jinhangjiang

gpu_info = !nvidia-smi
gpu_info = '\n'.join(gpu_info)
if gpu_info.find('failed') >= 0:
  print('Not connected to a GPU')
else:
  print(gpu_info)

nikvdp

# make sure you have `tac` [1] (if on on macOS) and `atuin` [2] installed, then drop the below in your ~/.zshrc
#
# [1]: https://unix.stackexchange.com/questions/114041/how-can-i-get-the-tac-command-on-os-x
# [2]: https://github.com/ellie/atuin 

atuin-setup() {
  ! hash atuin && return
  bindkey '^E' _atuin_search_widget

  export ATUIN_NOBIND="true"

veekaybee

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

charlesfrye

See rune2e.sh for info on how to run the experiment.

hamelsmu

Generating Synthetic Data for LLM Evaluation

Summary

1. Use your application extensively to build intuition about failure modes
2. Define 3-4 dimensions based on observed or anticipated failures
3. Create structured tuples covering your priority failure scenarios
4. Generate natural language queries from each tuple using a separate LLM call
5. Scale to more examples across your most important failure hypotheses (we suggest at least ~100)
6. Test and iterate on the most critical failure modes first, and generate more until you reach theoretical saturation