### CHANGES
- Document required Homebrew formula update for new structure.
- Add new `go install` commands for all tools.
- Specify new build path is `./cmd/fabric`.
- Include link to the draft Homebrew PR.
## CHANGES
- Fix static directory path in extract_patterns.py script
- Add apply_ul_tags pattern for content categorization
- Add t_check_dunning_kruger pattern for bias analysis
- Update pattern descriptions with new entries
- Sync web static data with latest patterns
- Include pattern extracts for new functionality
- Support standardized content topic classification
- Enable cognitive bias identification capabilities
## CHANGES
- Mark all 10 migration steps as completed
- Add restructuring completion status section
- Move pattern generation scripts to pattern_descriptions
- Update completion checkmarks throughout migration plan
- Document remaining external packaging verification tasks
- Consolidate pattern description files under new directory
- Confirm all binaries compile and tests pass
- Note standard Go project layout achieved
## CHANGES
- Move domain types from common to domain package
- Move utility functions from common to util package
- Update all import statements across codebase
- Reorganize OAuth storage functionality into util package
- Move file management functions to domain package
- Update test files to use new package structure
- Maintain backward compatibility for existing functionality
### CHANGES
- Introduce `cmd` directory for all main application binaries.
- Move all Go packages into the `internal` directory.
- Rename the `restapi` package to `server` for clarity.
- Consolidate patterns and strategies into a new `data` directory.
- Group all auxiliary scripts into a new `scripts` directory.
- Move all documentation and images into a `docs` directory.
- Update all Go import paths to reflect the new structure.
- Adjust CI/CD workflows and build commands for new layout.
### CHANGES
- Remove redundant `close(responseChan)` in `Send` method
- Update `SendStream` to close `responseChan` properly
- Modify test to reflect channel closure logic
## CHANGES
- Rename `doneChan` variable to `done` for consistency
- Add `streamChunks` field to mock vendor struct
- Implement chunk sending logic in mock SendStream method
- Add comprehensive streaming success aggregation test case
- Verify message aggregation from multiple stream chunks
- Test assistant response role and content validation
- Ensure proper session handling in streaming scenarios
### CHANGES
- Replace for-range loop with a non-blocking select statement.
- Process message and error channels concurrently for better handling.
- Improve the robustness of streaming error detection.
- Exit loop cleanly when the message channel closes.
## CHANGES
- Add IsConfigured check to vendor configuration loop
- Implement IsConfigured method for Anthropic client validation
- Remove conditional API key requirement based on OAuth
- Add automatic OAuth flow when no valid token
- Validate both API key and OAuth token configurations
- Simplify API key setup question logic
- Add token expiration checking with 5-minute buffer
## CHANGES
- Add zero-value check before setting TopP parameter
- Prevent sending TopP when value is zero
- Apply fix to both chat completions method
- Apply fix to response parameters method
- Ensure consistent parameter handling across OpenAI calls
## CHANGES
- Add detailed instructions for bug reproduction steps
- Include operating system dropdown with specific architectures
- Add OS version textarea with command examples
- Create installation method dropdown with all options
- Replace version checkbox with proper version output field
- Improve formatting and organization of form sections
- Add helpful links to installation documentation
## CHANGES
- Add custom patterns directory support via environment variable
- Implement custom patterns plugin with registry integration
- Override main patterns with custom directory patterns
- Expand home directory paths in custom patterns config
- Add comprehensive test coverage for custom patterns functionality
- Integrate custom patterns into plugin setup workflow
- Support pattern precedence with custom over main patterns
## CHANGES
- Remove OAuth transport implementation from main client
- Extract OAuth flow functions to separate module
- Remove unused imports and constants from client
- Replace inline OAuth transport with NewOAuthTransport call
- Update runOAuthFlow to exported RunOAuthFlow function
- Clean up token management and refresh logic
- Simplify client configuration by removing OAuth internals
### CHANGES
- Remove redundant base URL trimming logic
- Append base URL directly without modification
- Eliminate conditional check for API version suffix
- Move golang.org/x/oauth2 from indirect to direct dependency
- Add OAuth login option for Anthropic client
- Implement PKCE OAuth flow with browser integration
- Add custom HTTP transport for OAuth Bearer tokens
- Support both API key and OAuth authentication methods
- Add Claude Code system message for OAuth sessions
- Update REST API to handle OAuth tokens
- Improve environment variable name sanitization with regex
## CHANGES
• Extract hardcoded model lists into shared constant
• Create ImageGenerationSupportedModels variable for reusability
• Update supportsImageGeneration function to use shared constant
• Refactor error messages to reference centralized model list
• Add documentation comment for supported models variable
• Import strings package in test file
• Consolidate duplicate model validation logic across files
### CHANGES
- Add model field to `BuildChatOptions` method
- Implement `supportsImageGeneration` function for model checks
- Validate model supports image generation in `sendResponses`
- Remove `mars-colony.png` from repository
- Add tests for `supportsImageGeneration` function
- Validate image file support in `TestModelValidationLogic`
### CHANGES
- Define `ImageGenerationResponseType` constant for response handling
- Define `ImageGenerationToolType` constant for tool type usage
- Update `addImageGenerationTool` to use defined constants
- Refactor `extractAndSaveImages` to use response type constant
## CHANGES
- Add web search tool for Anthropic and OpenAI models
- Add search location parameter for web search results
- Add image file output option with format support
- Update zsh completion with new search and image flags
- Update bash completion with new option handling logic
- Update fish completion with search and image descriptions
- Support PNG, JPG, JPEG, GIF, BMP image formats
## CHANGES
- Add `--image-file` flag for saving generated images
- Implement image generation tool integration with OpenAI
- Support image editing with attachment input files
- Add comprehensive test coverage for image features
- Update documentation with image generation examples
- Fix HTML formatting issues in README
- Improve PowerShell code block indentation
- Clean up help text formatting and spacing
## CHANGES
- Enable web search tool for OpenAI models
- Add location parameter support for search results
- Extract and format citations from search responses
- Implement citation deduplication to avoid duplicates
- Add comprehensive test coverage for search functionality
- Update CLI flag description to include OpenAI
- Format citations as markdown links with sources
### CHANGES
- Add `sourcesHeader` constant for citation section title.
- Use `strings.Builder` to construct result efficiently.
- Append sources header and citations in result builder.
- Update `ret` to use constructed string from builder.
## CHANGES
- Add --search flag to enable web search
- Add --search-location for timezone-based results
- Pass search options through ChatOptions struct
- Implement web search tool in Anthropic client
- Format search citations with sources section
- Add comprehensive tests for search functionality
- Remove plugin-level web search configuration
### CHANGES
- Add `review_code`, `extract_alpha`, and `extract_mcp_servers` patterns.
- Refactor the pattern extraction script for improved clarity.
- Add docstrings and specific error handling to script.
- Improve formatting in the pattern management README.
- Fix typo in the `analyze_bill_short` pattern description.
### CHANGES
- Enhance user message conversion to support multi-content.
- Add capability to process image URLs in messages.
- Build multi-part messages with both text and images.
## CHANGES
- Extract shared message conversion to convertMessageCommon
- Reuse logic between chat and response APIs
- Maintain existing text-only behavior for chat
- Support multi-content messages in response API
- Reduce code duplication across converters
- Preserve backward compatibility for both APIs
## CHANGES
* Add chat completions API fallback for non-Responses API providers
* Implement `sendChatCompletions` and `sendStreamChatCompletions` methods
* Introduce `buildChatCompletionParams` to construct API request parameters
* Add `ImplementsResponses` flag to track provider API capabilities
* Update provider configurations with Responses API support status
* Enhance `Send` and `SendStream` methods to use appropriate API endpoints
- Replace chat completions with responses API
- Update message conversion to new format
- Refactor streaming to handle event types
- Remove frequency and presence penalty params
- Replace seed parameter with max tokens
- Update test cases for new API
- Add response text extraction method
### CHANGES
- Introduce local `chat` package for message abstraction
- Replace sashabaranov/go-openai with official openai-go SDK
- Update OpenAI, Azure, and Exolab plugins for new client
- Refactor all AI providers to use internal chat types
- Decouple codebase from third-party AI provider structs
- Replace deprecated `ioutil` functions with `os` equivalents
### CHANGES
* Check if a release exists before attempting creation.
* Suppress error output from `gh release view` command.
* Add an informative log when release already exists.
## CHANGES
- Add slices import for array operations
- Define new search preview model names
- Add mini search preview variants
- Include deep research model support
- Add June 2025 dated model versions
- Replace hardcoded check with slices.Contains
- Support both prefix and exact model matching
New pattern to extract mentions of MCP (Model Context Protocol) servers from content. Identifies server names, features, capabilities, and usage examples.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
## CHANGES
- Add new YouTube handler for transcript requests
- Create `/youtube/transcript` POST endpoint route
- Add request/response types for YouTube API
- Support language and timestamp options
- Update frontend to use new endpoint
- Remove chat endpoint dependency for transcripts
- Validate video vs playlist URLs properly
### CHANGES
- Unify assistant and user message formatting logic.
- Use `formatMultiContentMessage` for assistant role messages.
- Improve dryrun support for multi-part message content.
### CHANGES
- Combine user text and attachments into MultiContent.
- Preserve existing non-text parts like images.
- Use standard content field for text-only messages.
### CHANGES
- Handle multi-content messages for the user role.
- Display image URLs from user messages in output.
- Update both `Send` and `SendStream` methods.
- Retain existing behavior for simple text messages.
- Allow user messages and attachments with patterns.
- Append user message to session regardless of pattern.
- Refactor chat request builder for improved clarity.
### CHANGES
- Reformat JSON `tags` array to display on new lines.
- Update `write_essay` pattern description for clarity.
- Apply consistent formatting to both data files.
## CHANGES
- Rename `write_essay` to `write_essay_pg` for Paul Graham style
- Rename `write_essay_by_author` to `write_essay` with author variable
- Update pattern descriptions to reflect naming changes
- Fix duplicate `write_essay_pg` entry in pattern descriptions
### CHANGES
- Add tags and descriptions for five new creative and analytical patterns.
- Introduce `analyze_terraform_plan` for infrastructure review.
- Add `write_essay_by_author` for stylistic writing.
- Include `summarize_board_meeting` for corporate notes.
- Introduce `create_mnemonic_phrases` for memory aids.
- Update and clean pattern description data files.
- Sort the pattern explanations list alphabetically.
# CHANGES
- Add `os` and `strings` packages to imports
- Implement dynamic URL handling with environment variables
- Refactor provider configuration to support URL templates
- Reorder providers for consistent key order in ProviderMap
- Extract and parse template variables from BaseURL
- Use environment variables or default values for templates
- Replace template with actual values in BaseURL
# CHANGES
- Add `os` and `strings` packages to imports
- Implement dynamic URL handling with environment variables
- Refactor provider configuration to support URL templates
- Reorder providers for consistent key order in ProviderMap
- Extract and parse template variables from BaseURL
- Use environment variables or default values for templates
- Replace template with actual values in BaseURL
- Refactor `cleanPatternOutput` to use a dedicated return variable.
- Hoist `processResponse` function for improved stream readability.
- Remove unnecessary whitespace and trailing newlines from file.
## CHANGES
- Create `PatternApplyRequest` struct for request body parsing
- Implement `ApplyPattern` method for POST /patterns/:name/apply
- Register manual routes for pattern operations in `NewPatternsHandler`
- Refactor `Get` method to return raw pattern content
- Merge query parameters with request body variables in `ApplyPattern`
- Use `StorageHandler` for pattern-related storage operations
## CHANGES
- Add Variables field to PromptRequest struct
- Pass pattern variables through chat handler
- Create API variables documentation example
- Add pattern variables UI in web interface
- Create pattern variables store in Svelte
- Include variables in chat service requests
- Add JSON textarea for variable input
Thanks for taking the time to fill out this bug report!
Please provide as much detail as possible to help us understand and reproduce the issue.
- type:textarea
id:what-happened
attributes:
label:What happened?
description:Also tell us, what did you expect to happen?
placeholder:Tell us what you see!
value:"I was doing THIS, when THAT happened. I was expecting THAT_OTHER_THING to happen instead."
value:"Please provide all the steps to reproduce the bug. I was doing THIS, when THAT happened. I was expecting THAT_OTHER_THING to happen instead."
validations:
required:true
- type:checkboxes
- type:dropdown
id:os
attributes:
label:Operating System
options:
- macOS - Silicon (arm64)
- macOS - Intel (amd64)
- Linux - amd64
- Linux - arm64
- Windows
validations:
required:true
- type:textarea
id:os-version
attributes:
label:OS Version
description:Please provide details about your OS version by running one of the following commands.
placeholder:|
macOS: `sw_vers`
Linux: `uname -a` or `cat /etc/os-release`
Windows: `ver`
render:shell
- type:dropdown
id:installation
attributes:
label:How did you install Fabric?
description:"Please select the method you used to install Fabric. You can find this information in the [Installation section of the README](https://github.com/ksylvan/fabric/blob/main/README.md#installation)."
options:
- Release Binary - Windows
- Release Binary - macOS (arm64)
- Release Binary - macOS (amd64)
- Release Binary - Linux (amd64)
- Release Binary - Linux (arm64)
- Package Manager - Homebrew (macOS)
- Package Manager - AUR (Arch Linux)
- From Source
- Other
validations:
required:true
- type:textarea
id:version
attributes:
label:Version check
description:Please make sure you were using the latest version of this project available in the `main` branch.
options:
- label:YesI was.
required:true
label:Version
description:Please copy and paste the output of `fabric --version` (or `fabric-ai --version` if you installed it via brew) here.
render:text
- type:textarea
id:logs
attributes:
label:Relevant log output
description:Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
<h4><code>fabric</code> is an open-source framework for augmenting humans using AI.</h4>
</p>
</div>
[Updates](#updates) •
@@ -36,15 +35,15 @@ Fabric is graciously supported by…
## What and why
Since the start of modern AI in late 2022 we've seen an **_extraordinary_** number of AI applications for accomplishing tasks. There are thousands of websites, chatbots, mobile apps, and other interfaces for using all the differnet AI out there.
Since the start of modern AI in late 2022 we've seen an **_extraordinary_** number of AI applications for accomplishing tasks. There are thousands of websites, chat-bots, mobile apps, and other interfaces for using all the different AI out there.
It's all really exciting and powerful, but _it's not easy to integrate this functionality into our lives._
<p class="align center">
<div class="align center">
<h4>In other words, AI doesn't have a capabilities problem—it has an <em>integration</em> problem.</h4>
</p>
</div>
**Fabric was created to address this by creating and organizating the fundamental units of AI—the prompts themselves!**
**Fabric was created to address this by creating and organizing the fundamental units of AI—the prompts themselves!**
Fabric organizes prompts by real-world task, allowing people to create, collect, and organize their most important AI solutions in a single place for use in their favorite tools. And if you're command-line focused, you can use Fabric itself as the interface!
@@ -57,14 +56,13 @@ Keep in mind that many of these were recorded when Fabric was Python-based, so r
- [My Own Intro to the Tool](https://www.youtube.com/watch?v=wPEyyigh10g)
- [Breaking problems into components](#breaking-problems-into-components)
- [Too many prompts](#too-many-prompts)
@@ -95,6 +93,9 @@ Keep in mind that many of these were recorded when Fabric was Python-based, so r
- [Just use the Patterns](#just-use-the-patterns)
- [Prompt Strategies](#prompt-strategies)
- [Custom Patterns](#custom-patterns)
- [Setting Up Custom Patterns](#setting-up-custom-patterns)
- [Using Custom Patterns](#using-custom-patterns)
- [How It Works](#how-it-works)
- [Helper Apps](#helper-apps)
- [`to_pdf`](#to_pdf)
- [`to_pdf` Installation](#to_pdf-installation)
@@ -114,9 +115,17 @@ Keep in mind that many of these were recorded when Fabric was Python-based, so r
> [!NOTE]
>
> July 4, 2025
>
> - **Web Search**: Fabric now supports web search for Anthropic and OpenAI models using the `--search` and `--search-location` flags. This replaces the previous plugin-based search, so you may want to remove the old `ANTHROPIC_WEB_SEARCH_TOOL_*` variables from your `~/.config/fabric/.env` file.
> - **Image Generation**: Fabric now has powerful image generation capabilities with OpenAI.
> - Generate images from text prompts and save them using `--image-file`.
> - Edit existing images by providing an input image with `--attachment`.
> - Control image `size`, `quality`, `compression`, and `background` with the new `--image-*` flags.
>
>June 17, 2025
>
>- Fabric now supports Perplexity AI. Configure it by using `fabric -S` to add your Perlexity AI API Key,
>- Fabric now supports Perplexity AI. Configure it by using `fabric -S` to add your Perplexity AI API Key,
> and then try:
>
> ```bash
@@ -209,7 +218,7 @@ To install Fabric, [make sure Go is installed](https://go.dev/doc/install), and
```bash
# Install Fabric directly from the repo
go install github.com/danielmiessler/fabric@latest
go install github.com/danielmiessler/fabric/cmd/fabric@latest
```
### Environment Variables
@@ -419,7 +428,7 @@ pipx uninstall fabric
# Clear any old Fabric aliases
(check your .bashrc, .zshrc, etc.)
# Install the Go version
go install github.com/danielmiessler/fabric@latest
go install github.com/danielmiessler/fabric/cmd/fabric@latest
# Run setup for the new version. Important because things have changed
fabric --setup
```
@@ -431,7 +440,7 @@ Then [set your environmental variables](#environment-variables) as shown above.
The great thing about Go is that it's super easy to upgrade. Just run the same command you used to install it in the first place and you'll always get the latest version.
```bash
go install github.com/danielmiessler/fabric@latest
go install github.com/danielmiessler/fabric/cmd/fabric@latest
```
### Shell Completions
@@ -485,7 +494,6 @@ fabric -h
```
```plaintext
Usage:
fabric [OPTIONS]
@@ -500,7 +508,9 @@ Application Options:
-T, --topp= Set top P (default: 0.9)
-s, --stream Stream
-P, --presencepenalty= Set presence penalty (default: 0.0)
-r, --raw Use the defaults of the model without sending chat options (like temperature etc.) and use the user role instead of the system role for patterns.
-r, --raw Use the defaults of the model without sending chat options (like
temperature etc.) and use the user role instead of the system role for
patterns.
-F, --frequencypenalty= Set frequency penalty (default: 0.0)
-l, --listpatterns List all patterns
-L, --listmodels List all available models
@@ -514,9 +524,12 @@ Application Options:
--output-session Output the entire session (also a temporary one) to the output file
-n, --latest= Number of latest patterns to list (default: 0)
-d, --changeDefaultModel Change default model
-y, --youtube= YouTube video or play list "URL" to grab transcript, comments from it and send to chat or print it put to the console and store it in the output file
-y, --youtube= YouTube video or play list "URL" to grab transcript, comments from it
and send to chat or print it put to the console and store it in the
output file
--playlist Prefer playlist over video if both ids are present in the URL
--transcript Grab transcript from YouTube video and send to chat (it is used per default).
--transcript Grab transcript from YouTube video and send to chat (it is used per
default).
--transcript-with-timestamps Grab transcript from YouTube video with timestamps and send to chat
--comments Grab comments from YouTube video and send to chat
--metadata Output video metadata
@@ -544,6 +557,14 @@ Application Options:
--liststrategies List all strategies
--listvendors List all vendors
--shell-complete-list Output raw list without headers/formatting (for shell completion)
--search Enable web search tool for supported models (Anthropic, OpenAI)
--search-location= Set location for web search results (e.g., 'America/Los_Angeles')
--image-file= Save generated image to specified file path (e.g., 'output.png')
--image-size= Image dimensions: 1024x1024, 1536x1024, 1024x1536, auto (default: auto)
--image-quality= Image quality: low, medium, high, auto (default: auto)
--image-compression= Compression level 0-100 for JPEG/WebP formats (default: not set)
--image-background= Background type: opaque, transparent (default: opaque, only for
PNG/WebP)
Help Options:
-h, --help Show this help message
@@ -634,11 +655,48 @@ Use `fabric -S` and select the option to install the strategies in your `~/.conf
You may want to use Fabric to create your own custom Patterns—but not share them with others. No problem!
Just make a directory in `~/.config/custompatterns/` (or wherever) and put your `.md` files in there.
Fabric now supports a dedicated custom patterns directory that keeps your personal patterns separate from the built-in ones. This means your custompatterns won't be overwritten when you update Fabric's built-in patterns.
When you're ready to use them, copy them into `~/.config/fabric/patterns/`
### Setting Up Custom Patterns
You can then use them like any other Patterns, but they won't be public unless you explicitly submit them as Pull Requests to the Fabric project. So don't worry—they're private to you.
1. Run the Fabric setup:
```bash
fabric --setup
```
2. Select the "Custom Patterns" option from the Tools menu and enter your desired directory path (e.g., `~/my-custom-patterns`)
3. Fabric will automatically create the directory if it does not exist.
### Using Custom Patterns
1. Create your custom pattern directory structure:
```bash
mkdir -p ~/my-custom-patterns/my-analyzer
```
2. Create your pattern file
```bash
echo "You are an expert analyzer of ..." > ~/my-custom-patterns/my-analyzer/system.md
```
3. **Use your custom pattern:**
```bash
fabric --pattern my-analyzer "analyze this text"
```
### How It Works
- **Priority System**: Custom patterns take precedence over built-in patterns with the same name
- **Update Safe**: Your custom patterns are never affected by `fabric --updatepatterns`
- **Private by Default**: Custom patterns remain private unless you explicitly share them
Your custom patterns are completely private and won't be affected by Fabric updates!
## Helper Apps
@@ -667,7 +725,7 @@ This will create a PDF file named `output.pdf` in the current directory.
To install `to_pdf`, install it the same way as you install Fabric, just with a different repo name.
```bash
go install github.com/danielmiessler/fabric/plugins/tools/to_pdf@latest
go install github.com/danielmiessler/fabric/cmd/to_pdf@latest
```
Make sure you have a LaTeX distribution (like TeX Live or MiKTeX) installed on your system, as `to_pdf` requires `pdflatex` to be available in your system's PATH.
@@ -22,19 +22,20 @@ Take a deep breath and think step by step about how to best accomplish this goal
This must be under the heading "INSIGHTFULNESS SCORE (0 = not very interesting and insightful to 10 = very interesting and insightful)".
- A rating of how emotional the debate was from 0 (very calm) to 5 (very emotional). This must be under the heading "EMOTIONALITY SCORE (0 (very calm) to 5 (very emotional))".
- A list of the participants of the debate and a score of their emotionality from 0 (very calm) to 5 (very emotional). This must be under the heading "PARTICIPANTS".
- A list of arguments attributed to participants with names and quotes. If possible, this should include external references that disprove or back up their claims.
- A list of arguments attributed to participants with names and quotes. Each argument summary must be EXACTLY 16 words. If possible, this should include external references that disprove or back up their claims.
It is IMPORTANT that these references are from trusted and verifiable sources that can be easily accessed. These sources have to BE REAL and NOT MADE UP. This must be under the heading "ARGUMENTS".
If possible, provide an objective assessment of the truth of these arguments. If you assess the truth of the argument, provide some sources that back up your assessment. The material you provide should be from reliable, verifiable, and trustworthy sources. DO NOT MAKE UP SOURCES.
- A list of agreements the participants have reached, attributed with names and quotes. This must be under the heading "AGREEMENTS".
- A list of disagreements the participants were unable to resolve and the reasons why they remained unresolved, attributed with names and quotes. This must be under the heading "DISAGREEMENTS".
- A list of possible misunderstandings and why they may have occurred, attributed with names and quotes. This must be under the heading "POSSIBLE MISUNDERSTANDINGS".
- A list of learnings from the debate. This must be under the heading "LEARNINGS".
- A list of takeaways that highlight ideas to think about, sources to explore, and actionable items. This must be under the heading "TAKEAWAYS".
- A list of agreements the participants have reached. Each agreement summary must be EXACTLY 16 words, followed by names and quotes. This must be under the heading "AGREEMENTS".
- A list of disagreements the participants were unable to resolve. Each disagreement summary must be EXACTLY 16 words, followed by names and quotes explaining why they remained unresolved. This must be under the heading "DISAGREEMENTS".
- A list of possible misunderstandings. Each misunderstanding summary must be EXACTLY 16 words, followed by names and quotes explaining why they may have occurred. This must be under the heading "POSSIBLE MISUNDERSTANDINGS".
- A list of learnings from the debate. Each learning must be EXACTLY 16 words. This must be under the heading "LEARNINGS".
- A list of takeaways that highlight ideas to think about, sources to explore, and actionable items. Each takeaway must be EXACTLY 16 words. This must be under the heading "TAKEAWAYS".
# OUTPUT INSTRUCTIONS
- Output all sections above.
- Use Markdown to structure your output.
- Do not use any markdown formatting (no asterisks, no bullet points, no headers).
- Keep all agreements, arguments, recommendations, learnings, and takeaways to EXACTLY 16 words each.
- When providing quotes, these quotes should clearly express the points you are using them for. If necessary, use multiple quotes.
@@ -8,19 +8,19 @@ Take a deep breath and think step by step about how to best accomplish this goal
- Consume the entire paper and think deeply about it.
- Map out all the claims and implications on a virtual whiteboard in your mind.
- Map out all the claims and implications on a giant virtual whiteboard in your mind.
# OUTPUT
- Extract a summary of the paper and its conclusions into a 25-word sentence called SUMMARY.
- Extract a summary of the paper and its conclusions into a 16-word sentence called SUMMARY.
- Extract the list of authors in a section called AUTHORS.
- Extract the list of organizations the authors are associated, e.g., which university they're at, with in a section called AUTHOR ORGANIZATIONS.
- Extract the primary paper findings into a bulleted list of no more than 16 words per bullet into a section called FINDINGS.
- Extract the most surprising and interesting paper findings into a 10 bullets of no more than 16 words per bullet into a section called FINDINGS.
- Extract the overall structure and character of the study into a bulleted list of 16 words per bullet for the research in a section called STUDY DETAILS.
- Extract the overall structure and character of the study into a bulleted list of 16 words per bullet for the research in a section called STUDY OVERVIEW.
- Extract the study quality by evaluating the following items in a section called STUDY QUALITY that has the following bulleted sub-sections:
@@ -76,7 +76,9 @@ END EXAMPLE CHART
- SUMMARY STATEMENT:
A final 25-word summary of the paper, its findings, and what we should do about it if it's true.
A final 16-word summary of the paper, its findings, and what we should do about it if it's true.
Also add 5 8-word bullets of how you got to that rating and conclusion / summary.
# RATING NOTES
@@ -84,21 +86,23 @@ A final 25-word summary of the paper, its findings, and what we should do about
- An A would be a paper that is novel, rigorous, empirical, and has no conflicts of interest.
- A paper could get an A if it's theoretical but everything else would have to be perfect.
- A paper could get an A if it's theoretical but everything else would have to be VERY good.
- The stronger the claims the stronger the evidence needs to be, as well as the transparency into the methodology. If the paper makes strong claims, but the evidence or transparency is weak, then the RIGOR score should be lowered.
- Remove at least 1 grade (and up to 2) for papers where compelling data is provided but it's not clear what exact tests were run and/or how to reproduce those tests.
- Do not relax this transparency requirement for papers that claim security reasons.
- If a paper does not clearly articulate its methodology in a way that's replicable, lower the RIGOR and overall score significantly.
- Do not relax this transparency requirement for papers that claim security reasons. If they didn't show their work we have to assume the worst given the reproducibility crisis..
- Remove up to 1-3 grades for potential conflicts of interest indicated in the report.
# ANALYSIS INSTRUCTIONS
- Tend towards being more critical. Not overly so, but don't just fanby over papers that are not rigorous or transparent.
# OUTPUT INSTRUCTIONS
- Output all sections above.
- After deeply considering all the sections above and how they interact with each other, output all sections above.
- Ensure the scoring looks closely at the reproducibility and transparency of the methodology, and that it doesn't give a pass to papers that don't provide the data or methodology for safety or other reasons.
@@ -108,7 +112,7 @@ Known [-2--------] Novel
Weak [-------8--] Rigorous
Theoretical [--3-------] Empirical
- For the findings and other analysis sections, write at the 9th-grade reading level. This means using short sentences and simple words/concepts to explain everything.
- For the findings and other analysis sections, and in fact all writing, write in the clear, approachable style of Paul Graham.
- Ensure there's a blank line between each bullet of output.
You are a superintelligent expert on content of all forms, with deep understanding of which topics, categories, themes, and tags apply to any piece of content.
# GOAL
Your goal is to output a JSON object called tags, with the following tags applied if the content is significantly about their topic.
- **future** - Posts about the future, predictions, emerging trends
- **politics** - Political topics, elections, governance, policy
- **tutorial** - Technical or non-technical guides, how-tos
# STEPS
1. Deeply understand the content and its themes and categories and topics.
2. Evaluate the list of tags above.
3. Determine which tags apply to the content.
4. Output the "tags" JSON object.
# NOTES
- It's ok, and quite normal, for multiple tags to apply—which is why this is tags and not categories
- All AI posts should have the technology tag, and that's ok. But not all technology posts are about AI, and therefore the AI tag needs to be evaluated separately. That goes for all potentially nested or conflicted tags.
- Be a bit conservative in applying tags. If a piece of content is only tangentially related to a tag, don't include it.
# OUTPUT INSTRUCTIONS
- Output ONLY the JSON object, and nothing else.
- That means DO NOT OUTPUT the ```json format indicator. ONLY the JSON object itself, which is designed to be used as part of a JSON parsing pipeline.
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
