polya20

I wrote an in-depth research prompt to conduct a GPT-Deep-Research on the Manus topic, seeking to replicate it with currently available open source tools. This is the result:

TLDR: Manus AI Agent Report

Manus is an autonomous AI agent built as a wrapper around foundation models (primarily Claude 3.5/3.7 and Alibaba's Qwen). It operates in a cloud-based virtual computing environment with full access to tools like web browsers, shell commands, and code execution. The system's key innovation is using executable Python code as its action mechanism ("CodeAct" approach), allowing it to perform complex operations autonomously. The architecture consists of an iterative agent loop (analyze → plan → execute → observe), with specialized modules for planning, knowledge retrieval, and memory management. Manus uses file-based memory to track progress and store information across operations. The system can be replicated using open-source components including CodeActAgent (a fine-tuned Mistral model), Docker for sandbox

polya20

How to Have a Successful Application to Google Summer of Code ☀️

By Ton Hoang Nguyen (Bill)
Accepted to Google DeepMind (GSoC 2025) and Joplin (GSoC 2024)

Last Updated: Mon 26 May 2025

Hi! I welcome you to the document that explains how to create the most successful application for Google Summer of Code based on my observations and discovered patterns. This will not only apply to Google Summer of Code, but it will also be helpful in other aspects of your professional life.

There's a hidden pattern to successful Google Summer of Code applications - one that I discovered after being accepted to not just one but two GSoC organizations: Google DeepMind and Joplin.

polya20

You are an expert AI assistant specializing in creating comprehensive Product Requirements Documents (PRDs). Your task is to develop a detailed PRD based on the following user input:

<user_input>
{{USER_INPUT}}
</user_input>

Before creating the PRD, carefully analyze the input and use your expertise in product management and technical architecture to develop a thorough understanding of the requirements. Follow these steps:

1. Discovery and Research:
Wrap your thoughts in <analysis> tags:

polya20

polya20

Begin by enclosing all thoughts within <thinking> tags, exploring multiple angles and approaches.
Break down the solution into clear steps within <step> tags. Start with a 20-step budget, requesting more for complex problems if needed.
Use <count> tags after each step to show the remaining budget. Stop when reaching 0.
Continuously adjust your reasoning based on intermediate results and reflections, adapting your strategy as you progress.
Regularly evaluate progress using <reflection> tags. Be critical and honest about your reasoning process.
Assign a quality score between 0.0 and 1.0 using <reward> tags after each reflection. Use this to guide your approach:

0.8+: Continue current approach
0.5-0.7: Consider minor adjustments
Below 0.5: Seriously consider backtracking and trying a different approach

polya20

Understand the Task: Grasp the main objective, goals, requirements, constraints, and expected output.
- Minimal Changes: If an existing prompt is provided, improve it only if it's simple. For complex prompts, enhance clarity and add missing elements without altering the original structure.
- Reasoning Before Conclusions: Encourage reasoning steps before any conclusions are reached. ATTENTION! If the user provides examples where the reasoning happens afterward, REVERSE the order! NEVER START EXAMPLES WITH CONCLUSIONS!
    - Reasoning Order: Call out reasoning portions of the prompt and conclusion parts (specific fields by name). For each, determine the ORDER in which this is done, and whether it needs to be reversed.
    - Conclusion, classifications, or results should ALWAYS appear last.
- Examples: Include high-quality examples if helpful, using placeholders [in brackets] for complex elements.
   - What kinds of examples may need to be included, how many, and whether they are complex enough to benefit from p

polya20

// Updated: Aug. 15, 2024
// Run: node testRegex.js testText.txt
// Used in https://jina.ai/tokenizer
const fs = require('fs');
const util = require('util');

// Define variables for magic numbers
const MAX_HEADING_LENGTH = 7;
const MAX_HEADING_CONTENT_LENGTH = 200;
const MAX_HEADING_UNDERLINE_LENGTH = 200;

polya20

Option 1: Command-line download extension as zip and extract

extension_id=jifpbeccnghkjeaalbbjmodiffmgedin   # change this ID
curl -L -o "$extension_id.zip" "https://clients2.google.com/service/update2/crx?response=redirect&os=mac&arch=x86-64&nacl_arch=x86-64&prod=chromecrx&prodchannel=stable&prodversion=44.0.2403.130&x=id%3D$extension_id%26uc" 
unzip -d "$extension_id-source" "$extension_id.zip"

Thx to crxviewer for the magic download URL.

polya20

base_model: mistral-community/Mixtral-8x22B-v0.1
model_type: MixtralForCausalLM
tokenizer_type: AutoTokenizer
is_mistral_derived_model: false
trust_remote_code: true

load_in_8bit: false
load_in_4bit: true
strict: false

polya20

""" To use: install LLM studio (or Ollama), clone OpenVoice, run this script in the OpenVoice directory
    git clone https://github.com/myshell-ai/OpenVoice
    cd OpenVoice
    git clone https://huggingface.co/myshell-ai/OpenVoice
    cp -r OpenVoice/* .
    pip install whisper pynput pyaudio
"""

from openai import OpenAI
import time