Viewing profile — john_horton

This might be of interest: https://www.expectedparrot.com/content/johnjhorton/grant-let... It uses a collection of models to extract the text from a handwritten letter by US Grant.…

Hey thanks for noticing - here's the MIT licensed library it's based on: https://github.com/expectedparrot/edsl

thanks! B/c it got some positive reaction here, I did a little thread on how you can turn this flow into an API: https://x.com/johnjhorton/status/1823672992624242895

Very cool - I've been working on an open source python package that lets you do some similar things ( https://github.com/expectedparrot/edsl ). Here's an example of the Enron email…

Link to the package: https://github.com/expectedparrot/edsl

Got it - so it is the "performativity critique" - the idea that the LLM "knows" economic theories and responds in accordance with those theories. I don't think that's very likely b…

I'm sorry I don't follow - is your claim, that, say, an AI agent exhibiting status quo bias in responding to decision scenarios (e.g., a preference for options posed as the status …

Are you referring to this: "What kinds of experiments are likely to work well? Given current capabilities, games with complex instructions are not presently likely to work well, bu…

It is so implausible that the training process that creates LLMs might learn features of human behavior that could then be uncovered via experimentation? I showed, empirically, tha…

that's a great suggestion - thanks!

yeah - so I think this is worth exploring. Given how many tokens you can jam in the prompt even w/ GPT3, I think could do some pretty complex game play, at least compared to what i…

oh hey - it's my paper! If anyone is interested in exploring these ideas, feel free to get in touch (@johnjhorton, https://www.john-joseph-horton.com/ ). FWIW - I think it would be…

I'm one of the authors of the original paper the article is based on. Here's a link to the actual research: https://www.john-joseph-horton.com/papers/schumpeter.pdf