Posts
The Intentional Stance, LLMs Edition
2024-04-30T17:12:29.005Z
I designed an AI safety course (for a philosophy department)
2023-09-23T22:03:00.036Z
Confusions and updates on STEM AI
2023-05-19T21:34:58.041Z
AI Alignment in The New Yorker
2023-05-17T21:36:18.341Z
A Study of AI Science Models
2023-05-13T23:25:31.715Z
A Guide to Forecasting AI Science Capabilities
2023-04-29T23:24:46.579Z
On taking AI risk seriously
2023-03-13T05:50:57.170Z
Everything's normal until it's not
2023-03-10T02:02:16.822Z
Questions about AI that bother me
2023-02-05T05:04:07.582Z
Should AI writers be prohibited in education?
2023-01-17T00:42:56.999Z
Progress and research disruptiveness
2023-01-12T03:51:01.640Z
AI Safety Camp: Machine Learning for Scientific Discovery
2023-01-06T03:21:37.823Z
Book recommendations for the history of ML?
2022-12-28T23:50:55.512Z
Why I think that teaching philosophy is high impact
2022-12-19T03:11:38.363Z
My summary of “Pragmatic AI Safety”
2022-11-05T12:54:53.532Z
Against the weirdness heuristic
2022-10-02T19:41:10.562Z
There is no royal road to alignment
2022-09-18T03:33:50.720Z
It's (not) how you use it
2022-09-07T17:15:52.493Z
Three scenarios of pseudo-alignment
2022-09-03T12:47:43.526Z
Alignment is hard. Communicating that, might be harder
2022-09-01T16:57:55.564Z
Who ordered alignment's apple?
2022-08-28T04:05:34.942Z
Alignment's phlogiston
2022-08-18T22:27:31.093Z
Deception as the optimal: mesa-optimizers and inner alignment
2022-08-16T04:49:50.957Z
Comments
Comment by
Eleni Angelou (ea-1) on
Looking for reading recommendations: Theories of right/justice that safeguard against having one's job automated? ·
2023-10-12T19:44:09.329Z ·
LW ·
GW
Here's a famous book on this: https://www.amazon.com/Rise-Robots-Technology-Threat-Jobless/dp/0465097537
Comment by
Eleni Angelou (ea-1) on
I designed an AI safety course (for a philosophy department) ·
2023-09-24T03:01:38.065Z ·
LW ·
GW
Course titles are fixed so I didn't choose that, but because it's a non-intro course it's up to the instructor to decide the course's focus. And yes, the students had seen the description before selecting it.
Comment by
Eleni Angelou (ea-1) on
Questions about AI that bother me ·
2023-02-05T06:26:30.535Z ·
LW ·
GW
Yup, that's what I mean. Specifically, I had Pinker in mind: https://forum.effectivealtruism.org/posts/3nL7Ak43gmCYEFz9P/cognitive-science-and-failed-ai-forecasts
Comment by
Eleni Angelou (ea-1) on
Questions about AI that bother me ·
2023-02-05T06:24:28.845Z ·
LW ·
GW
It was intro to phil 101 at Queens College CUNY. I was also confused by this.
Comment by
Eleni Angelou (ea-1) on
Book recommendations for the history of ML? ·
2022-12-29T00:13:33.086Z ·
LW ·
GW
Thank you Lawrence!
Comment by
Eleni Angelou (ea-1) on
Who ordered alignment's apple? ·
2022-08-28T13:13:49.266Z ·
LW ·
GW
I agree there probably isn't enough time. Best case scenario there's enough time for weak alignment tools (small apples).