James Padolsey's Blog

Anthropic’s weak watermarks appease a weak law Anthropic announced in August 2026 that text generated by supported Claude models will carry invisible, machine-readable watermarks, applied at model level across supported Claude products and API surfaces wo…

Using git diffs to circumvent Fable’s safeguards Fable, Anthropic’s most heavily guarded and famously ‘locked down’ model, can be made to output persuasive misinformation on a range of topics, the example here being links between autism and vaccines, a de…

Don't let the LLM speak, just probe it.

AI Safety is theatre The AI Safety and Alignment communities are prolific.

I am building an AI safety company A couple of months ago I wrote about the Context->Interception->Thinking->Escalation approach to safer AI conversations.

CITE: Layered Defense in AI Chat Safety There have been a spate of suicides and other mental health crises recently attributed to large language models.

Tips for stroke-surviving software engineers This is a pretty niche topic; I don't imagine there are many of us out there.

Sorry, We Deprecated Your Friend With the release of GPT-5, OpenAI killed off a bunch of older models being used by millions of people around the globe.

Browser AI Agents Break Zero Trust Anthropic has shipped a pilot of Claude for Chrome—an LLM that lives in your browser.

The scribbler, the scribe, the sculptor.

Latent Pluralism in Language Models In my latest work at CIP I've been thinking a lot about the western monopolization of AI and how our values have now leaked almost irreversibly into all of these models.

Unrepresented Zeitgeists in AI There is a hypothesis that says roughly: we believe AI is–by its nature and training–embedded with a collective truth or zeitgeist of human thought captured at a specific time.

Working with LLMs – not against them.

LLM Security: Keep Untrusted Content in the User Role—Always When you're working with Large Language Models that use roles like system, assistant, and user, there's one rule you need to burn into your brain: Never put untrusted content into system or assi…

AIs without levers are inert I don't know whether this revelation is just really obvious or really dull.

Improving LLM Alignment with Metric-Based Self-Reflection While building tiptap.chat, I've been pretty obsessed with safety and guardrails to prevent bad outputs.

Intercepting LLM Streams for Improved Chat UX I’ve been building LLM chat interfaces for a while now and wanted to share some weird methods I’ve been using to get a finer grained control over text streams.

Tipping AI for better responses?

Robots Talking To Machines TL;DR: we're at an inflection point where we're seeing more robots and physically-embodied AIs wanting to engage with machines that were made for humans.

Akihabara, and my reflections on the democratization of AI Weaving through alleys of Akihabara, the so-called Electric Town of Tokyo, one notices the overwhelming amount of choice.

Multifaceted: the linguistic echo chambers of LLMs This is a fun one.

[imported from medium.com] Simple LLM/GPT trick: “seeding” How to coerce a response with less up-front prompting This is an easy prompt-engineering hack I encountered when building both pippy.app and veri.foo.

[imported from medium.com] PSA: Always sanitize LLM user inputs Protect yourself from different types of attacks that can expose data or functionality that you’d rather keep private.

[imported from medium.com] Using History Insertion, Policy Drift and Allusions to jailbreak DALL·E 3 A quick attempt to contravene content policies with ‘history insertion’ and ‘policy drift’ to create images of political figures.

[imported from medium.com] Wanted: the engineer’s entrepreneur.

[imported from medium.com] Building Safe, Aligned & Informed AI Chatbots An analysis and walkthrough of how to build a safe, capable and truly aligned AI chatbot with ChatGPT A lot of AI fanfare has recently enveloped the world.

[imported from medium.com] The silliness, lossiness, and bias of leetcode screening in tech At some point in the last ten years, LeetCode-like interview/screening platforms re-invaded tech and beautifully inserted themselves as the new norm.

[imported from medium.com] Using LLMs to parse and understand proposed legislation Legislation is famously challenging to read and understand.

[imported from medium.com] Disability: Models, Cultures, Perceptions and the Path to Inclusivity.