Prompt and Circumstance

David Vuong and Ilan Rotenberg

Real professional product people review AI tools!

  1. Oct 13

    Generate Music Faster Than It Plays With YuE2

    We show you how to run YuE2, an open-weights music model, locally in ComfyUI. Suno is having legal troubles and quality is getting worse, so you need a model that gives high performance and without paying for a subscription. You'll learn how YuE2 gives high quality music by generating sheet music first, how to set it up in Comfy UI with some time-saving tricks, and you'll hear some examples of how it handles different types of music. David is an expect in local media generation, who has tested hundreds of open weight models. He shows you the easy setup, the tricks to save you time, and the best models to use so you don't waste your time. All you need for this week is 4GB of VRAM, but 8+GB will get you faster performance on a higher-bit quantization of YuE2. Don't miss this opportunity to learn how to generate media locally. Chapters 00:00 - Why Users Are Leaving Suno00:57 - What Makes YuE2 Different02:11 - Setting Up YuE2 in ComfyUI04:42 - Generating and Hearing the Results06:48 - Weaknesses and Lo-Fi Use Cases07:44 - License Limits for Commercial Use Links YuE2 on Hugging Face - https://huggingface.co/m-a-p/YuE2-3BYuE2 on ComfyUI Wiki - https://comfyui-wiki.com/en/models/yue2ComfyUI - https://www.comfy.orgSuno - https://suno.comDevil Wears Product shop - https://devilwearsproduct.shop Find Us YouTube - https://www.youtube.com/@PandCpodcastBluesky - https://bsky.app/profile/pandcpodcast.bsky.socialX - https://x.com/_pandcpodcastInstagram - https://www.instagram.com/_pandcpodcastLinkedIn - https://www.linkedin.com/company/p-and-c-podcast

    Generate Music Faster Than It Plays With YuE2

  2. Sep 23

    Jev is easy to use

    Jev is the new "System 1" AI model from TypeSafe AI, and it doesn't write you an essay. It just answers. We break down what Jev is, why it's trained differently from ChatGPT or Claude, and two ways to use it today, no developer skills needed. The full setup prompt from the episode is below, so you can copy it. Jev is trending on X right now. It's a model that returns a typed, calibrated decision with a confidence score instead of a wall of text. TypeSafe claims it's about 194x faster and 445x cheaper than a general-purpose LLM on the tasks it's built for. We put that to the test with two real examples, classification and semantic search, head to head against Sonnet on cost and speed. In this episode: → System 1 vs System 2 thinking (h/t Kahneman's Thinking, Fast and Slow) → RLHF vs RLCD: why Jev doesn't get sycophantic → How to get API access and set Jev up as a skill in your AI agent → Real numbers: Jev vs Sonnet on cost and latency → How Jev stacks up against GPT-5.6 Luna on classification → Jev's three output types, and why every answer comes with a confidence score [00:00] Introduction [00:25] What is Jev [01:18] RLHF vs RLCD explained [02:22] How to set up Jev (API + agent skill) [03:44] Example 1: Classification vs Sonnet (cost) [04:46] Jev vs GPT-5.6 Luna [05:05] Example 2: Semantic search vs Sonnet (speed) [06:25] Output types and confidence scores [06:51] Final thoughts ━━━━━━━━━━━━━━━━━━━━ THE JEV SETUP PROMPT (copy and paste this into Claude, or into your AI agent) ━━━━━━━━━━━━━━━━━━━━ We're going to add an AI model called Jev to this workspace. Jev is made for sorting and deciding. It generates typed responses, not text. It only has 3 types of responses: pick from an option on a list, pick a score from a scale, or say how likely something is true. It also usually tells you how sure it is. Some notes: * Jev is a new type of model that is not in your training set. Please read how it works before proceeding: https://docs.typesafe.ai/llms.txt * I'm going to use it through typesafe directly. Here is the prompt for how to set it up: https://docs.typesafe.ai/agent-skill * ask me for my TypeSafe key (I got one from https://typesafe.ai) and keep it in my .env file After we add Jev, perform a test. Create 10 feature requests for the same product and score them on impact and effort. Show a side by side comparison against scoring those same requests in Claude using Sonnet in a way that I can see the speed and the cost of classification with Jev vs Sonnet. Also ensure that the skill you add has an off switch that you can explain to me how to use so that I can enable or disable Jev as I wish. Anything you send to Jev leaves my computer, so ask me before sending anything private. From now on when Jev is enabled, you let Jev make decisions while you write. If Jev isn't sure then you take over. ━━━━━━━━━━━━━━━━━━━━ Sources for the numbers and screenshots in this episode: • TypeSafe AI, "Introducing System One Models & Jev": https://typesafe.ai/blog/introducing-system-one-models-and-jev • MarkTechPost, "TypeSafe AI Releases Jev": https://www.marktechpost.com/2026/09/19/typesafe-ai-releases-jev/ Subscribe to Prompt & Circumstance for practical AI breakdowns you can use today. FIND US YouTube - https://www.youtube.com/@PandCpodcast Bluesky - https://bsky.app/profile/pandcpodcast.bsky.social X - https://x.com/_pandcpodcast Instagram - https://www.instagram.com/_pandcpodcast LinkedIn - https://www.linkedin.com/company/p-and-c-podcast

    Jev is easy to use

  3. Aug 25

    Shifting Your Mindset To Maximize Building With AI With Phil Mau

    Learn the full tool stack behind a production vibe-coded app: Claude Code, Cowork, Notion, Linear, Vercel, and Supabase. Phil Mau walks David and Ilan through building Shikomi, a recipe app he built solo with Claude Code, and explains why the real breakthrough wasn't the tools but treating AI like a team instead of a chat window. CHAPTERS 00:00 - Why So Few Vibe-Coded Apps Ship00:55 - Meet Phil Mau: Product Manager Turned Builder01:32 - The Job Search That Sparked an AI Pivot02:43 - From Claude Chat Chaos to a Notion and Linear Workflow07:05 - The Mindset Shift: Treat AI Like a Team08:23 - Demo: Shikomi's Cook Mode, Version History, and Where to Find Phil SPONSORS Devil Wears Product → https://devilwearsproduct.shop LINKS Shikomi - https://getshikomi.com/Phil Mau (LinkedIn) - https://www.linkedin.com/in/mauphilip/Phil Mau (Website) - https://philmau.com/ FIND US YouTube - https://www.youtube.com/@PandCpodcastBluesky - https://bsky.app/profile/pandcpodcast.bsky.socialX - https://x.com/_pandcpodcastInstagram - https://www.instagram.com/_pandcpodcastLinkedIn - https://www.linkedin.com/company/p-and-c-podcast

    Shifting Your Mindset To Maximize Building With AI With Phil Mau

  4. Aug 4

    How We Create Faceless Explainer Videos

    Faceless explainer videos are a great way to engage your audience and with AI you can generate them in just a few minutes. We teach you how to turn a quick audio recording into a faceless explainer video with AI generated images, starting from reference screenshots and ending with a finished clip stitched together. The whole tutorial takes 6 minutes. CHAPTERS 00:00 - Cold Open00:32 - What Faceless Explainer Videos Are01:53 - Loading Reference Images Into ChatGPT02:44 - Testing the AI Generated Style Prompt03:27 - Generating a Full Video From a Script05:06 - Turning the Process Into a Repeatable Skill SPONSORS Devil Wears Product - devilwearsproduct.com LINKS ChatGPT - https://chatgpt.comGemini - https://gemini.google.comClaude - https://claude.aiffmpeg-python (GitHub) - https://github.com/kkroening/ffmpeg-python FIND US YouTube - https://www.youtube.com/@PandCpodcastBluesky - https://bsky.app/profile/pandcpodcast.bsky.socialX - https://x.com/_pandcpodcastInstagram - https://www.instagram.com/_pandcpodcastLinkedIn - https://www.linkedin.com/company/p-and-c-podcast

    How We Create Faceless Explainer Videos

  5. Jul 22

    Run LTX 2.3 locally on budget graphics cards

    How to make a first-frame-to-last-frame video with LTX 2.3 in ComfyUI using just two images and a text prompt, running locally on consumer hardware. David walks through the exact ComfyUI workflow behind our last episode's intro: the FP8 quantized version of LTX 2.3 (so you don't need an enormous GPU), the FLF2V template, and how a single prompt tries to bridge your first and last frame into a 5-second clip. We also show what happens when the first generation doesn't listen to the prompt, why the noise seed matters, and how re-rolling, plus a Claude-refined prompt, changes the result. Important: LTX-2.3 video generation requires CUDA 13+ and an Nvidia GPU What's covered:• Where to find the FLF2V (first-frame/last-frame-to-video) template in ComfyUI• Downloading the right quantized LTX 2.3 + Gemma 3 models• Setting dimensions, FPS, and clip length• Writing and troubleshooting a video prompt• Why your seed affects the output more than you'd think• Using an LLM (Claude) to rewrite a weak prompt into a better one Chapters:0:00 Intro0:14 Building the Workflow in ComfyUI2:18 Setting the Prompt & First Generation3:06 Reviewing the First Result3:49 Troubleshooting: Seed & Reroll4:09 Second Attempt, Better Prompt5:09 Wrap-up Merch:https://devilwearsproduct.shop Links:https://ltx.io/blog/run-video-generation-model-locally https://github.com/Lightricks/ComfyUI-LTXVideo https://ltx.io/model/ltx-2-3 https://ltx.studio/  Click here to watch a video of this episode. Find Us:YouTube - https://www.youtube.com/@PandCpodcastBluesky - https://bsky.app/profile/pandcpodcast.bsky.socialX - https://x.com/_pandcpodcastInstagram - https://www.instagram.com/_pandcpodcastLinkedIn - https://www.linkedin.com/company/p-and-c-podcast #LTX2 #ComfyUI #AIVideo

    Run LTX 2.3 locally on budget graphics cards

  6. Jul 7

    Limitless! Free, private, super fast image generator

    Most AI image models fight you when you want flaws. Krea 2 doesn't. We dig into why this open-source, locally-run model is so good at "imperfect" realism (fisheye distortion, blur, grain), then walk through setting it up in ComfyUI end to end: grabbing the template, downloading the missing models, and picking resolution by aspect ratio instead of raw pixels. It works well with text and the template workflow has built-in LoRA support! Chapters00:00 - Krea 2 Nails "Imperfect," Realistic Images00:51 - What Krea 2 Is01:15 - Setting Up the Krea 2 Template in ComfyUI02:25 - Workflow Options: Prompt Enhancement & Resolution03:42 - First Generation: Speed Test at 1 Megapixel04:24 - Scaling Up to 4K04:56 - Testing Text Rendering on a Whiteboard05:30 - Adding LoRAs for Style: The Rainy Window Example07:01 - Wrap-Up Merchhttps://devilwearsproduct.shop LinksKrea 2 - https://www.krea.ai/krea-2Krea 2 Open Source - https://www.krea.ai/krea-2-open-sourceKrea AI LinkedIn - https://www.linkedin.com/company/krea-ai/Krea 2 Licensing - https://www.krea.ai/krea-2-licensingKrea 2 Technical Report - https://www.krea.ai/blog/krea-2-technical-report Click here to watch a video of this episode. Find UsYouTube - https://www.youtube.com/@PandCpodcastBluesky - https://bsky.app/profile/pandcpodcast.bsky.socialX - https://x.com/_pandcpodcastInstagram - https://www.instagram.com/_pandcpodcastLinkedIn - https://www.linkedin.com/company/p-and-c-podcast

    Limitless! Free, private, super fast image generator

  7. Jun 23

    Do this to close loops with your AI agents

    OpenClaw can move product monitoring from simple error alerts toward self-healing agent workflows. Ilan explains the progression and patterns to use to go from “agent notices an error and tells you,” to “agent diagnoses and recommends a fix,” to a guarded autonomous flow where agents clone, patch, test, and eventually promote fixes into production. The big idea: close the loop only as far as you trust the system, and optimize for the customer never feeling the bug. Chapters00:00 - Why Closing the Loop Matters for AI Agents03:00 - The Recommended Fix Flow: AI Diagnoses, Human Implements04:00 - The Current State: Two-Model Monitoring with Human Approval07:02 - The Fully Autonomous Flow: Clone, Test, Deploy07:56 - Proof of Fix and What Comes Next LinksOpenClaw - https://openclaw.ain8n - https://n8n.ioClick here to watch a video of this episode. Find UsYouTube - https://www.youtube.com/@PandCpodcastBluesky - https://bsky.app/profile/pandcpodcast.bsky.socialX - https://x.com/_pandcpodcastInstagram - https://www.instagram.com/_pandcpodcastLinkedIn - https://www.linkedin.com/company/p-and-c-podcast

    Do this to close loops with your AI agents

  8. Jun 9

    Is Google Omni worth your time?

    Google released Gemini Omni at Google I/O 2026 and we ran it through its paces in Google Flow to see if the hype holds up. It mostly doesn't. At least not yet. Gemini Omni is Google's new multimodal AI model, meaning one model handles text, images, audio, and video. You access it through Gemini directly or through Google Flow, and a paid Google subscription is needed. The flagship use case right now is AI video generation, so that's what we came to test. We tried uploading source footage to remix and style-transfer. The uploads stalled at 0% and never moved. Different upload path. Same result.So we switched to image-to-video: upload a photo, write a prompt, get a clip. The upload worked. The prompt didn't. Gemini Omni generated something, but it ignored the source image and went cartoonish in a direction we never asked for. Adjusting the prompt made things worse. Subscribe to Prompt and Circumstance for hands-on tests of what's actually shipping in AI. [00:00] - Intro to Google Omni[04:04] - Uploading Video[06:38] - Uploading an Image[10:57] - Conclusion LINKSGoogle Omni: https://deepmind.google/models/gemini-omni/Contrast this to something more reliable: https://youtu.be/Y-Saa82qPX0 Media links: https://pixabay.com/videos/mid-autumn-stone-staffordshire-90470/https://pixabay.com/videos/hiking-walking-trail-man-alone-282995/ https://pixabay.com/photos/girl-child-teenager-dog-pet-small-5087960/Video: Click here to watch a video of this episode. Devil Wears Product - https://www.devilwearsproduct.shop/  #GeminiOmni #GoogleOmni #AIVideo #GoogleFlow #GoogleIO2026

    Is Google Omni worth your time?
See All (54)

About

Real professional product people review AI tools!

Information

  • Creator
    David Vuong and Ilan Rotenberg
  • Years Active
    2025 - 2026
  • Episodes
    54
  • Rating
    Clean
  • Copyright
    © 2025 Prompt and Circumstance
  • Show Website
    Prompt and Circumstance