Using Haiku many of the answers which should be incorrect are now correct on first pass. Exercises likely need to be updated.

Open
#86 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
3/5
Estimated time
1-2 days
Newbie friendliness
48/100
Issue type
Bug
Clarity
Mostly clear
Activity status
Quiet
Tech stack
jupyter-notebook
Domain
content

Research direction

Review the Lesson 3 logic problem and Lesson 4 name/signature examples described in the issue, then reproduce them with claude-3-haiku-20240307. Identify which exercise expectations no longer distinguish incorrect answers and update the affected exercise content so the intended reasoning and answers are reliably evaluated.

Written by the indexing model from the issue text.

Description

Examples include lesson 4 not putting in "Dear Claude" but rather "Dear [your Name] " still wrong since it signs with [Your Name] as well.
Lesson 3. the logic problem "Jack is looking at Anne. Anne is looking at George. Jack is married, George is not, and we don’t know if Anne is married. Is a married person looking at an unmarried person?" it gets it correct the first time but with poor rationale.
Says its using model claude-3-haiku-20240307

Dominant language
Jupyter Notebook
Stars
39.5k
Forks
4.4k
PR merge metrics
No merged PRs in 30d

Getting set up

This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from anthropics/prompt-eng-interactive-tutorial

All issues in anthropics/prompt-eng-interactive-tutorial

Similar issues

More Content issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.