AI News Today | Julian Goldie Podcast

OpenClaw 5.24: New Update Just Dropped…

10 min · 27 de may de 2026
Portada del episodio OpenClaw 5.24: New Update Just Dropped…

Descripción

OpenClaw 5.24 Beta: Discord Meeting Notes, iMessage Approvals, Live Voice Steering + Token-Saving ImagesOpenClaw 5.24 is a GitHub pre-release beta with new features including a meeting notes plugin that lets an agent join Discord voice calls, capture who said what, auto-start recording, and provide transcripts for summaries, action items, and search. The update adds iMessage action approvals via thumbs up/down, more interactive voice conversations with real-time status checks, cancel/redirect/queue controls, and Discord wake-name gating. Images now auto-adjust quality/compression by model with override modes to save tokens, and gateway startup is faster by reusing persistent data. Dashboard chat search is improved, the install package is smaller, and Grok web search moves to OAuth login rather than separate API keys. Fixes include Telegram topic concurrency, follow-up cancel-signal issues, Claude image support detection, DeepSeek tool cleanup, faster non-blocking memory search, and quicker skill refresh/updates. The script warns not to deploy beta on live setups and outlines backup, beta update, testing, and rollback steps.00:00 [https://www.youtube.com/watch?v=H4iND8JT9TI] Biggest 5.24 Beta Features00:50 [https://www.youtube.com/watch?v=H4iND8JT9TI&t=50s] Beta Warning and Safe Testing01:10 [https://www.youtube.com/watch?v=H4iND8JT9TI&t=70s] Discord Meeting Notes Plugin02:20 [https://www.youtube.com/watch?v=H4iND8JT9TI&t=140s] iMessage Emoji Approvals02:58 [https://www.youtube.com/watch?v=H4iND8JT9TI&t=178s] Real Time Voice Controls03:41 [https://www.youtube.com/watch?v=H4iND8JT9TI&t=221s] Smarter Images and Faster Startup04:38 [https://www.youtube.com/watch?v=H4iND8JT9TI&t=278s] Dashboard Search and Grok OAuth05:32 [https://www.youtube.com/watch?v=H4iND8JT9TI&t=332s] Smaller Install and Ecosystem Pitch06:24 [https://www.youtube.com/watch?v=H4iND8JT9TI&t=384s] Stability Fixes and Performance08:24 [https://www.youtube.com/watch?v=H4iND8JT9TI&t=504s] How to Update and Roll Back08:58 [https://www.youtube.com/watch?v=H4iND8JT9TI&t=538s] Agent OS Offer and Wrap Up

Comentarios

0

Sé la primera persona en comentar

¡Regístrate ahora y únete a la comunidad de AI News Today | Julian Goldie Podcast!

Empezar

2 meses por 1 €

Después 4,99 € / mes · Cancela cuando quieras.

  • Podcasts exclusivos
  • 20 horas de audiolibros / mes
  • Podcast gratuitos

Todos los episodios

418 episodios

Portada del episodio Kimi K2.7 + Hermes Agent is INSANE!

Kimi K2.7 + Hermes Agent is INSANE!

Kimi K2.7 Code + Hermes Agents: Build Apps & Videos Autonomously (Full Demo)The script showcases the release of Kimi K2.7 Code and how it’s been integrated into a Hermes Agent “crew” to autonomously build, run, bug-fix, and iterate on real projects using a large context window and a flat monthly coding plan. It demonstrates a fully AI-produced video where the avatar (via HeyGen CLI), editing/design, music, voiceover, and even camera zooms are generated by orchestrated Hermes agents using Kimi K2.7, with tasks managed through a Kanban board and a “judge” agent that scores and iterates the output from 6 to 9/10. Additional examples include a 3D game and a Web OS with persistent notes, calculator, paint, and clock apps. The speaker notes some slowness for browser-use tasks but highlights strong long-horizon performance and Moonshot benchmark gains.00:00 [https://www.youtube.com/watch?v=IQNR2k0WLPk] Kimi K2.7 Drops00:26 [https://www.youtube.com/watch?v=IQNR2k0WLPk&t=26s] One Sentence App Builder01:03 [https://www.youtube.com/watch?v=IQNR2k0WLPk&t=63s] AI Video Made by Agents02:10 [https://www.youtube.com/watch?v=IQNR2k0WLPk&t=130s] Kanban Orchestrated Workflow03:29 [https://www.youtube.com/watch?v=IQNR2k0WLPk&t=209s] Demos Games and Web OS05:59 [https://www.youtube.com/watch?v=IQNR2k0WLPk&t=359s] Chat Agent Speed Test07:49 [https://www.youtube.com/watch?v=IQNR2k0WLPk&t=469s] Best AI Video Workflow08:33 [https://www.youtube.com/watch?v=IQNR2k0WLPk&t=513s] Benchmarks and Context09:03 [https://www.youtube.com/watch?v=IQNR2k0WLPk&t=543s] Setup Inside Agent OS12:29 [https://www.youtube.com/watch?v=IQNR2k0WLPk&t=749s] AI Profit Vault Pitch14:03 [https://www.youtube.com/watch?v=IQNR2k0WLPk&t=843s] Final Recap and Outro

14 de jun de 202614 min
Portada del episodio Claude Fable + Mythos 5 is BANNED!

Claude Fable + Mythos 5 is BANNED!

Breaking: Anthropic Pulls Fable-5 & Mythos-5 After US Government Directive (What We Know)The video reports breaking news that Anthropic’s Claude models Fable-5 and Mythos-5 have been abruptly disabled after a US government directive, which reportedly suspends access for foreign nationals (including Anthropic employees), though the creator notes some users still appear to have access and is unsure why. The announcement was received at 5:21 PM ET on June 12 and provided no specific reason, but the creator suggests it may relate to alleged bypass techniques and model use for reading codebases and fixing software flaws. Anthropic says it added strong safeguards with US/UK and third-party help, believes the directive is a misunderstanding, and warns applying this standard broadly could halt frontier model deployments. The creator compares the situation to earlier incidents, notes Opus 4.8 remains available but feels like a step backward, and promotes Agent OS and the AI Profit Boardroom for switching between models and learning AI automation.00:00 [https://www.youtube.com/watch?v=5NdAlV85MPE] Breaking Shutdown News00:44 [https://www.youtube.com/watch?v=5NdAlV85MPE&t=44s] Testing Model Access00:59 [https://www.youtube.com/watch?v=5NdAlV85MPE&t=59s] Official Directive Details01:51 [https://www.youtube.com/watch?v=5NdAlV85MPE&t=111s] Why It Happened03:46 [https://www.youtube.com/watch?v=5NdAlV85MPE&t=226s] Anthropic Safeguards Statement05:31 [https://www.youtube.com/watch?v=5NdAlV85MPE&t=331s] Compliance And Disagreement05:58 [https://www.youtube.com/watch?v=5NdAlV85MPE&t=358s] Still Available Confusion06:38 [https://www.youtube.com/watch?v=5NdAlV85MPE&t=398s] Hands On With Fable 507:56 [https://www.youtube.com/watch?v=5NdAlV85MPE&t=476s] Industry Impact Debate08:27 [https://www.youtube.com/watch?v=5NdAlV85MPE&t=507s] Watch For Updates08:58 [https://www.youtube.com/watch?v=5NdAlV85MPE&t=538s] Agent OS Promo09:58 [https://www.youtube.com/watch?v=5NdAlV85MPE&t=598s] Final Sign Off

14 de jun de 20269 min
Portada del episodio New Chinese AI Model Is INSANE! (FREE & Open Source)

New Chinese AI Model Is INSANE! (FREE & Open Source)

N2 Pro: Free Open-Source Chinese Coding Model Beating Claude & GPT on Benchmarks (260K Context)The video introduces N2, a new free Chinese open-source model with open weights and a 260K-token context window, designed for coding and agentic workflows with strong tool/function calling. It highlights benchmark results where N2 outperforms paid APIs like Claude Opus 4.7, GPT 5.5, and DeepSeek V4 Pro on some tests (including SWE Bench), and notes it is based on Qwen 3.5’s architecture. The model is available on Hugging Face and via a free API on OpenRouter, and can be used inside agents such as Kilocode, Hermes Agent, Claude Code (via an open-source “Free Claude Code” project), OpenClaude, and Pi. The creator demonstrates configuring N2 in Hermes Agent using model profiles, compares N2 Pro and N2 Mini, and shows N2 responding faster than a Gemma 4 setup. The video ends by promoting training and resources in the AI Profit Boardroom.00:00 [https://www.youtube.com/watch?v=NbxZVAPWEW0] Free N2 Model Reveal00:29 [https://www.youtube.com/watch?v=NbxZVAPWEW0&t=29s] Benchmarks and Specs00:58 [https://www.youtube.com/watch?v=NbxZVAPWEW0&t=58s] Where to Get It Free01:24 [https://www.youtube.com/watch?v=NbxZVAPWEW0&t=84s] Setup in Hermes Agent02:01 [https://www.youtube.com/watch?v=NbxZVAPWEW0&t=121s] Use with Claude Code02:16 [https://www.youtube.com/watch?v=NbxZVAPWEW0&t=136s] What You Can Build02:32 [https://www.youtube.com/watch?v=NbxZVAPWEW0&t=152s] DeepSeek Comparison02:58 [https://www.youtube.com/watch?v=NbxZVAPWEW0&t=178s] Use Cases and Variants03:28 [https://www.youtube.com/watch?v=NbxZVAPWEW0&t=208s] Speed Test vs Gemma04:18 [https://www.youtube.com/watch?v=NbxZVAPWEW0&t=258s] Wrap Up and Next Steps04:30 [https://www.youtube.com/watch?v=NbxZVAPWEW0&t=270s] AI Profit Boardroom Pitch05:17 [https://www.youtube.com/watch?v=NbxZVAPWEW0&t=317s] Final Thanks

Ayer5 min
Portada del episodio Hermes: Agent OS + Obsidian + Kanban + Paperclip

Hermes: Agent OS + Obsidian + Kanban + Paperclip

Turn One Hermes Agent Into a Full AI Team (Agent OS + Obsidian Memory Galaxy + Kanban vs Paperclip)The video explains how to expand a single Hermes agent into a coordinated team by plugging Hermes into an Agent Operating System, including voice control via “Hermes Jarvis,” and using Obsidian as a local, markdown-based memory vault. It answers community questions on setting up the Obsidian “Memory Galaxy” view (now built into the latest Agent OS with a markdown setup guide), when to use Hermes’ native Kanban versus Paperclip (more complex dashboards and org charts, especially for orchestrating multiple tools), and whether Hermes profile agents can collaborate via group chat, Telegram, WhatsApp, or within the Agent OS. It also covers migrating notes from OneNote to Obsidian using MCP bridges, organizing multiple clients to avoid data conflation with separate folders and Kanban boards, customizing Agent OS UI toggles, and editing each agent’s soulmd instructions to improve response quality.00:00 [https://www.youtube.com/watch?v=6QLzDqB5YKU] Build a Team of Agents00:43 [https://www.youtube.com/watch?v=6QLzDqB5YKU&t=43s] Community Q&A Setup01:08 [https://www.youtube.com/watch?v=6QLzDqB5YKU&t=68s] Obsidian Memory Galaxy03:34 [https://www.youtube.com/watch?v=6QLzDqB5YKU&t=214s] Hermes Kanban vs Paperclip05:50 [https://www.youtube.com/watch?v=6QLzDqB5YKU&t=350s] Voice Jarvis Inspiration07:37 [https://www.youtube.com/watch?v=6QLzDqB5YKU&t=457s] Agents Chat Together08:52 [https://www.youtube.com/watch?v=6QLzDqB5YKU&t=532s] Move Notes to Obsidian10:07 [https://www.youtube.com/watch?v=6QLzDqB5YKU&t=607s] Agents in GoHighLevel10:36 [https://www.youtube.com/watch?v=6QLzDqB5YKU&t=636s] Avoid Client Data Mixups11:26 [https://www.youtube.com/watch?v=6QLzDqB5YKU&t=686s] Customize Agent OS UI11:54 [https://www.youtube.com/watch?v=6QLzDqB5YKU&t=714s] Improve Memory Responses12:56 [https://www.youtube.com/watch?v=6QLzDqB5YKU&t=776s] Wrap Up and Join Boardroom

Ayer14 min
Portada del episodio How to Use Claude Code FREE with N2!

How to Use Claude Code FREE with N2!

Use Claude Code for FREE with N2 (New Agentic API) + Voice-Build Apps LiveThe video demonstrates how to use Claude Code for free by plugging in the newly released N2 agentic “mixture of experts” API via an open-source project called Free Claude Code. N2 is based on Qwen 3.5 architecture, supports text and images, is designed for coding, tool use, deep research, and long-horizon agent workflows, offers a 262K context window, and is available on OpenRouter as a free API (with occasional token limits). The presenter shows voice-operating Free Claude Code to generate apps (e.g., a to-do list, habit tracker, meditation timer), preview results, and save every build in a workspace, plus adding skills like Hyperframes for video creation. They also show N2 working in Hermes Agent and explain integrating it into an “idea factory” pipeline and a shared memory dashboard, with setup available via the AI Profit Boardroom or the open-source project.00:00 [https://www.youtube.com/watch?v=B2-ExnJAE4E] Free Claude Code Intro00:30 [https://www.youtube.com/watch?v=B2-ExnJAE4E&t=30s] What Is N2 Model00:52 [https://www.youtube.com/watch?v=B2-ExnJAE4E&t=52s] Setup Free Claude Code01:14 [https://www.youtube.com/watch?v=B2-ExnJAE4E&t=74s] Voice Build Demo02:07 [https://www.youtube.com/watch?v=B2-ExnJAE4E&t=127s] Limits And Tradeoffs02:43 [https://www.youtube.com/watch?v=B2-ExnJAE4E&t=163s] Skills And Hyperframes03:10 [https://www.youtube.com/watch?v=B2-ExnJAE4E&t=190s] Goldie Voice Factory03:48 [https://www.youtube.com/watch?v=B2-ExnJAE4E&t=228s] Using N2 In Other Apps05:01 [https://www.youtube.com/watch?v=B2-ExnJAE4E&t=301s] Workspace And Idea Pipeline06:34 [https://www.youtube.com/watch?v=B2-ExnJAE4E&t=394s] Should You Try It06:59 [https://www.youtube.com/watch?v=B2-ExnJAE4E&t=419s] Recap And Next Steps07:46 [https://www.youtube.com/watch?v=B2-ExnJAE4E&t=466s] Shared Memory Dashboard08:26 [https://www.youtube.com/watch?v=B2-ExnJAE4E&t=506s] Community And Training Offer09:11 [https://www.youtube.com/watch?v=B2-ExnJAE4E&t=551s] Final Thanks

Ayer9 min