Sign in

Adrian Chan

@gravity7.bsky.social
799 followers 618 following 407 posts

Bridging IxD, UX, & Gen AI design & theory. Ex Deloitte Digital CX. Stanford '88 IR. Edinburgh, Berlin, SF. Philosophy, Psych, Sociology, Film, Cycling, Guitar, Photog. Linkedin: adrianchan. Web: gravity7.com. Insta, X, medium: @gravity7

PostsRepliesMedia
Adrian Chan @gravity7.bsky.social · 03/05/2025
"coherent discourse organisation. This is achieved by either pointing backward to previously discussed material or forward to upcoming propositions" ...wouldn't lack of cataphoric be explained by Transformer architecture, so not anticipating arguments made later?
000
Adrian Chan @gravity7.bsky.social · 25/04/2025
This missive from Dario is worth the read (and mech interp on #AI is truly fascinating). Among features/concepts found in #LLMs: "genres of music that express discontent." I'm reminded of Borges Chinese Encyclopedia of Animals www.darioamodei.com/post/the-urg...
Borges' Chinese Encyclopedia
010
Adrian Chan @gravity7.bsky.social · 27/02/2025
Yes ... and this visualization of the diffusion model's "thinking" is perhaps much more honest than the verbalization or inner dialog we see with exposed 01, 03 etc reasoning traces. arxiv.org/abs/2502.09992
Large Language  Diffusion Model "thinking"
010
Adrian Chan @gravity7.bsky.social · 20/02/2025
Compare this view of an LLM diffusion model generating its response to the "reasoning" we see in conventional LLMs. This view illustrates the degree to which seeing an AI "think" step by step sustains an illusion that it's actually thinking. Really it's just choosing its words carefully. #LLM #AI
https://www.alphaxiv.org/abs/2502.09992
020
Adrian Chan @gravity7.bsky.social · 28/01/2025
During research into Big Five personality traits, LLMs spontaneously started generating emojis. So the mech interp detectives went after it, and found that training on informal (conversational) data likely resulted in neurons activated for emojis. #LLM #ML #AI arxiv.org/abs/2409.102...
050
Adrian Chan @gravity7.bsky.social · 27/01/2025
"when an LLM explains a concept, can it answer related questions derived from that explanation...?" "gap highlights fundamental limitations in the internal knowledge representation and reasoning abilities of current LLMs" #ML #LLM #AI www.alphaxiv.org/abs/2501.11721
030
Adrian Chan @gravity7.bsky.social · 27/01/2025
"Spurious Forgetting" - fine-tuning not necessarily cause of catastrophic forgetting, but rather task misalignment is cause. #AI #ML #LLM #AIAlignment www.alphaxiv.org/abs/2501.13453
020
Adrian Chan @gravity7.bsky.social · 09/01/2025
Polycrisis
The Graduate
000
Adrian Chan @gravity7.bsky.social · 07/01/2025
Using #LLMs to translate user preferences from user data & reviews. Demonstrates difficulty of capturing user prefs from text vs structured data, sentiment, etc. Paper shows progress but fund Q remains: reviews seek social status thus = polluted motives. #UX #AI #ML www.alphaxiv.org/abs/2412.08604
Preference Discerning with LLM-Enhanced Generative Retrieval
030
Adrian Chan @gravity7.bsky.social · 22/12/2024
Cold, quiet, and wet out. Today might be the day for Satantango. #filmsky
000
Adrian Chan @gravity7.bsky.social · 20/12/2024
User experience, as usual, is going to shape success of integration of AI into so many of these applications... Whilst it's convenient to Ask AI about a PDF within Adobe Acrobat, copying and pasting passages into ChatGPT is faster (though responses lack document context). This is a fail
Adobe Acrobat AI example
000
Adrian Chan @gravity7.bsky.social · 16/12/2024
Had one of those Eureka moments using Claude text prompt to build and post a web page to github using Claude Computer Use. Required some tinkering. AI Hacklets will soon be shared like pinterest boards. I cld see this being the social sharing feature of Gen AI. #AI #GenAI #Claude #Sonnet
Claude Computer screenshot
020
Adrian Chan @gravity7.bsky.social · 14/12/2024
Watched 2001: A Space Odyssey again last night. This is what Hal could do. Are we there yet? Getting close?
110
Adrian Chan @gravity7.bsky.social · 13/12/2024
Trust in AI - huge concept for AI design. This def from '22 doesn't account for hallucinations (facticity), deceptions (fakes), automations/delegations (comprehension?), other LLM/GenAI user trust issues. Is there a more recent survey? #UX #ML #AI #AIEthics arxiv.org/abs/2205.00189
Trust in AI, https://arxiv.org/abs/2205.00189
010
Adrian Chan @gravity7.bsky.social · 06/12/2024
Great book. How many of our product and company ideas should Stephenson, Gibson, others get credit for?! Though funnily I think of this from Westworld as more of how we use gen AI
Westworld character personality interface
000
Adrian Chan @gravity7.bsky.social · 04/12/2024
Known knowns and known unknowns! Neel Nanda et al find entity recognition w/in LLMs to be a factor in chat refusal & hallucinations. I can't determine whether this would have implications for user prompting? Would this suggest an SEO-type approach to prompting? #AI #artificialintelligence #ML #LLM
210
Adrian Chan @gravity7.bsky.social · 03/12/2024
This was interesting - could be a technique for use in generating unexpected use cases, scenarios, outcomes etc (in other fields)
010
Adrian Chan @gravity7.bsky.social · 20/11/2024
UXers, Designers... What to make of these AI-generated conversational personas, intended to allow creators more insight into their audiences by conversing with agents about their content. arxiv.org/abs/2408.109... #ux #AI #design
Conversational AI personas
120