Latest videos about Large Language Models (LLMs)
An ex-OpenAI researcher just deleted language from the LLM...
- **Jev: A New Frontier in AI Classification**: Jev is a novel AI model developed by an ex-OpenAI researcher, designed to be a faster, cheaper, and more efficient classifier than traditional large language models (LLMs). It achieves this by removing language from the model, focusing on type-safe, gut-instinct decisions. - **Addressing LLM Flaws**: Jev tackles the verbosity and cost issues of current LLMs by providing concise, structured outputs (choice, score, null) with guaranteed schema matching, making type errors mathematically impossible. This contrasts with LLMs that often generate lengthy, expensive responses. - **System One AI for Real-time Applications**: Described as a "system one model" (referencing Daniel Kahneman's "Thinking, Fast and Slow"), Jev excels at rapid, instinctual decisions. This makes it ideal for real-time applications like content moderation, NPC behavior in video games, and other scenarios requiring immediate, low-cost AI processing. - **Calibrated Confidence and Open-Source Alternatives**: Jev provides a "calibrated confidence number" for its responses, trained with RLCD (reinforcement learning for calibrated decisions), aiming for more reliable confidence metrics than human-pleasing LLMs. Despite its proprietary nature, open-source alternatives like "OpenJev" have emerged, demonstrating similar functionality using existing models like Qwen-4B. - **Sponsor: Mux for Video Infrastructure**: The video is sponsored by Mux, a platform that simplifies adding video features to applications. Mux offers an API for hosting, streaming, and advanced AI-powered workflows like transcription, moderation, and translation, automating video processing without requiring users to manage models or pipelines.
AI Agents For Beginners – OpenClaw Case Study
- This course offers a beginner-friendly, hands-on approach to building real AI agents, moving from LLM fundamentals to multi-agent systems without complex setup. - Led by Mumshed, founder of CodeCloud, the course emphasizes practical skills, culminating in a case study of OpenClaw, a production-inspired AI agent. - Participants will build four specialized AI agents (Zippy, Savvy, Meshy, Cody) to understand orchestration, research, memory, and coding capabilities. - The curriculum covers core AI concepts like LLM architecture (transformers, pre-training, generation), tokenization, temperature, context windows, and effective prompting techniques. - The course provides hands-on lab environments with pre-configured API keys and cloud sandboxes, allowing learners to focus purely on building and deploying AI agents.