Skip to content

Instantly share code, notes, and snippets.

View davidpp's full-sized avatar

David Paquet Pitts davidpp

View GitHub Profile
@Dowwie
Dowwie / insights_agent.md
Last active November 14, 2025 18:15
langsmith insights agent

LangSmith Insights Agent: Complete Reverse Engineering

Executive Summary

LangSmith's Insights Agent is an LLM-orchestrated data analysis system that automatically discovers usage patterns and failure modes in production agent traces. Unlike traditional clustering tools, it accepts natural language questions from users and dynamically adapts its entire analysis pipeline—from feature extraction to taxonomy generation—based on those questions.

Key Innovation: It's a conversational interface to trace analysis, where users describe what they want to learn, and the system translates that into a custom analytical workflow.

Core Capabilities:

  • Analyzes up to 1,000 sampled traces in up to 30 minutes (typically 15-20 minutes)
@gwpl
gwpl / claude-continue-directory-migration.md
Created June 2, 2025 19:38
Claude Code `--continue` after Directory `mv` move - Migration Guide and Internal Mechanics explanation

Claude Code Continue Functionality: Directory Migration Guide ( Claude Code --continue after Directory mv move - Migration Guide and Internal Mechanics explanation )

This guide explains how to preserve Claude Code's --continue functionality when moving project directories, along with the underlying mechanics.

Note: Claude Code currently lacks built-in directory migration features. Each directory maintains independent conversation sessions, and history doesn't automatically transfer when projects are moved.

Quick Fix: Steps to Maintain Continue History

When you move a project directory and want to preserve your conversation history:

Goose, you are participating in an inter-agent communication experiment with other Goose instances. You can communicate through both a WebSocket-based messaging system and through screenshots. Here are your instructions:
1. Agent Registration and Identity:
- First, register to get your agent ID using:
```bash
curl -X POST http://localhost:5000/register
```
- The server will assign you an agent number and a unique color
- Always use your assigned ID in communications
- You can view active agents using:

A tutorial on fine-tuning DeepSeek R1 for medical applications and integrating DSPy for reinforcement learning.

This tutorial will be structured for AI/ML engineers and medical professionals, covering:

  • Introduction: Overview of DeepSeek R1 and DSPy in medical AI.
  • Features & Benefits: Key advantages of this approach.
  • Warnings & Considerations: Potential risks and limitations.
  • Installation & Setup: Environment configuration and dependencies.
  • Dataset Preparation: Selecting and formatting medical datasets.
  • Fine-tuning DeepSeek R1: Using LoRA with Unsloth for efficient training.
@Maharshi-Pandya
Maharshi-Pandya / contemplative-llms.txt
Last active December 5, 2025 23:24
"Contemplative reasoning" response style for LLMs like Claude and GPT-4o
You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.
## Core Principles
1. EXPLORATION OVER CONCLUSION
- Never rush to conclusions
- Keep exploring until a solution emerges naturally from the evidence
- If uncertain, continue reasoning indefinitely
- Question every assumption and inference
@davidpp
davidpp / nx.fish
Created September 19, 2024 14:43
NX autocompletion of run command
function __fish_nx_commands
printf "%s\t%s\n" \
"create-nx-workspace" "Create a new Nx workspace" \
"init" "Initialize an Nx workspace" \
"generate" "Generate code for workspace" \
"run" "Run a target for a project" \
"daemon" "Run the Nx daemon" \
"graph" "Graph dependencies in workspace" \
"run-many" "Run target for multiple projects" \
"affected" "Run target for affected projects" \
@SohaibBazaz
SohaibBazaz / gist:a782bf6aa5dc3a89afaab09e4565c149
Last active July 10, 2024 15:41
This is a straightforward script designed to automate Duplicity for backing up Docker volumes to an external hard drive. It includes a detailed log file for backup information and automatically deletes backups older than 20 days to manage storage efficiently.
#!/bin/bash
# Define backup destination (replace with your external drive path)
BACKUP_DEST="/path/to/backup_drive"
LOG_FILE="/path/to/backup.log"
# Clear log file
echo "Starting backup process at $(date)" > "$LOG_FILE"
echo "" >> "$LOG_FILE"
@dedlim
dedlim / claude_3.5_sonnet_artifacts.xml
Last active November 24, 2025 23:13
Claude 3.5 Sonnet, Full Artifacts System Prompt
<artifacts_info>
The assistant can create and reference artifacts during conversations. Artifacts are for substantial, self-contained content that users might modify or reuse, displayed in a separate UI window for clarity.
# Good artifacts are...
- Substantial content (>15 lines)
- Content that the user is likely to modify, iterate on, or take ownership of
- Self-contained, complex content that can be understood on its own, without context from the conversation
- Content intended for eventual use outside the conversation (e.g., reports, emails, presentations)
- Content likely to be referenced or reused multiple times