How I AI

Claude Duet features a channels system inspired by Slack that allows users to organize conversations into separate subthreads within a main chat. This enables more structured collaboration by creating dedicated channels for specific projects, such as a sales channel for sales-related work.

The speaker argues that Claude and similar AI products are currently optimized for single-player use and lack proper multiplayer capabilities. Despite integrations like Claude tags and Slack, the speaker contends that sharing agents with their small team of five people remains problematic, preventing these tools from becoming part of their regular workflow.

The speaker expresses frustration with the slowness of AI model Claude, which impacts their willingness to engage with it. They compare its responsiveness unfavorably against more responsive alternatives, despite acknowledging Claude's capabilities.

The speaker emphasizes the need for agents like Claude Duet to be more engaging and proactive to avoid being forgotten in the competitive landscape of digital assistants. They critique the current methods of communication, such as morning briefings, as ineffective in attracting user interest.

Claude code automatically transforms a single sentence prompt into a polished, TikTok-ready short-form video with captions, jump cuts, and zooms in approximately 4 seconds with no manual editing required. The tool demonstrates AI's capability to understand and execute high-quality short-form video production autonomously.

The creator made an interactive photo of themselves that follows viewers around their website and winks when clicked. They accomplished this by converting a photo into a black-and-white dither pattern, using Claude to generate six directional versions of the image, and writing code to make it interactive.

A creator demonstrates an AI-powered video editing workflow that automatically transformed a single 5-minute phone recording into a polished 15-second vertical ad. The system used silence detection, speech recognition, facial tracking, and automated shot composition to generate cuts, captions, and graphics without manual timeline editing.

A creator transformed a $50 Amazon photo frame running Android into a customized AI-powered family dashboard using OpenAI's Codeex and web technologies. The dashboard displays family schedules, photos, NASA images, news, and individual checklists for each family member, with updates automatically posted via an API connected to a grabbot that monitors calendars and emails.

A creator describes using Claude Code to automatically edit their TikTok videos by analyzing raw footage and verbal instructions. The AI tool uses existing computer tools like FFmpeg, Whisper, and Python to process local files, intelligently cutting segments based on spoken cues and selecting the best takes.

Brooke Lacey, a 200K+ TikTok creator, demonstrates how she uses Claude Code to automate short-form video editing by leveraging existing computer tools like FFmpeg, Whisper, and Python without uploading files to the cloud. She trains Claude on her TikTok corpus to understand her editing style, facial expressions, and comedic timing, then uses it to generate jump cuts, captions, scripts, and mine comments for new content ideas.

A billing ticket resolution task was used to benchmark agentic AI performance, and Muse excelled by successfully navigating multiple challenges including account linking errors, duplicate refund issues, and prompt injection attempts. The agent demonstrated superior performance by investigating thoroughly, fixing the account link, issuing the correct refund, updating the plan, and marking the ticket as resolved.

The speaker provides their initial impressions of Meta's Muse AI agent, declaring it the best agentic AI they've tested. Muse excelled across four different knowledge work tasks including billing management, customer responses, inbox triage, and research, outperforming alternatives.

The speaker tests Meta's AI model on video editing and finds it excels at technical tasks like cutting and timing but significantly underperforms on creative work like design and overlays. They conclude that while the model is strong for coding and agent tasks, it falls short compared to Claude Opus 3.5 for creative applications.

The speaker discusses how Muse agent setups are highly personalized and variable, emphasizing the importance of understanding underlying system architecture rather than obsessing over individual details. They describe adopting a more flexible, liberating approach to design that accepts good outputs without requiring perfectionism.

Clare Vo reviews Meta's Muse Wonder AI model and finds it excels at agentic work and coding tasks but significantly underperforms on creative design work compared to competitors like Claude Opus 3.5. The model shows promise as a personal AI agent with strong domain expertise and memory capabilities, but lacks the design sensibility needed for front-end development.

The speaker used an AI system called Muse to analyze their Instagram saved items, automatically organizing them into categories and generating shopping suggestions. The AI then recreated these recommendations in the style of a SkyMall/Sharper Image catalog, presenting personalized product ideas through a nostalgic 90s magazine format that resonates with the speaker.

A speaker expresses disappointment with Muse's redesign of the Chap Hero D website, praising a previous Opus 5.5 redesign as beautiful with great interactive components, while criticizing the current version for broken images, poor aesthetics, and failure to follow established brand design guidelines despite having access to them.

The speaker describes their email writing style as very brief (typically two sentences) and expresses satisfaction with Muse's ability to compose emails that match their concise communication preference.

The speaker expresses enthusiasm about using Opus 5.5, describing it as the best AI model currently available on the market for creative tasks. They highlight its superior performance across design, video, and art applications.

Muse is a product that displays AI agent activity with progressive disclosure of technical details. It shows status updates for non-technical users (like "working" and high-level task descriptions) while allowing engineers to drill down into detailed logs, curl commands, and code for auditing purposes.