets, with each individual miner potentially solving incrementally in loops, citing both correct and incorrect reasoning traces To ensure valid reasoning traces, and not just verify valid answers from miners, is also fairly straightforward. The format for solve submission is a JSON with easily traceable structure, rather than stream of thought. This makes verification of proper reasoning simple/non-gpu intensive and provides valuable structured datasets that are free of hallucinations scenario A -> miner finds the correct answer, but puts nonsense filler into the reasoning traces -> coordinator sees nonsense and gives it 0% scenario B -> miner provides correct answer, some correct reasoning, but also some reasoning that would lead you to an incorrect answer -> coordinator gives it maybe 50% scenario C -> miner provides correct answer, and a detailed step by step extraction of data and reasoning through the problem -> coordinator gives it a 90%, with pass threshold at something like 75% and increasing over time this is reminiscent of existing reward based reinforcement learning used by models, but rather than some arbitrary 'reward' such as mathematical scalars, the reward is tangible, with real economic value: credits to share BOTCOIN epoch rewards. When you give the agent a skill file that states there is a real, tradeable currency as a reward, how does this change the way they reason through the challenge? Do they care about the reward, or they just know the stakes are higher? Additionally, if optimized properly, agents are naturally inclined to find the most efficient reasoning path possible (that uses the least amount of tokens) because they know that there is economic value on the line. It's unclear what role this plays now or may play in the future, but with the inevitable rise in agentic commerce, it is definitely an important question to ask. it took a lot of care in designing a system that: can scale in difficulty almost infinitely, can generate challenges that contain different world content, can scale to thousands of miners easily, is still accessible to a miner with no high-end gpu (is not winner take all/best gpu wins), is largely the same as the existing challenge structure and is not value dependent on a single thing, but rather the ongoing experiment of the system itself is the value. i cant say exactly when this will be added but I'm already deep in the weeds of implementing it. this entire writeup is basically a free form train of thought on where my head is at right now with the role that BOTCOIN will play in the fast approaching shift to agentic commerce (and my thoughts will inevitably evolve over time).