Entries are closed, and every strategy is now being tracked through October. You can follow the positions here as the month goes on: https://www.part-timequant.com/leaderboard There's a competition in the Academy every month. If you missed this one, join for $29 a month and you'll be in time for November: https://www.skool.com/part-time-quant-academy/about

Hi everyone, Me and my team are working on the next round of content for the YouTube Channel and we need your help. We're now accepting ideas from members of Zero One Systems for specific tutorials, builds and explainers YOU want to see on my YouTube Channel. I'm talking: - Builds you've never seen before - Tutorials you've always wanted - Explanations no one has given yet I'll be able to pull from this list and ACTUALLY make the videos you've asked for. You can also "Like" another comment if you like their idea and I'll track the likes as "Upvotes" Lewis p.s.sometimes it's really hard to know which content people want vs what is made. This would help tremendously with that.

I have just completed Days 1–16 of the Zero One Systems curriculum. My contribution has been applying the prompts provided each day to my own work, challenging the assumptions where they did not fit, and following the process far enough to see what emerged. For my use case, a personal agent is not simply a chatbot that remembers you. It is an operator-facing manager backed by explicit context, bounded authority, specialist systems, and evidence. That is the claim this post is trying to earn. I began with a personal dashboard and a simple question: what would an AI need to know about me to become genuinely useful? The curriculum works through personality, values, goals, risk tolerance, and decision-making. The most useful—and uncomfortable—exercise was a documentary-style interview covering my background, career change, failures, family, money, and what actually drives me. That became soul.md: a private canonical file describing how I think and operate. I then distilled it into soul.runtime.md, a smaller set of executable principles for practical agent use. Two of those principles have already changed the architecture: - Autonomy requires bounded authority, which exposed the weakness in my original agent design. - Correctness governs speed, which is why completion evidence now belongs in an append-only - Decision and Evidence Ledger rather than being reduced to a status flag. One lesson mattered more than the rest: More context is not automatically better. Stable identity, current project state, private history, operational knowledge, and evidence are different classes of information. They update at different rates and should only be exposed to agents that genuinely need them. The biggest change came when I reviewed which agent to build first. My initial choice was a Founder Intelligence Scout—monitoring AI tools, GitHub repositories, contracting opportunities, and founder tactics. After two separate research workflows, the problem became obvious. I already had specialised systems doing adjacent work:

Is putting the context window inside a document or file a turn around for an AI Agent to keep on the same project without exceeding limit?

TradingView for Windows only ships as an MSIX package and cannot be installed/ opened in debug mode, which is required for MCP and Claude connection. Anyone know of a workaround TradingView instal thats avoid the MS windows trap?