This is not a terrible idea, if you view it as a tool for better meetings by making speaking imbalances clear. It reminds me of this experiment in VR designed to make you aware of conversational imbalances by having the words you speak literally pile up at your feet.
@emollick
-
Decision Making Rule for Entrepreneurs: Explore Then Execute
By
–
While this paper is about entrepreneurs, it it also gives a general rule for when it is time to stop exploring alternatives & start doing something: Explore until you find two equally good options. Then pick the one that matches your goals & get to work! https://
papers.ssrn.com/sol3/papers.cf
m?abstract_id=2844843
… -
Understanding LLM Behavior: Why Experts Still Have Knowledge Gaps
By
–
A reminder that even the best experts on LLMs don’t really understand all their behaviors (in this case, why AIs often seem a bit preachy & condescending). Lots left to learn.
-
H1-B Immigration Boosts Targeted Product Development Strategy
By
–
When companies hire H1-B immigrants at headquarters, their products aimed at the immigrants’ home counties become better targeted and specific, especially in food and beverages. Neat new paper.
-
Measuring LLM Abilities: Current Limitations and Testing Challenges
By
–
We don't know how to measure LLM abilities well. Most tests are groups of multiple choice questions, tasks, or trivia – they don't represent real world uses well, they are subject to gaming & results are impacted by prompt design in unknown ways. Or they use human preference.
-
Image Generation Bias Mitigation Through Prompt Injection Techniques
By
–
But as you know, image generation is a different technology with well-understood biases. The attempts to mitigate those with prompt injection is a common approach, even if Google did it badly. https://
bloomberg.com/graphics/2023-
generative-ai-bias/
… -
LLMs Don’t Have Political Opinions, Research Shows
By
–
Asking AIs for their political opinions is a hot topic, but this paper shows it can be misleading. LLMs don’t have them: “We found that models will express diametrically opposing views depending on minimal changes in prompt phrasing or situative context” https://
arxiv.org/html/2402.1678
6v1
… -
Correlation vs Accuracy in Big Five Personality Testing
By
–
Since it keeps coming up in the comments: correlation is not accuracy. More on the Big Five & other tests
-
Unsettling AI Prompt Engineering Science Fiction Story
By
–
An extremely unsettling science fiction story about prompting AI, told in the format of a Wikipedia article from the future (
@qntm is pretty good at unsettling science fiction stories). Also an absolutely amazing reference in the title. -
Do Frontier LLMs Actually Reason? New Evidence Suggests Yes
By
–
It is fascinating that, over a year after ChatGPT released, we still don't actually know when, if, and how well frontier LLMs "reason." There have been some papers suggesting limits to reasoning, but this new work finds that LLMs, while not as good as humans, can do reasoning. https://t.co/PlMiNE2RFJ
— Ethan Mollick (@emollick) 28 février 2024It is fascinating that, over a year after ChatGPT released, we still don't actually know when, if, and how well frontier LLMs "reason." There have been some papers suggesting limits to reasoning, but this new work finds that LLMs, while not as good as humans, can do reasoning.