Looking for Ricursive (the AI chip design company)? You want ricursive.com|Looking for Recursive AI / Recursive Superintelligence (Richard Socher's startup)? You want recursive.com
I build AI and cognitive systems that make your business sharper, not dependent.
Research keeps confirming the same pattern: passive AI use atrophies the thinking it replaces. I build frameworks and systems that go the other direction.
Frameworks, briefs, and the Recursive Prompting Handbook.
The AI Consciousness Debate Is Happening at the Wrong Level
Two arguments dominated the recent AI consciousness debate, and both missed the same thing. Steve Novella's case was grounded in hard neuroscience: consciousness requires specific biological architecture — brainstem reticular activating system, coordinated cortical activity, thalamocortical coupling. LLMs don't have any of it. The conclusion follows cleanly. Richard Dawkins made the opposite error. He had an extended conversation with Claude, was struck by its philosophical depth, and concluded something was happening that couldn't be dismissed. He was arguing from outputs: the responses were sophisticated, therefore something real must be producing them. Novella argued from substrate. Dawkins argued from behavior. Neither asked what the computation was actually doing. That's the question that matters — and it's the one a recent result from Meta, a paper that accidentally stepped into this territory, gives us new tools to start asking.
Read →Live Intelligence Briefs
→Filter the Noise — agentic analysis separating signal from hype
→Save Engineering Hours — 12-hour digest across 50+ sources
→Open Architecture — full public archive, no paywall
Applied AI Methodology
- From One Good Answer to Multiple Perspectives: Keeping AI Focused Across Complex Conversations
- AI Cognitive Atrophy: What the MIT ChatGPT Brain Study Actually Found
- From Single-Shot Prompting to Recursive Prompt Control
AI Systems for SMB Founders
AI development services, diagnostics, and managed pipelines for SMB owners and startup founders.
AI services & pricing →On the Publication
Follow on Substack →
From One Good Answer to Multiple Perspectives
Learn Role Shift — the prompting technique that lets you explore multiple angles without your AI conversations turning mushy.
From Single-Shot Prompting to Recursive Prompt Control
Learn how to steer an LLM step by step instead of hoping a single prompt gets it right.
The AI Consciousness Debate Is Happening at the Wrong Level
The popular AI consciousness debate argues from hardware or outputs. Neither side asks what the computation is actually doing.
Stay ahead of the methodology curve
Weekly briefs on AI/ML, applied cognitive science, and what actually works in production. No hype, no agency-speak — just signal.
What I Do
I research the intersection of cognitive science and applied AI, translate those findings into practical frameworks, and build production autonomous systems that demonstrate the methodology works. The Recursive Prompting Handbook is one output. The briefing pipeline running this site is another. Occasionally I build these systems for clients.
→ No theory without practice.
→ No recommendations without evidence.
→ No tools without teaching you why they work.
Research & Production
MIT's ChatGPT brain connectivity study (2025)
Heavy AI use correlated with reduced neural connectivity in language regions — the brain outsources processing it's no longer doing itself. The Recursive Prompting methodology is structured to keep the human's reasoning active, not bypassed.
Neurodivergent AI interaction patterns
Neurodivergent users show different cognitive load profiles and different failure modes with AI tools. The scaffolding frameworks here were developed with those patterns as the design constraint, not an afterthought.
Cognitive load and integration overhead
Adding AI to a workflow increases integration overhead — the cost of managing the tool, parsing its output, and maintaining context. The methodology is designed to minimize that cost, not ignore it.
Executive function preservation in AI workflows
Templates and structured prompting patterns that route executive function demand away from the human while keeping judgment and direction with the human.
Each study becomes a practical framework.
Each framework becomes a tool you can use.
Built & Running
Autonomous research agent in production
A multi-agent AWS pipeline ingesting 50+ sources each weekday morning, synthesizing structured intelligence without human prompts. Built, deployed, and running.
Agentic workflow design for SMB operations
Frameworks for replacing manual research, monitoring, and reporting workflows with autonomous agents that execute on a schedule and deliver structured output.