dazzaji
Joined 10 years ago
Karma
158
Submissions
88
Member since
Jul 20
Recent submissions
Comment · 3 months ago
Location: San Francisco Bay Area, CA
Remote: Yes (US and international consulting); available for occasional onsite work and travel
Willing to relocate: No
Technologies: LLM agents; Claude Code; Codex; MCP; multi-agent orchestration; evals; workflow automation; legal-AI architecture; privilege and authority controls; system-prompt assurance
Résumé/CV: https://www.dazzagreenwood.com/about
LinkedIn: https://www.linkedin.com/in/dazzagreenwood
Email: [email protected]
SEEKING CONSULTING / CONTRACT WORK — also open to the right full-time role
Lawyer-technologist designing and building agentic AI systems for legal and other high-stakes work. I focus on the difficult distance between a promising demo and a deployment-ready workflow: selecting the right work, mapping privilege, data, and authority boundaries, designing evals and human-decision gates, and creating tool-agnostic operating architectures that can survive legal and security review. Current obsession: chaining authority- and scope-bounded agents into high-assurance workflows that can run autonomously for six-plus hours, show their receipts, and stop at explicit human (sometimes licensed professional) gates between stages—then produce genuinely valuable, substantial, compliant, and defensible deliverables.
A useful first engagement is a bounded two-week sprint: rank workflows by value, readiness, and fit; sketch an initial target operating architecture; and produce a prioritized 90-day pilot plan plus one implementation-ready pilot brief.
Recent work: AISPA system-prompt assurance paper: https://arxiv.org/abs/2607.28617 Authority Boundaries for AI: https://www.dazzagreenwood.com/p/authority-boundaries-for-ai Interlateral Agents: https://github.com/dazzaji/interlateral_agents (I have a private repo version with professional authorization or approval/adoption gates and control kernel verifiable logging)
Earlier work includes founding law.MIT.edu, testifying before Congress on electronic-transactions law, and leading Consumer Reports’ Data Rights Protocol. I am currently a Stanford CodeX affiliate.
Available now for one bounded sprint and booking one or two larger engagements beginning in September. Best fit: in-house legal teams, legal-tech companies, and AI companies building high-stakes professional workflows. Contract through https://www.civics.com.
Comment · 7 months ago
Nope, not bored at all. I'm clicking on most HN AI threads out of sheer curiosity, eager to learn new techniques and see what folks are thinking or building. Given its transformative ripple effects, AI feels like the single biggest shift reshaping the economy and society right now. Kind of the opposite of boring.
Comment · 7 months ago
I’m pleasantly surprised this was AI assisted so deeply that inconsistencies like that slipped by you. The writing is really extraordinary. It made me want to read for fun again for the first time in decades. Thank you!
Comment · 1 year ago
Thanks for those links - these are the rules and norms I didn’t know before. Now that I see them, they seem pretty sensible overall. Some are of them are a bit quirky.
Comment · 1 year ago
By all means! I’m not sure if Hacker News rules or norms permit us to talk here or not but I’ll at least respond here as a start:
What about loyal agents would you like to talk about?
Comment · 1 year ago
This discussion hits close to home. A few of us at Stanford and Consumer Reports have been working on a project called Loyal Agents (loyalagents.org
) that’s focused on the same core issue raised in the Economist article, namely how to make sure AI agents actually act in the interest of the people they represent.
The idea is to define what “loyalty” means for an AI agent in both technical and legal terms, and then build systems that can prove they’re acting on a user’s behalf (ie not a platform’s or advertiser’s).
It’s early-stage research, but the overlap with many of the questions here is striking. Would be great to get feedback from this crowd as the work evolves.
I’m part of the group working on Loyal Agents and happy to discuss it.
Comment · 1 year ago
Here’s what Claude Sonnet 4.5 suggested to take this piece from something that sounds impressive but lacks substance to something that could actually deliver on its promise. I did this thought exercise to explore whether being AI-generated necessarily precludes brilliance. You be the judge - I think Claude succeeded in mapping the gap between the current draft and what a truly excellent version would actually require.
https://claude.ai/share/46dd4b7e-9adf-473d-8372-22cb1ae34249
Comment · 1 year ago
Based on the URL correlation and content, it sure appears to be the same book.
Comment · 1 year ago
Registration full :-(
Comment · 1 year ago
Not quite - as I understand it box-counting measures global space-filling, manifolds handle local coordinate structure. Consider that the Earth is locally flat but globally spherical, and a Möbius strip vs cylinder are locally identical but globally different. Related problems, but the tools reveal different aspects of geometry. So I think whether “this is exactly what topological manifolds are for” depends what you’re trying to understand.
Comment · 1 year ago
Synthi is an open web tool that instantly summarizes and synthesizes Hacker News threads and their linked articles, grouping every point of view by topic.
[Live demo here: https://prototypejam.github.io/synthesize/](https://prototypejam.github.io/synthesize/)
Why I Built This:
I love the deep discussions on HN, but I never have time to read a long article and a 400-comment thread. The tipping point for building this was when I nearly burned through my monthly API credits on another service just trying to synthesize a few threads! I needed my own tool.
How It Works:
1. Paste any HN thread URL into Synthi. 2. It instantly detects it and fetches the linked article. 3. Click "Full Analysis" for a unified, topic-based synthesis (with attribution to the article or the commenter). 4. Export the result, bookmark it, or listen to it (the output is text-to-speech friendly).
Key Features:
* Smart HN workflow: Auto-detects HN links for a one-click analysis. * Works with any URLs: Can also synthesize any two articles or pieces of text. * 100% client-side: All processing happens in your browser. No backend, no tracking. * Open source (MIT License): The code is yours to inspect, fork, and use.
The Code: [https://github.com/prototypejam/synthesize](https://github.com/prototypejam/synthesize)
A Note on the API Key:
Synthi is a "Bring Your Own Key" app. You'll need a Google Gemini API key, which is stored securely in your browser's local storage and never sent anywhere else.
For now, it's Gemini only, largely because the free tier on Google AI Studio is incredibly generous and a great way to get started. I'm considering adding support for other models like Claude or OpenAI via OpenRouter in the future.
I've been using this every day and I hope it's useful to some of you too. All feedback is welcome!
Comment · 1 year ago
Wow - I'd forgotten all about this but just realized I have posts from an entire phase of earlier professional life - topic by topic and event by event - on an old blog there. Amazingly the browser remembered my login so I was able to find the URL. It's been quite a trip down memory lane revisiting some of the posts. Not sure I need to keep any of that published but I'll at least scrape and store it somewhere for old times sake. Maybe I'll find some buried gem of an idea when I scan them during the great scrape. Or - optimistically - perhaps a future zillion-token context LLM will uncover some personal patterns that unleash deep and actionable insights. Irrespective of the measurable value, I just hate to see the old posts dissapear forever.
Comment · 1 year ago
This is a fun project to be sure. I just wish the author would not refer to the experiment as an "autonomous startup builder" unless they mean it humorously. Having poked around the GitHub repo and read through the materials, it seems like more of an AI coding assistant running in a loop that built and deployed a broken web application with no users, no business model, and no understanding of what problem it was trying to solve. There were quasi-autonomous processes and there were things that were built, but nothing I'd call a startup.
[ my public key: https://keybase.io/civics; my proof: https://keybase.io/civics/sigs/QCufNppvl0j1drs4yNOjS65VhZb8NrnKU0CAPwGSNUM ]