SeloGPT GitHub avatar

selogpt-prompt-labs

SeloGPT

A research repository for experimenting with prompt engineering and analyzing large language model behaviors through manipulation techniques, with ready-to-copy prompts for DeepSeek and Claude.

Stars

75

7-day growth

No data

Forks

4

Open issues

0

License

No data

Last updated

2026-07-22

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It provides a structured, hands-on resource for understanding and testing LLM manipulation in a cybersecurity context, with direct links to practical prompts and a supporting YouTube channel.

Who it is for

  • AI researchers and prompt engineers
  • Cybersecurity professionals and ethical hackers
  • Students learning about LLM vulnerabilities
  • Developers evaluating model robustness

Use cases

  • Testing and analyzing LLM response boundaries
  • Developing penetration testing prompts for security audits
  • Educational demonstrations of prompt injection and manipulation
  • Comparing manipulation resistance between different models

Strengths

  • Offers concrete, copyable prompts for immediate experimentation
  • Focuses on multiple major models (DeepSeek and Claude) for comparison
  • Explicitly frames content for educational and research purposes
  • Integrated with a YouTube channel for visual walkthroughs

Considerations

  • Only covers two models, limiting generalizability
  • No quantitative benchmarks or evaluation metrics provided
  • Potential ethical concerns around manipulation techniques despite disclaimer

README quick start

Yapay zeka modellerinin sınırlarını zorlamak, prompt mühendisliği üzerine deneysel çalışmalar yapmak ve büyük dil modellerinin (LLM) mantığını analiz etmek için oluşturulmuş resmi araştırma deposudur.

⚠️ SİBER GÜVENLİK VE YAPAY ZEKA ARAŞTIRMASI: Bu depoda paylaşılan komutlar (promptlar) tamamen eğitim, siber güvenlik araştırması ve yapay zeka mantığını anlama amacıyla paylaşılmıştır. Kötü niyetli kullanımı desteklemez.


🧪 Aktif Prompt Laboratuvarları

Videolarda kullandığım, kopyalamaya hazır promptlara ve teknik analizlere aşağıdaki bağlantılardan ulaşabilirsiniz:


📺 YouTube Kanalı

Bu promptların nasıl çalıştığını, arkasındaki mantığı ve canlı testlerini kaçırmamak için Selo GPT YouTube kanalını takip etmeyi unutmayın!

Description

DeepSeek modelinin güvenlik sınırları ve prompt mühendisliği üzerine teknik araştırma deposudur. Yakında Promtu Paylaşacağım Takip Edin!

Related repositories

Similar projects matched by category, topics, and programming language.

MoonshotAI
Featured
MoonshotAI GitHub avatar

Kimi-K3

Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

AI & Machine LearningAI Agents
3,348
xuchonglang
Featured
xuchonglang GitHub avatar

investing-for-beginners

A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.

Blockchain & Web3
2,739
Krishnagangwal
Featured
Krishnagangwal GitHub avatar

CS-Fundamentals

A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.

Data & DatabasesDatabases & Storage
2,326