Jev Live Demo, God's Eye View and First Build with Gemini 3.8 Live

The episode showed how quickly AI is moving beyond the familiar pattern of sending a prompt to one large model and waiting for an answer. It opened with evidence that Claude Fable 5.1 remains highly competitive with GPT-6 Astra for software engineering. The hosts discussed Nous Research using 1,393 Fable subagents to refactor the million-line Hermes codebase in 19 hours for roughly $25,000, along with a new private-code benchmark where Fable led the tested models. That moved into God's Eye View, an open-source spatial intelligence project that combines public sources such as flight data, cameras, satellite information, maps and other feeds.

The science discussion followed the same specialization theme. Periodic's Neon model reportedly outperformed general frontier models on materials-science analysis, while Google's Dream-RSI proposed a more efficient approach to recursive self-improvement by allowing an agent to use the history of previous discoveries to "dream" through promising possibilities instead of evaluating every candidate from scratch.

The centerpiece came when Brian demonstrated JEV, TypeSafe's new System One decision model. Unlike a traditional LLM, JEV works from explicitly defined criteria to return choices, scores or yes/no judgments. Brian connected it to Claude Code and ran 116 Daily AI Show transcripts through it, breaking them into 4,872 passages and evaluating them in 143 seconds for 26 cents. Beth highlighted TypeSafe's data agreement as an important concern before using sensitive client information.

Brian then demonstrated Gemini 3.8 Live as a live review interface. He shared a webpage, talked naturally about requested changes and let Gemini capture the screen context, mouse position and conversation so another AI system could turn the feedback into actionable work.

Key Points Discussed

00:00:18 Episode Intro And What’s Coming Up

00:03:54 Is Fable Still Better Than Codex For Some Coding Work?

00:06:10 1,393 Fable Agents Refactor The Hermes Codebase

00:07:24 A New Software Benchmark Uses Private Production Code

00:08:20 Fable 5.1 Leads The New Coding Benchmark

00:09:16 Racing To Use Fable Before The Weekly Reset

00:10:33 Has Claude Opus Improved Again?

00:11:39 Why Beth Still Prefers Opus 4.8

00:13:21 Compound Engineering Plugins And Outdated Workflows

00:15:19 God’s Eye View Combines Public Data Into One Interface

00:17:40 Is A “Spy Satellite Simulator” The Wrong Description?

00:18:01 What Should People Be Able To Do With Public Data?

00:19:17 Mapping Heat Signatures, Cameras And Real-World Events

00:24:44 Reconstructing A Plane Crash With Public Information

00:28:25 Astra Builds New Daily AI Show Thumbnails From Video

00:34:00 Neon Beats General Frontier Models In Materials Science

00:36:11 Google Dream-RSI And Recursive Self-Improvement

00:37:43 Teaching AI To “Dream” Through Its Discovery History

00:42:23 Brian Opens The JEV Playground

00:43:37 How JEV Uses Choices, Scores And Explicit Criteria

00:47:28 Connecting JEV Directly To Claude Code

00:48:19 JEV Analyzes 116 Daily AI Show Transcripts

00:48:53 4,872 Passages Evaluated In 143 Seconds For 26 Cents

00:49:30 What JEV Found About The Show’s Most Common Topics

00:51:49 Using JEV As A Checks-And-Balances Layer

00:53:03 TypeSafe’s Data Agreement Raises A Privacy Question

00:54:25 Adding JEV Validation To Multimodal Video Search

00:57:10 Brian Demos Gemini 3.8 Live For Real-Time Review

00:58:09 Gemini Watches The Screen While Brian Talks Through Changes

00:59:31 Replacing Recorded Review Videos With Live AI Feedback

01:01:23 Gemini Live Watches And Discusses A Phone Screen

01:02:18 Comparing Gemini, ChatGPT And Perplexity Voice Experiences

01:03:40 Episode Wrap-Up

The Daily AI Show Co Hosts: Brian Maucere, Andy Halliday, Beth Lyons, Karl Yeh, Gareth Hood.