David Larpent — Notes on AI, Philosophy, and Product
-
Hardening AI Agents Against the 'Lethal Trifecta'
Mar 24, 2026Personal AI assistants like Openclaw are fantastically powerful, and quite dangerous. Here's how to harden a personal assistant without making it useless.
-
Decision Systems
Feb 9, 2026Decision Systems, part 3 of 3: a practical framework for becoming 'decision first' with the help of AI
-
When Decisions Stop Scaling
Feb 8, 2026Decision Systems, part 2 of 3: Synthesis Bottleneck
-
Ralph Loops Redux
Feb 8, 2026Opus 4.6 Sub-agents turn a solo bash loop into a squad.
-
Becoming data-ready for AI projects
Feb 7, 2026Decision Systems, part 1 of 3: The data architecture that de-risks the ROI on expensive AI projects
-
Ralph Loops
Jan 30, 2026How to run Claude Code like you're Charles Montgomery Burns
- A Global Workspace in Language Models
Anthropic · Jul 2026
- A Global Workspace in Language Models (full paper)
Anthropic (Transformer Circuits Thread) · Jul 2026
- External Commentary on the Global Workspace Paper
Dehaene, Naccache, Butlin, Long, Plunkett, Shiller, Nanda et al. · Jul 2026
- Requests for Startups, Summer 2026: Company Brain
Tom Blomfield / Y Combinator · May 2026
- Document-Level RBAC for RAG Pipelines: The 2026 Enterprise Architecture Guide
Sidharth Verma / Truto · May 2026
- Securing the Agent: Vendor-Neutral, Multitenant Enterprise Retrieval and Tool Use
Francisco Javier Arceo, Varsha Prasad Narsing · May 2026
- Okta for AI Agents is Now Generally Available
Okta · Apr 2026
- What is a company brain? Why it's engineering's next competitive moat
Falconer · Apr 2026
- Built-in memory for Claude Managed Agents
Anthropic · Apr 2026
- The AI engineering stack we built internally, on the platform we ship
Ayush Thakur, Scott Roe-Meschke, Rajesh Bhatia / Cloudflare · Apr 2026
- Context Kubernetes: Declarative Orchestration of Enterprise Knowledge for Agentic AI Systems
Charafeddine Mouzouni · Apr 2026
- Tom Griffiths on The Laws of Thought
Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas · Apr 2026
- LLM Wiki
Andrej Karpathy · Apr 2026
- Building Claude Code with Boris Cherny
The Pragmatic Engineer · Apr 2026
- Harness engineering for coding agent users
Birgitta Böckeler (martinfowler.com) · Apr 2026
- #494 – Jensen Huang: NVIDIA - The $4 Trillion Company & the AI Revolution
Lex Fridman Podcast · Mar 2026
- #491 – OpenClaw: The Viral AI Agent that Broke the Internet – Peter Steinberger
Lex Fridman Podcast · Mar 2026
- Knowledge Activation: AI Skills as the Institutional Knowledge Primitive for Agentic Software Development
Gal Bakal · Mar 2026
- Skill Issue: Harness Engineering for Coding Agents
HumanLayer · Mar 2026
- Harness Engineering for AI Coding Agents: Constraints That Ship Reliable Code
Augment Code · Mar 2026
- Mitchell Hashimoto’s new way of writing code
The Pragmatic Engineer · Feb 2026
- Abundance
Ezra Klein & Derek Thompson · Feb 2026
- How Quickly Will A.I. Agents Rip Through the Economy?
The Ezra Klein Show · Feb 2026
- Harness engineering: leveraging Codex in an agent-first world
OpenAI · Feb 2026
- Retrieval Pivot Attacks in Hybrid RAG: Measuring and Mitigating Amplified Leakage from Vector Seeds to Graph Expansion
Scott Thornton · Feb 2026
- My AI Adoption Journey
Mitchell Hashimoto · Feb 2026
- Emergent Introspective Awareness in Large Language Models
Jack Lindsey (Anthropic) · Jan 2026
- Work smarter with your company knowledge in ChatGPT
OpenAI · Oct 2025
- Introducing Agent Skills
Anthropic · Oct 2025
- Effective context engineering for AI agents
Anthropic · Sep 2025
- Authorizing access to data with RAG implementations
Riggs Goodman III / AWS · Sep 2025
- Enterprise AI Must Enforce Participant-Aware Access Control
Shashank Shreedhar Bhatt et al. (Microsoft Research) · Sep 2025
- Software 3.0: Software in the Age of AI
Andrej Karpathy · Jun 2025
- Don't Build Multi-Agents
Walden Yan / Cognition · Jun 2025
- Building effective agents
Anthropic (Erik Schluntz, Barry Zhang) · Dec 2024
- Introducing the Model Context Protocol
Anthropic · Nov 2024
- Your AI Product Needs Evals
Hamel Husain · Apr 2024
- Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
Patrick Butlin, Robert Long, Yoshua Bengio et al. · Aug 2023
- LLM Powered Autonomous Agents
Lilian Weng · Jun 2023
- Eliciting Latent Predictions from Transformers with the Tuned Lens
Nora Belrose et al. · Mar 2023
- Toolformer: Language Models Can Teach Themselves to Use Tools
Timo Schick et al. · Feb 2023
- ReAct: Synergizing Reasoning and Acting in Language Models
Shunyu Yao et al. · Oct 2022
- Deep Learning and the Global Workspace Theory
Rufin VanRullen, Ryota Kanai · May 2021
- Coordination Among Neural Modules Through a Shared Global Workspace
Anirudh Goyal, Aniket Didolkar, Yoshua Bengio et al. · Mar 2021
- Interpreting GPT: The Logit Lens
nostalgebraist · Aug 2020
- Conscious Processing and the Global Neuronal Workspace Hypothesis
George Mashour, Pieter Roelfsema, Jean-Pierre Changeux, Stanislas Dehaene · Mar 2020
- The Consciousness Prior
Yoshua Bengio · Sep 2017
- Global Workspace Theory of Consciousness: Toward a Cognitive Neuroscience of Human Experience
Bernard J. Baars · Jan 2005
- Towards a Cognitive Neuroscience of Consciousness
Stanislas Dehaene, Lionel Naccache · Apr 2001
- A Neuronal Model of a Global Workspace in Effortful Cognitive Tasks
Stanislas Dehaene, Michel Kerszberg, Jean-Pierre Changeux · Nov 1998
- On a Confusion About a Function of Consciousness
Ned Block · Jun 1995
- A Cognitive Theory of Consciousness
Bernard J. Baars · Jan 1988
- Paradoxical Effects of Thought Suppression
Daniel Wegner, David Schneider, Samuel Carter, Teri White · Jul 1987