𝖕𝖗𝖔𝖔𝖋𝖔𝖋𝖙𝖔𝖒.𝖊𝖙𝖍 🪁

Finally publishing this 🧠 dump of a proposal: research.allo.capital/t/pan-archi-go…

@DennisonBertram @JinjingLiang @opencode Precisely my sentiments of CC/Codex/etc. The real enthusiast is rolling their own Pi harnesses 💪

@JinjingLiang @opencode I haven’t had much luck with it to be honest. I liked it for a hot minute but too many weird edge cases.

Unlimited Coding Cheat code: Codex GPT 5.5 runs a Deepseek powered Claude Code harness in a git worktree in tmux. Codex plans, Deep-Claude executes, 99% cheaper. 100% of the quality. Stop hitting your limits.

@DennisonBertram @claudeai Same thing happened when they were rolling out 4.6 over 4.5; 4.7 release is about to drop. OR x.com/proofoftom/sta…

While Opus' current lobotomization is likely due to the role out of the 4.7 series, I have an alternative theory: What if everyone using Caveman - combined with Claude's self improving shadow-RL - has just scrambled the neural network vectors back 10's of thousand of years in IQ

I'm running for US Congress. Seriously. Imagine common sense crypto policy and regulation, aligned with American dynamism. Check out our list of new Crypto Policies we will support, linked below. x.com/va_joe/status/…

what if ethereum strengthened local communities? ethereum localism starts with a simple premise: a global, permissionless network should still care about place governance/funding optimized for watersheds, in city councils, in food systems, in REAL local economies what if we could achieve open source coordination that's rooted in soil?

one simple trick to make claude write better tests (especially solidity): have it read the @MolochDAO testing guide I wrote 7 years ago thank me later 👹 github.com/MolochVentures…

Working on isolated Agent-as-a-Service @openclaw instances and building my clawrmy in the process 🦞

@auryn_macmillan @opencode I’m just using the subscription version as I don’t have the beast of a machine required to run full GLM 4.7 and have yet to play with the Flash variation locally but have run Qwen 3 coder locally using LM studio and was impressed by that some months ago. Requires some tuning 🤏

@proofoftom @opencode Oh awesome. Have you run it locally? What specs and what did the performance look like?

What are the best open source models for coding that could run acceptably with @opencode on a machine with 128GB of unified memory?

We need more DAOs - but different and better DAOs. The original drive to build Ethereum was heavily inspired by decentralized autonomous organizations: systems of code and rules that lived on decentralized networks that could manage resources and direct activity, more efficiently and more robustly than traditional governments and corporations could. Since then, the concept of DAOs has migrated to essentially referring to a treasury controlled by token holder voting - a design which "works", hence why it got copied so much, but a design which is inefficient, vulnerable to capture, and fails utterly at the goal of mitigating the weaknesses of human politics. As a result, many have become cynical about DAOs. But we need DAOs. * We need DAOs to create better oracles. Today, decentralized stablecoins, prediction markets, and other basic building blocks of defi are built on oracle designs that we are not satisfied with. If the oracle is token based, whales can manipulate the answer on a subjective issue and it becomes difficult to counteract them. Fundamentally, a token-based oracle cannot have a cost of attack higher than its market cap, which in turn means it cannot secure assets without extracting rent higher than the discount rate. And if the oracle uses human curation, then it's not very decentralized. The problem here is not greed. The problem is that we have bad oracle designs, we need better ones, and bootstrapping them is not just a technical problem but also a social problem. * We need DAOs for onchain dispute resolution, a necessary component of many types of more advanced smart contract use cases (eg. insurance). This is the same type of problem as price oracles, but even more subjective, and so even harder to get right. * We need DAOs to maintain lists. This includes: lists of applications known to be secure or not scams, lists of canonical interfaces, lists of token contract addresses, and much more. * We need DAOs to get projects off the ground quickly. If you have a group of people, who all want something done and are willing to contribute some funds (perhaps in exchange for benefits), then how do you manage this, especially if the task is too short-duration for legal entities to be worth it? * We need DAOs to do long-term project maintenance. If the original team of a project disappears, how can a community keep going, and how can new people coming in get the funding they need? One framework that I use to analyze this is "convex vs concave" from vitalik.eth.limo/general/2020/1… . If the DAO is solving a concave problem, then it is in an environment where, if faced with two possible courses of action, a compromise is better than a coin flip. Hence, you want systems that maximize robustness by averaging (or rather, medianing) in input from many sources, and protect against capture and financial attacks. If the DAO is solving a convex problem, then you want the ability to make decisive choices and follow through on them. In this case, leaders can be good, and the job of the decentralized process should be to keep the leaders in check. For all of this to work, we need to solve two problems: privacy, and decision fatigue. Without privacy, governance becomes a social game (see vitalik.eth.limo/general/2025/0… ). And if people have to make decisions every week, for the first month you see excited participation, but over time willingness to participate, and even to stay informed, declines. I see modern technology as opening the door to a renaissance here. Specifically: * ZK (and in some cases MPC/FHE, though these should be used only when ZK along cannot solve the problem) for privacy * AI to solve decision fatigue * Consensus-finding communication tools (like pol.is, but going further) AI must be used carefully: we must *not* put full-size deepseek (or worse, GPT 5.2) in charge of a DAO and call it a day. Rather, AI must be put in thoughtfully, as something that scales and enhances human intention and judgement, rather than replacing it. This could be done at DAO level (eg. see how deepfunding.org works), or at individual level (user-controlled local LLMs that vote on their behalf). It is important to think about the "DAO stack" as also including the communication layer, hence the need for forums and platforms specially designed for the purpose. A multisig plus well-designed consensus-finding tools can easily beat idealized collusion-resistant quadratic funding plus crypto twitter. But in all cases, we need new designs. Projects that need new oracles and want to build their own should see that as 50% of their job, not 10%. Projects working on new governance designs should build with ZK and AI in mind, and they should treat the communication layer as 50% of their job, not 10%. This is how we can ensure the decentralization and robustness of the Ethereum base layer also applies to the world that gets built on top.

@omniharmonic This is essentially the goal of Archon (github.com/coleam00/Archon) but you’d probably have better experience rolling your own minimalist version that’s specific to your needs with Claude Agent SDK, crawl4ai, and docling

what I’m looking for: a single tool that I can dump markdown, pdf, and csv content into that will parse it, tag it, and make it available to my local agent via MCP who is building this?

finally installed a markdown export browser plugin after realizing how much I need a context-window building pipeline @claudeai code is changing how I do personal knowledge mgmt, finally getting me to use Obsidian who’s building the best context-engineering pipeline tooling?

@DennisonBertram @Railway I came here for this. Thanks for spreading the knowledge!

I finally got Claude to work with @Railway and it's fantastic. Now my process is: - Have an idea - Talk to GPT5 about it - Give a spec to Claude - Have Claude interview me about it - Give it to Continuous Claude - Do something else - Check out the app in production

@DennisonBertram Maybe give Chrome dev tools MCP a whirl; out of the above, it’s the one I’ve had the most success with

Browser testing for LLMs isn't really solved yet. Shill me something new. Playwright MCP - Token heavy Browser Skill - Good, but so far not super reliable, need to try it more Orchid - Very opinionated, haven't gotten it working well yet Antigravity - Okayish? Hard to tell.

@DennisonBertram @claudeai Have you tried Spec Kit or other PRD driven development? By defining the tasks thoroughly upfront I’ve found my results to be as complete as the spec that I provide

My main complaint still about @claudeai is how it will come to the conclusion that radically simplifying or eliminating large chunks of what you're trying to do is the right way to solve a task.

We have 3 trillion hours wasted scrolling that could become 'investments' into solving the many challenges each community faces. So many startups die unsuported and many problems that are not venture-backable are left unaddressed. We can empower communities at scale when we can offer a frictionless and effective system for people to start projects, leverage sweat equity contributions from their community, and fairly govern the value created. People currently lack the mechanisms to enable it: - Sense making to define problems where is tricky - Managing work across fluid groups is cumbersome - Valuing work is prone to conflict and too time-consuming to do in small pieces - Rewarding work requires paying lawyers and setting ESOPs, excluding freelancers - Governing the collective is impossible without proper tooling past 5-8 people But we're changing all of that. It's not a single venture thing (too complex) but we already have super capable founders working on multiple of the pieces and making serious progress.

@UpdraftFund Need some UPD 🪁 to get started? Join the Discord discord.gg/ywwVNJKf and let us now where to send you some in #get-free-upd. This is precisely why we need this faucet though. Soon, you'll be able to just grab some free streaming UPD in the app!

Hey Fam, there's just a couple days left to support this Solution on @UpdraftFund and make some dough yourself in the process! 💸🪁 It'd mean the world to me if you could add a couple UPD 🪁 to help support the development of this open source next-gen faucet for the masses! 🫶

@karmaticacid Just listen to the rhythm of the chain 🙌 And all the capital flowing to public goods ❤️

I beliETH in a thing called love

. @ethboulder2026 is coming [2026]

P.S. - follow @UpdraftFund 🪁 for future updates of Ideas that, if you’re an early Finder, you can earn $UPD from 💸 4/3

Help support my first Solution 💡 on Updraft and make money 💰 in the process! updraft.fund/solution/0x5e4… 1/3