Interestingly the post implies at least one obvious security countermeasure for me personally and, thinking how I’d implement it, I immediately thought “Actually who cares; Claude will implement it after being told to look at the post.”
@patio11
-
LLMs Capture Tacit Knowledge in Organizations
By
–
We have an understanding that standard management approaches do not capture "tacit knowledge" / process knowledge and that this is frequently encoded in e.g. network graphs within firms, individuals' own heads, etc without being recorded. LLMs: Recording. You're welcome.
-
The inevitable shift to LLM-assisted professional writing
By
–
There will be a last day on which a policy brief, Supreme Court opinion, draft bill, etc is written without LLM assistance. That last day is much sooner than people in DC model it as being. Get your weights in good while it’s still underappreciated how much they matter.
-
The debate over whether LLMs possess genuine understanding
By
–
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.”
-
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.