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 · 25/04/2025This 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... 010
Adrian Chan @gravity7.bsky.social · 27/02/2025Yes ... 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 010
Adrian Chan @gravity7.bsky.social · 20/02/2025Compare 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 020
Adrian Chan @gravity7.bsky.social · 28/01/2025During 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 · 07/01/2025Using #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 030
Adrian Chan @gravity7.bsky.social · 22/12/2024Cold, quiet, and wet out. Today might be the day for Satantango. #filmsky 000
Adrian Chan @gravity7.bsky.social · 20/12/2024User 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 000
Adrian Chan @gravity7.bsky.social · 16/12/2024Had 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 020
Adrian Chan @gravity7.bsky.social · 14/12/2024Watched 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 · 13/12/2024Trust 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 010
Adrian Chan @gravity7.bsky.social · 06/12/2024Great 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 000
Adrian Chan @gravity7.bsky.social · 04/12/2024Known 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 · 03/12/2024This 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 · 20/11/2024UXers, 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 120