Beyond Roleplay: Jailbreaking Gemini with drugs and ritual - Tidepool Heavy Industries

LLM-generated skills work, if you generate them afterwards

LLM “skills” are a short explanatory prompt for a particular task, typically bundled with helper scripts. A recent paper showed that while skills are useful to LLMs, LLM-authored skills are not. From the abstract:

What Happens, Exactly, When a Person Talks to an LLM?

A phenomenology of thinking with a model.

Guardian Angels: LLM Personalization for Productivity and Security

I propose an approach for highly personalized LLMs, for near-future productivity gains and personal info/cybersecurity against increasingly powerful LLMs: they should, in the spirit of uploading, try to emulate the user’s values and preferences in order to amplify the principal—not replace them. I discuss a package of techniques and proposals to accomplish such ‘guardian angels’; dynamic evaluation of LLMs combined with active learning and elicitation and heavy inner-monologue search/data-augmentation.

Vibe Maintainer

Some attendees at an AI Tinkerers meetup in early Feb were asking me what it’s like to be the maintainer of a big OSS project where the…

How creatives and devs can all finally escape the control of the silicon valley of evil and make a trillion dollars - Multi-hyphenate

ft. ATprotocol (the remix)

How creatives and devs can all finally escape the control of the silicon valley of evil and make a trillion dollars · Multi-hyphenate

ft. ATprotocol (the remix)

‘Doom Loop’: OpenAI and Microsoft Admits LLMs Are Destroying the Web and Built on Theft

"Millions of people around the world will soon consider large models ‘hoovering up’ all their work to be an astonishing theft of unprecedented proportions."

Ten Lines Of Code That Changed My World – Pixelambacht

Front-end antics and typographic mischievousness

Are we evolving from pages to apps to agents?

Recently, Vercel came to London and teamed up with Anthropic’s local chapter to host a skills event.

The Contracting Circle

Why don't we believe LLMs are people?

Vibe Coding: The Final Form of Hyper-Individualism

A few days ago, I had to deal with the first "vibe coded" PR to my software. In this article, I reflect on this encounter, and analyze the social …

IO Factory: Simulating AI-Enabled Influence Campaigns at Scale

We introduce IO Factory, an AI-driven framework for simulating information and influence campaigns as fully integrated, traceable processes. The threat of digital manipulation now extends beyond persuasive text from individual language models to AI swarms, i.e., persistent groups of coordinated agents that adapt to platform feedback and disguise organized campaigns as ordinary social interaction. Because such campaigns cannot be identified from isolated messages alone, they must be analyzed across a continuous spectrum of planning, platform action, exposure, interpretation, measurement, and adaptation. IO Factory represents this process inside a controlled simulated platform, linking actor roles, platform actions, exposure records, structured model-based evaluations, and configured changes in the simulated population. We implement the architecture and evaluate it across configurations of up to 100,000 agents. The results show that IO Factory executes campaign timelines at scale and produces inspectable evidence of exposure and measured movement in configured belief variables. By recording the actors, objectives, action constraints, exposure paths, and measurement rules used in each run, IO Factory supports reproducible research and red-team analysis of coordinated influence.

Note-Taking and Personal Knowledge Management — Unattributed

Bridge heading into the smokey landscape. License: CC-0 I read Brennan Kenneth Brown's What have note-taking PKMs accomplished, really?...

AT Moderation Architecture | bryan newbold (⛱️ sabbatical mode)

The AT network is becoming more heterogeneous in practice, with independent PDS hosts, apps, and alternative bsky AppViews establishing themselves. This means that more complex inter-service moderation scenarios are starting to get attention. While the labeling system was released all the way back i...

We Need To Stop Calling Entertainers ‘Artists’

Expert in building reliable digital platforms and leading high-impact technical teams. 20+ years experience at the intersection of technology, teams, and learning.