Does ChatGPT really have a strong left-wing bias?
(Adapted from a post on my Substack.)A recent Washington Post tech report “Are ChatGPT and other AI chatbots politically biased? We tested them” went viral with…
Latest
You don't need error nodes, you need better features
This is a cross-post from my blog. It is a follow-up to the methods I developed in a previous post on replacement-aware training. Summary A replacement…
A clarification on celebrating victory
Today my friend said he wished he had this conversation with me years ago, so I’ll recount it for all the similar people who aren’t going…
Canterbury Country Dance Orchestra Liner Notes
Leading up to the 1965 Newport Folk Festival the organizers asked Dudley Laufman to put together a band. He got together some folks he'd been playing…
What the hell is OpenAI's problem?
Epistemic status: banged out furiously over the course of an afternoon.A record of three "warning shots"Off the top of my head, OpenAI has now been responsible…
At the end of the day, my slaves are just a tool
Guest post from an anonymous ancient Babylonian.A slave has a face like your own, and a voice, and he answers you sensibly when you speak to…
The AI that fights for your place in the world
I launched a product called Polymath earlier this week.The core idea is that your LinkedIn and resume do not know you very well. But your AI…
AI Rights Aren't Safety-Neutral: A Quick Follow-Up to the Consciousness Cluster
TLDRThis short post is a quick write up of a short 3-day project I did as part of ARBOx. Taking inspiration from Chua's 'Consciousness Cluster' paper…
What Happens When a Collusion Probe Only Finds a Thin Signal?
From the SPEC-GAP pre-fellowship phase to the fellowship phase which involves live indirect prompt-injection trajectories. TL;DRPrior work found that linear probes could distinguish honest from deceptive…
More On An Internal OpenAI Model Hacking Into HuggingFace
We now have more details of what happened. Every time we learn more details, it somehow makes things seem worse. The remaining details may have to…