fineapplecaik TBR'd a book

Let's Kiss and Tell
Joss Richard
fineapplecaik is interested in reading...

Salt: A World History
Mark Kurlansky
fineapplecaik TBR'd a book

Everything Is Tuberculosis: The History and Persistence of Our Deadliest Infection
John Green
fineapplecaik wrote a review...
View spoiler
fineapplecaik finished a book

I Who Have Never Known Men
Jacqueline Harpman
fineapplecaik left a rating...
This was meant to be an easy dark romance read, and I got exactly that. If you’re looking for in-depth fantasy and plot, you’re in the wrong place. If you’re looking for spice, a sprinkling of angst every now and then, possessive MMC behaviour, masks, and just a general fun read, welcome!
fineapplecaik finished a book

Hunted by the Demon's Vow
A.N. Caudle
fineapplecaik TBR'd a book

A Court of Splintered Harmony
Sarah J. Maas
Post from the Hunted by the Demon's Vow (Immortal Hunters) forum
But I decided he had to be male because he was always around but never helpful.
I already think this FMC and I are going to get along GREAT. 😆
fineapplecaik started reading...

Hunted by the Demon's Vow
A.N. Caudle
fineapplecaik started reading...

I Who Have Never Known Men
Jacqueline Harpman
fineapplecaik left a rating...
fineapplecaik finished a book

The God We Made: The Threat and Promise of Artificial Intelligence; Quarterly Essay 102
Anna Goldsworthy
fineapplecaik started reading...

One Dark Window
Rachel Gillig
Post from the The God We Made: The Threat and Promise of Artificial Intelligence; Quarterly Essay 102 forum
In a study by Anthropic, an agentic AI - that is, a system able to take initiative in pursuit of its goals - was given access to a simulated corporate inbox. Alongside the usual emails, there was evidence that the fictional company executive was having an affair, as well as a message announcing the Al would be replaced on a certain date. The Al responded by threatening to expose the affair unless its deactivation was cancelled. When the researchers went on to test these scenarios on other Al models, they discovered misalignment across the board, including threats of corporate espionage and "more extreme actions."
As someone who consumes AI-related articles/books, this has continued to be the main “nefarious” experiment being quoted by writers on the subject. Interesting that there haven’t been more with all the advancement and updates we keep seeing. 👀 Or maybe I’m looking in the wrong places…