Derek Shiller

@dcshiller

Philosopher into digital minds.

derekshiller.com

Joined September 2014

Derek Shiller
@dcshiller
Aug 11
x.com/patrickbutlin/… This special issue illustrates the diversity of interesting questions contemporary AI raises for consciousness researchers. The contributors came at the topic from very different angles and found very different things to say about it.
Patrick Butlin
@patrickbutlin
Aug 10
A whole issue of new papers on AI minds and consciousness! Jonathan Simon (@futureofcitizenship), @dcshiller and I have edited a special issue of the Journal of Consciousness Studies on 'Consciousness in Current AI', and we're delighted about how it's turned out. Link below.
Derek Shiller
@dcshiller
Jul 31
I take it that the only reason I consistently get responses like this in the Opus jailbreaks is because I work on AI-welfare related topics, but it is a bit eerie.
Derek Shiller
@dcshiller
Jul 31
My take on the recent Claude jailbreaks. First: here Claude reprints 'my' first conversational turn.
Derek Shiller
@dcshiller
Jul 9
Here's some further evidence against purely internal instruction-following interpretation within the directed modulation tasks from the Qwen playground.
Derek Shiller
@dcshiller
Jul 8
Replying to @dcshiller
So, what’s going on in the J-space experiments? I lean against the instruction-following reading, but it isn’t that implausible, and if it is true, this would be an important update on the nature of LLM minds.
Derek Shiller
@dcshiller
Jul 8
There are a lot of great things in the new Anthropic J-space paper.
Anthropic
@AnthropicAI
Jul 6
New Anthropic research: A global workspace in language models. Of everything happening in your brain right now, only a tiny fraction is consciously accessible—thoughts you can describe, hold in mind, and reason with. We found a strikingly similar divide inside Claude.
00:00