Thoughts on Role Confusion

The other day, I came across "Prompt Injection as Role Confusion" (via Simon Willison). It's a really interesting blog-style version of a paper by Charles Ye, Jasmine Cui and Dylan Hadfield-Menell, where they find that LLMs seem to almost ignore 'role' tags like <system>, <user> or <think>, and instead use the tone of text to infer roles. This seems to explain a lot of jailbreaks.

[ Read more ]

Best. Video. Ever.

Cats and robots. What more does a meme need?

I came for the article, I stayed for the comments

An OK but somewhat oversimplified post on short selling leads to a fascinating discussion on the topic from market practitioners. Well worth reading to the end, you'll wind up holding at least two irrefutable but mutually contradictory opinions about the issue...

Making a fool of yourself in public

On the Business of Software Blog, Neil Davidson recommends using your fear of making yourself look stupid by failing publicly as a way to motivate yourself to work as hard as you need to work on your startup. Sounds right to me. When I was in my early 20s I saw the mortality rates for smokers and decided that I would give up at the age of 30. In order to make sure that I stuck to that, over the years I told pretty much every one of my friends that I was going to quit then, which meant that I really could not back down. The result is that on the night of my 30th birthday party I quit, and (bar one or two particularly drunken evenings) I've not touched a cigarette since.

IPv6

I knew that these odd random colon-separated thingies in my /etc/hosts were IPv6 addresses of some sort, but it was good to find something that explains them clearly (update: link now sadly dead).