Hackworth

Meanwhile, Anthropic in the last month:

The assistant axis: situating and stabilizing the character of large language models

Next-generation Constitutional Classifiers: More efficient protection against universal jailbreaks

Introducing Bloom: an open source tool for automated behavioral evaluations

Here’s the 60 Minutes piece and Anthropic’s June article about the one in their own office.

Claudius was cajoled via Slack messages into providing numerous discount codes and let many other people reduce their quoted prices ex post based on those discounts. It even gave away some items, ranging from a bag of chips to a tungsten cube, for free.

Their article on this trial has some more details too.

That was all part of the idea, though, because Anthropic had designed this test as a stress test to begin with. Previous runs in their own office had indicated similar concerns.

Are they expecting AI to… make decisions regarding tenants? I wonder if they are aware of universal prompt injection.

The fact that workers with expense accounts still feel they’re getting paid so little that they deserve to commit fraud says something about that stratum of employee.

Pretty much anyone who travels has to submit receipts. Most people who travel are not making bank. They’re the people who set up and stand at convention booths, sales staff support, assistants, videographers, etc. Also, most travel is a miserable ordeal. I’m not saying it’s okay to commit fraud, but let’s not equate the hourly employee “re-creating” his lost lunch receipt with a 6-figure income.