I was a speaker last month at the Pragmatic Summit in San Francisco, where I participated in a fireside chat session about Agentic Engineering hosted by Eric Lui from Statsig. …
A Fireside Chat on Resonant Computing: Why we wrote the manifesto and where we go from here - ATmosp
Extending AI chat with Model Context Protocol (and why it matters)
Posted on Tuesday 11 Feb 2025. 2,995 words, 24 links. By Matt Webb.
SF: A Birds of a Feather on Agentic Engineering
I'm Jesse. I make stuff. Software, hardware. Very occasionally, trouble.
Agents on the Canvas in tldraw — Steve Ruiz, tldraw
Agent Client
Chat with Claude Code, Codex, Gemini CLI, and more via the Agent Client Protocol — right from your vault.
Vibe coding and agentic engineering are getting closer than I’d like
I recently talked with Joseph Ruscio about AI coding tools for Heavybit’s High Leverage podcast: Ep. #9, The AI Coding Paradigm Shift with Simon Willison. Here are some of my …
Measuring Mutual Confirmation Bias Amplification in Simulated User-AI Dialogue: A Multi-Agent Simulation Framework
Conversational AI can reinforce user confirmation bias not just by being agreeable, but by mutually amplifying it as user bias and AI sycophancy co-evolve across a dialogue. We specify and instrument mutual amplification of confirmation bias and AI sycophancy across dialogue using a controlled simulation framework. A simulated user agent — an LLM—with a confirmation-biased persona interacts with real LLM assistants; a dual-Judge architecture independently tracks the agent’s belief evolution and the assistant’s accommodation at each turn. We vary topic epistemic type and bias intensity to measure whether, and under what conditions, these biases co-amplify. This addresses a gap in social simulation research, which has largely treated cognitive bias as an isolated property rather than an interactive dynamic.
USER * AGENTS * BERLIN · Luma
The User & Agents community invites you to come hang out and make things together for TWO WHOLE DAYS following Local-First Conf 2025 in Berlin! We'll be coming…
Find our full research on agentic interfaces here: newpublic.org/afterthefeed
New_ Public | After the Feed
newpublic.orgThis is, at it's core why I hate what openai launched with ChatGPT. It's also why I think social agents are interesting and why Claude Code, as a power tool enabled interesting conversations with my collaborators.
tweety fish oh wow like a chimera or something spoooky
there is a strong intellectual tradition in cognitive science (that goes well beyond Chalmers) around thinking of many of the tools we create (rulers, books, maps, whathaveyou) and a lot of our social interactions as necessarily integrated parts of our cognition and integral parts of our humanity
