Hoppa till innehållet
Global sound
Super Prompt: Building in the Era of AI Agents

Super Prompt: Building in the Era of AI Agents

av Tony Wan

Senaste avsnittet
AI Agents at Work: Scaffold Required

Om den här podden

AI agents are expanding what one person can build, operate, and own.

They lower the cost of building and operating while making scattered demand easier to reach. That changes the shape of ambition. A company need not be venture-shaped. It can be founder-shaped: focused, durable, and capable of changing its founder’s life without changing the world.

Super Prompt began by exploring how humans work with AI. Now we learn by building.

Avsnitt

De 20 senaste av 30 avsnitt

  • AI Agents at Work: Scaffold Required · 40 min · Säsong 2 Avsnitt 2We review four clips from the Dwarkesh Patel Podcast with Satya Nadella, Microsoft's CEO. I highly recommend Dwarkesh’s show—technical & nerdy, but excellent. Satya talks about…
  • Whose Agent Is It Anyways? · 16 min · Säsong 2 Avsnitt 1Description: AI agents from OpenAI, Google, and Anthropic promise to act on your behalf—booking flights, handling tasks, making decisions. What kind of agency do these systems…
  • AI Safety: Constitutional AI vs Human Feedback · 17 min · Säsong 1 Avsnitt 27With great power comes great responsibility. How do leading AI companies implement safety and ethics as language models scale? OpenAI uses Model Spec combined with RLHF…
  • Open Source LLMs: How Open Is "Open"? · 13 min · Säsong 1 Avsnitt 26Notable open source large language models from Meta, French AI company Mistral (valued at $2B), Microsoft, and Apple. Not all open source models are equally open—the restrictions…
  • Open Source AI: The Safety Debate · 16 min · Säsong 1 Avsnitt 25Why enterprises and entrepreneurs choose open source LLMs like Meta's Llama—cost-effectiveness, control, privacy, and security. The safety and ethics debate: which poses greater…
  • LLM Benchmarks: How to Know Which AI Is Better · 11 min · Säsong 1 Avsnitt 24Beyond ChatGPT and Gemini: Anthropic's Claude and the $4 billion Amazon investment. How AI industry benchmarks work, including LMSYS Arena Elo and MMLU (Measuring Massive…
  • Multimodal AI: When ChatGPT Learned to See · 10 min · Säsong 1 Avsnitt 23Recent updates from Google and OpenAI feature multimodal capabilities—AI that processes multiple input types simultaneously. Why multimodal models outperform single-modality…
  • Google Gemini: Three Models, One Strategy · 7 min · Säsong 1 Avsnitt 22Google's Gemini family of multimodal AI models compared to OpenAI equivalents. What Nano, Pro, and Ultra each do, how they compare to GPT-3.5, GPT-4, and ChatGPT, and what…
  • Building Custom GPTs: Seven Lessons from GPT Builder · 26 min · Säsong 1 Avsnitt 21Creating a travel planning AI using OpenAI's GPT Builder with no code. Seven takeaways from building a custom GPT, what the process reveals about prompt engineering, and the…
  • Enterprise LLMs: Cloud Deployment Strategy · 58 min · Säsong 1 Avsnitt 20Deploying large language models for enterprise applications. Rackspace CTO Jeff DeVerter discusses implementing Google PaLM for sales, enabling Azure and AWS customers, and why…
  • ChatGPT in the Classroom: Yale's Response · 1 h 34 min · Säsong 1 Avsnitt 19How is generative AI changing teaching, learning, and evaluation? Yale's Assistant Dean of Academic Affairs Alfred Guy discusses the university's AI guidance and its implications…
  • AI Screenwriting: GPT-4 Meets the Writers Strike · 33 min · Säsong 1 Avsnitt 18Creating a science fiction blockbuster pitch using ChatGPT power prompts: Role Play, Chain of Thought, and Self Critique. How these techniques improve output, and the AI-related…
  • ChatGPT Guardrails: The One Question It Won't Debate · 20 min · Säsong 1 Avsnitt 17Ask ChatGPT if it possesses human-like intelligence and you'll get a definitive "NO"—unusual for a system that typically provides balanced perspectives. This guardrail reveals…
  • ChatGPT vs The Onion: Can AI Get the Joke? · 16 min · Säsong 1 Avsnitt 16Does ChatGPT have a sense of humor? We test whether it would find an Onion headline funny: "Microsoft renames ChatGPT to ClippyChat." Large language models are better at…
  • ChatGPT Jailbreaks: The Grandma Exploit · 24 min · Säsong 1 Avsnitt 15How do you extract prohibited information from ChatGPT? Grandma and DAN exploits trick language models into violating their own policies. Why these techniques work, what they…
  • AI Hallucinations: Bug or Feature? · 23 min · Säsong 1 Avsnitt 14What are AI hallucinations, and should we consider them bugs or features? The top 10 categories of AI hallucinations with examples, how ChatGPT might hallucinate an answer about…
  • LLM Training: Superman's Kryptonite-Proof Suit · 19 min · Säsong 1 Avsnitt 13Why isn't Superman's suit Kryptonite-proof? This question reveals how large language models are trained. We break down transformers (the T in GPT), self-attention mechanisms, and…
  • Large Language Models: Getting from GPT-3 to chatGPT · 22 min · Säsong 1 Avsnitt 12How do ChatGPT, GPT-3, and Large Language Models relate to each other? We explore the hierarchy: artificial intelligence, neural networks, large language models, GPT-3, and…
  • What Is ChatGPT? Explained · 25 min · Säsong 1 Avsnitt 11How would you describe ChatGPT in your own words? This solo episode provides definition and context for newcomers to AI. I answer the question myself, then ask ChatGPT to…
  • DALL-E: Why AI Can't Make Your Perfect Pizza · 52 min · Säsong 1 Avsnitt 10Why is it so hard to get DALL-E to create the exact image you envision? PhD candidate and entrepreneur Arijit Ray discusses generative AI constraints, and his startup training AI…

Live, senaste timmen: 12 206 låtar på 5 060 stationer i 134 länder

Upptäck världen genom radion

Fler sätt att upptäcka (7)

Hört något bra? Spara det, eller öppna det direkt i Spotify.

★ Artist of the week The fastest riser on the radio this week
Your song here? From € 9 per week →
Радио Русские Песни | Russian Songs RadioFortsätt lyssna