๐๐๐ฐ ๐๐๐๐ซ ๐๐ซ๐๐๐ค ๐ฉ๐ซ๐จ๐ฃ๐๐๐ญ: built a voice-native AI assistant called ๐๐ญ๐ฎ๐๐ฒ ๐๐ฎ๐๐๐ฒ, a personal learning companion for any @DeepLearningAI course (with my friend @SiddoSamith ).
๐ ๐๐๐ญ๐ฎ๐ซ๐๐ฌ:
- Context-aware (knows the exact timestamp you paused the video at)
- Real-time voice conversations (listens + speaks)
- Visual diagrams for effective understanding
- Interactive quizzes with feedback
- Persistent timestamped notes
Demo below. Built using @antigravity and Gemini Live API.
Shout out to @AndrewYNg for democratizing AI through @DeepLearningAI.
I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue. There's a new programmable layer of abstraction to master (in addition to the usual layers below) involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering. Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it, while the resulting magnitude 9 earthquake is rocking the profession. Roll up your sleeves to not fall behind.
Had an incredible time last week at Y Combinator in San Francisco for the Google Gemini ร Pipecat Hackathon last week. An inspiring weekend of innovation, collaboration, and voice AI exploration
#SFTechWeek#Ycombinator#pipecat#Gemini
Gemini x Pipecat hackathon last Saturday. 250 Developers. 20 judges from Google, YC companies, and the multimodal AI ecosystem. 75 projects submitted.
We're continuing remotely all week. You can still sign up your team and compete for $300,000 in API credits.
You don't have to start a project from scratch. You can port something you've been working on to use a Gemini model. You can add a realtime voice or video feature to your startup's product.
Here are the winners from the in-person day on Saturday ...
@T_Zahil A Prompt Engineering Platform where you drop your UI, and our AI crafts a single-shot prompt, from project planning to code snippets in that prompt so any coding agent (Bolt, Lovable, cursor, windsurf) can use to build it end-to-end in one go.MCP coming!
https://t.co/2Sif3583dY.
@trikcode Currently building https://t.co/T26Lo0LRgM one shot prompt engineering platform which turns users UI into AI readable and buildable prompts in a single go!
@dodopayments Building AI which writes single shot prompts that results in a complete website with a single go by coding agents, no more struggling to explain what you need to AI, meet prompt weaver at โก https://t.co/2Sif357voq
Turn your Napkin sketches to beautiful UIs โ drawn on @tldrawโs brilliant canvas, brought to life by @promptweaver . Big shoutout to the @tldraw team โ we couldnโt have asked for a better foundation! ๐, refer below where napkin sketch is converted into beautiful looking UI!
Turn your Napkin sketches to beautiful UIs โ drawn on @tldrawโs brilliant canvas, brought to life by @promptweaver . Big shoutout to the @tldraw team โ we couldnโt have asked for a better foundation! ๐, refer below where napkin sketch is converted into beautiful looking UI!
We are seeing new customers from Australia and UK!๐ช
Excited to see and help them prompt better!
Checkout https://t.co/HAf8uMZ6pa for amazing tools to help you prompt better.