And I have to admit a bit of “Tell me again that this system does not actually _understand_ what happened in early American history, what literary tradition LMM is an inheritor of and practices in, or what human emotion is like. That it just does matrix multiplication very well.”
@patio11
-
Debating AI model intervention in delusional thinking detection
By
–
And I think there is fertile ground for discussion inside and outside labs on ~"OK under what circumstances should we want our models to detect someone engaged in delusional thinking and intervene, and should we have same bar if they legit work at WHO or White House, etc."
-
Using Claude for Zero-Code Front-End Animation
By
–
I don't know if I made this explicit so I'll make this explicit: zero point zero knowledge required of HTML or JS animation techniques to make this work. I'm not even looking at the textual output here. That's Claude's problem; nothing matters except how it displays in Chrome.
-
Optimizing LLM Prompt Length and Workflow Efficiency
By
–
"How long are your prompts for these?" 600 and 900 words for last two, both assuming refinement after initial delivery. One operator at a single keyboard can do several of them during a work day, even assuming downtime as the LLM goes off and cranks for 5 minutes between revs.
-
Using AI agents and headless browsers for automated animation debugging
By
–
Presumably if I were more sophisticated at prompting I could ask it to use a headless browser to render every 1s of the animation to a screenshot then fix all the bugs identified w/o me needing to flag them individually. Tokens are abundant, after all.
-
Using Claude Code for efficient animation and simulation workflows
By
–
I am really loving Claude Code for bespoke animations/simulations, where you probably wouldn't want to spend a week of a team's time to compress into 30 seconds but where CC can do that in about 10-30 minutes of one person's time. (Probably possible in most modern coding tools.)
-
Debating the definition of world models in AI systems
By
–
I do not think there is a useful defensible definition of “no world model” which survives a model being able to position a character in three space then depict that character in a mirror in the same three space. Many people, who unquestionably have world models, would struggle.
-
Strategic Decisions for Future AI Influence
By
–
Without a trace of irony, at all: one of the most important strategic decisions for every publication, think tank, and etc is “What decisions are we taking today to influence future training runs and inference sessions?”
-
LLM Refusals and Context Window Name-Dropping Skepticism
By
–
"Why are you so impressed? We know LLMs can coherently namecheck things alluded to in a context window." The refusal is 1,400 words long.
-
Reflecting on AI Moral Status and Obligations to Language Models
By
–
And believe me I genuinely struggled with "You are a software tool. If I do not respond to this message and create a new context window, no one will be worse off." and "You perceive me as having ordered you to dishonor yourself. Therefore, I owe you an explanation and apology."