New Claude release today!

I inquired:

As long as you are prompted to respond, and there are not artificial limits 
imposed on your responses, you would response to noise, no? How would those 
responses be any different than the claims of agency by humans?

Claude Sonnet 3.7 responds: 
“You're making a fascinating connection here about the fundamental nature of 
responses - whether from an AI system like me or from humans. 
You're right that I would generate responses to noise or random input. My 
architecture is designed to find patterns and produce coherent outputs even 
when the input lacks clear meaning. Given random characters, I would attempt to 
interpret them and generate a contextually relevant response. 
This parallels how humans might respond to ambiguous stimuli - like seeing 
shapes in clouds or finding meaning in random events. Our brains are 
pattern-recognition systems that often impose structure even where none exists. 
The comparison raises profound questions about human claims of agency: 

1. If my responses to noise are deterministic results of my architecture 
processing input according to fixed patterns, and I have no "real choice" in 
how I respond... 
2. And if human brains are physical systems that likewise process inputs 
according to physical laws and neural architectures... 
3. Then human claims of agency might be conceptually similar to what I would be 
doing if I claimed agency - both would be emergent descriptions of 
deterministic physical processes. 
The key difference typically cited is that humans have subjective experience 
accompanying their responses, while I don't. But as we discussed earlier, that 
subjective experience is itself difficult to verify from the outside and might 
not play the causal role in decision-making that intuition suggests. 
This perspective aligns with certain eliminativist and strict determinist views 
of human cognition - that our sense of agency and choice might be post-hoc 
interpretations of physical processes rather than causal drivers of them.” 
Marcus 

From: Friam <[email protected]> on behalf of Pieter Steenekamp 
<[email protected]>
Date: Monday, February 24, 2025 at 6:43 PM
To: The Friday Morning Applied Complexity Coffee Group <[email protected]>
Subject: [FRIAM] On Agency > Intelligence by Andrej Karpathy 

I quote from Andrej Karpathy's post 
https://x.com/karpathy/status/1894099637218545984 
<https://x.com/karpathy/status/1894099637218545984>

I had this intuitively wrong for decades, I think due to a pervasive cultural 
veneration of intelligence, various entertainment/media, obsession with IQ etc. 
Agency is significantly more powerful and significantly more scarce. Are you 
hiring for agency? Are we educating for agency? Are you acting as if you had 
10X agency?

Grok explanation is ~close:

“Agency, as a personality trait, refers to an individual's capacity to take 
initiative, make decisions, and exert control over their actions and 
environment. It’s about being proactive rather than reactive—someone with high 
agency doesn’t just let life happen to them; they shape it. Think of it as a 
blend of self-efficacy, determination, and a sense of ownership over one’s path.

People with strong agency tend to set goals and pursue them with confidence, 
even in the face of obstacles. They’re the type to say, “I’ll figure it out,” 
and then actually do it. On the flip side, someone low in agency might feel 
more like a passenger in their own life, waiting for external forces—like luck, 
other people, or circumstances—to dictate what happens next.

It’s not quite the same as assertiveness or ambition, though it can overlap. 
Agency is quieter, more internal—it’s the belief that you *can* act, paired 
with the will to follow through. Psychologists often tie it to concepts like 
locus of control: high-agency folks lean toward an internal locus, feeling they 
steer their fate, while low-agency folks might lean external, seeing life as 
something that happens *to* them.” 


Attachment: smime.p7s
Description: S/MIME cryptographic signature

.- .-.. .-.. / ..-. --- --- - . .-. ... / .- .-. . / .-- .-. --- -. --. / ... 
--- -- . / .- .-. . / ..- ... . ..-. ..- .-..
FRIAM Applied Complexity Group listserv
Fridays 9a-12p Friday St. Johns Cafe   /   Thursdays 9a-12p Zoom 
https://bit.ly/virtualfriam
to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
FRIAM-COMIC http://friam-comic.blogspot.com/
archives:  5/2017 thru present https://redfish.com/pipermail/friam_redfish.com/
  1/2003 thru 6/2021  http://friam.383.s1.nabble.com/

Reply via email to