wilhelm____
ChatGPT Can Determine Your Age Indirectly
AI Evaluation via an AI Led Turing Test (A Proposal)
Ask HN: Examples of LLM agents submitting queries to a website's search bar?
Emergence in LLMs
Part of the reason I wrote this is to separate the signal from the noise and why one should be {cautiously, more tempered} optimistic in the medium term.
SFT and RLHF is attempting to further guide the model in terms of steerability + alignment of output.
In fact, the InstructGPT authors were worried about losing the pre-trained model's underlying probability distribution, so they try a version where it penalizes the model deviating too significantly from the original distribution (using KL). I don't remember them seeing a significant difference in performance.
What We Know About LLMs (A Primer)
Intraday financial data visualization tool
Trading algo visual debugging tool
Show HN: The “tl;dr” of Recent Transformer Papers
"TL;DR" on Recent Transformers Papers
With the explosion in research on all things transformers, it seemed there was a need to have a single table to distill the "tl;dr" of each paper's contributions relative to each other. Here is what I got so far: https://github.com/will-thompson-k/tldr-transformers . Would love feedback - and feel free to contribute too :)