llms-as-method-actors

Name: llms-as-method-actors
Author: colindoyle0000

46stars3forks

How to install llms-as-method-actors?

colindoyle0000/llms-as-method-actors

$git clone https://github.com/colindoyle0000/llms-as-method-actors

Installs into the current project.

Summary

Official implementation for paper LLMs as Method Actors: A Model for Prompt Engineering and Architecture with code, prompts, and sample outputs.

Files · 1

View on GitHub

README.md

1	# Official Repo of LLMs as Method Actors
2
3	Official implementation for paper [LLMs as Method Actors: A Model for Prompt Engineering and Architecture](https://arxiv.org/abs/2411.05778) with code, prompts, and sample outputs.
4
5	## Setup
6
7	1. Setup your API key
8
9	Store your OpenAI API key in environment variable ``OPENAI_API_KEY``. (To learn more about setting up an OpenAI API key, follow [this link](https://help.openai.com/en/articles/5112595-best-practices-for-api-key-safety)). If you would like to use Anthropic or Gemini models, store those keys in environmental variables ``ANTHROPIC_API_KEY`` and ``GEMINI_API_KEY``.
10
11	2. Install the necessary packages
12
13	```bash
14	pip install -r requirements.txt
15	```
16
17	This will install all dependencies listed in `requirements.txt`.
18
19	## Tutorials
20
21	The Jupyter notebook tutorial.ipynb can walk you through how to run each of the approaches from the paper on any Connections puzzle.
22
23	## Sample Outputs
24
25	Sample outputs for each of the approaches are available in the “sample_outputs” folder as markdown files. For the more complicated approaches, markdown files are included that track the intermediary progress for each guess that was considered. Markdown files named “summary” and “summary_detailed” summarize the overall outcome and the results of the intermediary steps.
26
27	The sample outputs were created by running the python scripts on the Connections puzzle from the day that the paper was announced on arXiv.org, November 11, 2024.
28
29	The results were as follows:
30
31	\| Approach \| Success? \| # Correct Guesses \| # Incorrect Guesses \|
32	\| --------------------------- \| -------- \| ----------------- \| ------------------- \|
33	\| Vanilla \| No \| 0 \| 4 \|
34	\| Chain-of-Thought \| No \| 1 \| 4 \|
35	\| Chain-of-Thought (Scripted) \| Yes \| 4 \| 3 \|
36	\| Actor \| Yes \| 4 \| 0 \|
37	\| Actor-2 \| Yes \| 4 \| 1 \|
38	\| Oneshot-o1 \| No \| 2 \| 2 \|
39	\| Vanilla-o1 \| Yes \| 4 \| 0 \|
40	\| Actor-o1 \| Yes \| 4 \| 0 \|
41
42	## Citations
43
44	Please cite the paper and star this repo if you find it interesting or useful. Feel free to contact colin.doyle@lls.edu if you have any questions.
45
46	```bibtex
47	@misc{doyle2024method,
48	title={LLMs as Method Actors: A Model for Prompt Engineering and Architecture},
49	author={Colin Doyle},
50	year={2024},
51	eprint={2411.05778},
52	archivePrefix={arXiv},
53	primaryClass={cs.CL}
54	}
55	```

People who liked this also viewed

6 picks

Type

model-alignmentModel Alignment is a python library from the PAIR team that enable users to create model prompts through user feedback instead of manual prompt writing and editing. The technique makes use of constitutional principles to align prompts to users' desired values.PromptsOct 202521239
prompt-decoratorsA standardized framework for enhancing how LLMs process and respond to prompts through composable decorators, featuring an official open standard specification and Python reference implementation. Claude Code plugin and MCP server integration.PromptsJul 202617742
tree-promptTree prompting: easy-to-use scikit-learn interface for improved prompting.PromptsOct 20232342
claudifyAI-powered Spotify playlist generator using Claude API. Create personalized playlists from text prompts or transform your liked songs into curated collections. Seamlessly blends AI creativity with music discovery.PromptsJul 20241729
system-prompts-and-models-of-ai-toolsFULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI ModelsPromptsJul 2026—142k
CL4R1T4SLEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐PromptsJul 2026—46k

llms-as-method-actors

46stars3forks

View on GitHub

How to install llms-as-method-actors?

colindoyle0000/llms-as-method-actors

$git clone https://github.com/colindoyle0000/llms-as-method-actors

Installs into the current project.

Summary

Official implementation for paper LLMs as Method Actors: A Model for Prompt Engineering and Architecture with code, prompts, and sample outputs.

Files · 1

View on GitHub

README.md

1	# Official Repo of LLMs as Method Actors
2
3	Official implementation for paper [LLMs as Method Actors: A Model for Prompt Engineering and Architecture](https://arxiv.org/abs/2411.05778) with code, prompts, and sample outputs.
4
5	## Setup
6
7	1. Setup your API key
8
9	Store your OpenAI API key in environment variable ``OPENAI_API_KEY``. (To learn more about setting up an OpenAI API key, follow [this link](https://help.openai.com/en/articles/5112595-best-practices-for-api-key-safety)). If you would like to use Anthropic or Gemini models, store those keys in environmental variables ``ANTHROPIC_API_KEY`` and ``GEMINI_API_KEY``.
10
11	2. Install the necessary packages
12
13	```bash
14	pip install -r requirements.txt
15	```
16
17	This will install all dependencies listed in `requirements.txt`.
18
19	## Tutorials
20
21	The Jupyter notebook tutorial.ipynb can walk you through how to run each of the approaches from the paper on any Connections puzzle.
22
23	## Sample Outputs
24
25	Sample outputs for each of the approaches are available in the “sample_outputs” folder as markdown files. For the more complicated approaches, markdown files are included that track the intermediary progress for each guess that was considered. Markdown files named “summary” and “summary_detailed” summarize the overall outcome and the results of the intermediary steps.
26
27	The sample outputs were created by running the python scripts on the Connections puzzle from the day that the paper was announced on arXiv.org, November 11, 2024.
28
29	The results were as follows:
30
31	\| Approach \| Success? \| # Correct Guesses \| # Incorrect Guesses \|
32	\| --------------------------- \| -------- \| ----------------- \| ------------------- \|
33	\| Vanilla \| No \| 0 \| 4 \|
34	\| Chain-of-Thought \| No \| 1 \| 4 \|
35	\| Chain-of-Thought (Scripted) \| Yes \| 4 \| 3 \|
36	\| Actor \| Yes \| 4 \| 0 \|
37	\| Actor-2 \| Yes \| 4 \| 1 \|
38	\| Oneshot-o1 \| No \| 2 \| 2 \|
39	\| Vanilla-o1 \| Yes \| 4 \| 0 \|
40	\| Actor-o1 \| Yes \| 4 \| 0 \|
41
42	## Citations
43
44	Please cite the paper and star this repo if you find it interesting or useful. Feel free to contact colin.doyle@lls.edu if you have any questions.
45
46	```bibtex
47	@misc{doyle2024method,
48	title={LLMs as Method Actors: A Model for Prompt Engineering and Architecture},
49	author={Colin Doyle},
50	year={2024},
51	eprint={2411.05778},
52	archivePrefix={arXiv},
53	primaryClass={cs.CL}
54	}
55	```

People who liked this also viewed

6 picks

Type