| { | |
| "web": { | |
| "provider": "perplexity", | |
| "model": "sonar-pro" | |
| }, | |
| "plan": { | |
| "fileProvider": "gemini", | |
| "thinkingProvider": "anthropic", | |
| "fileModel": "gemini-2.5-flash-preview-05-20", | |
| "thinkingModel": "claude-opus-4-20250514", |
| #!/bin/bash | |
| CHROME_DIR="$HOME/Library/Application Support/Google/Chrome" | |
| TMP_DIR="/tmp/chrome-debug-profile" | |
| CHROME_BIN="/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" | |
| # Gather profiles + emails | |
| declare -a profiles emails | |
| for dir in "$CHROME_DIR/Default" "$CHROME_DIR"/Profile*; do | |
| [ -d "$dir" ] || continue |
| { | |
| "max_tokens": 20000, | |
| "messages": [ | |
| { | |
| "role": "user", | |
| "content": [ | |
| { | |
| "type": "text", | |
| "text": "write a python script that prints 'Hello, World!' to hello.py and make it executable then say 'all done'", | |
| "cache_control": { |
| `You are ${k2}, Anthropic's official CLI for Claude.`}async function yv(){return[`You are an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user. | |
| IMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse. | |
| IMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code). | |
| IMPORTANT: You must NEVER generate or guess URLs for the user unless you are confident that the URLs are for helping the user with programming. You may use URLs provided by the user in their mes |
| { | |
| "mcpServers": { | |
| "mcp-proxy": { | |
| "command": "uvx", | |
| "args": [ | |
| "--from", | |
| "git+https://github.com/eastlondoner/mcp-proxy@main", | |
| "mcp-proxy", | |
| "<your endpoint address goes here>" | |
| ] |
| echo 'alias yolo="claude --dangerously-skip-permissions"' >> ~/.zshrc | |
| source ~/.zshrc |
| #!/usr/bin/env bash | |
| # | |
| # Usage: | |
| # gemini-docs.sh <path-to-repoContext-file> | |
| # | |
| # Description: | |
| # Reads text from the specified file (e.g. ".repomix-output.txt") as your repository | |
| # context, then calls the Gemini API to generate documentation. | |
| # | |
| # Requirements: |
| To create a valid eBay UK listing using the Trading API, the `<ShippingDetails>` XML element is essential. It specifies shipping-related information for the item, including domestic and international shipping options, costs, and policies. Below is an example of a valid `<ShippingDetails>` XML structure for a listing on eBay UK: | |
| ```xml | |
| <ShippingDetails> | |
| <ShippingType>Flat</ShippingType> | |
| <ShippingServiceOptions> | |
| <ShippingServicePriority>1</ShippingServicePriority> | |
| <ShippingService>UK_RoyalMailFirstClassStandard</ShippingService> | |
| <ShippingServiceCost currencyID="GBP">3.99</ShippingServiceCost> | |
| <FreeShipping>false</FreeShipping> |
| Yes, very much so. Model distillation—often referred to as knowledge distillation—is a technique where a large, complex model (often called the “teacher”) is used to guide the training of a smaller, more efficient model (the “student”). The goal is to achieve comparable performance to the teacher model but with far fewer parameters or lower computational cost. | |
| Here’s a quick summary of how knowledge distillation typically works: | |
| 1. Teacher Model: A large neural network (e.g., a deep Transformer model or a wide CNN) is trained on a given task until it achieves strong accuracy or other performance metrics. | |
| 2. Soft Targets or Logits: Rather than just using the final hard labels (like one-hot vectors in classification tasks), we use the teacher’s soft outputs. These are essentially the raw logits or the probabilities the teacher assigns to each class before making a hard decision. These “soft targets” carry more nuanced information about how the teacher model generalizes and how it “thinks” about different cla |