Reposted by Joshua CrowleyCharlie Warzel @cwarzel.bsky.social · 13/05/2025"fully operational mobile McDonald’s unit" is a phrase that makes me feel like maybe i've passed away and all the news i read is all just the final neurons in my brain racing around making haphazard connections in the moments before darkness 661288225
Joshua Crowley @joshuacrowley.com · 23/02/2025Hi @jesseyuen.bsky.social added you to this handy starter pack, hope that's okay -> go.bsky.app/GXihHDK 110
Reposted by Joshua CrowleyThe Verge @theverge.com · 14/01/2025ChatGPT can now handle reminders and to-dosbuff.lyChatGPT can now handle reminders and to-dosChatGPT just got a new automation feature for future tasks. 64686
Joshua Crowley @joshuacrowley.com · 03/01/2025Multimodal models like Flash 2.0 and GPT4o can use audio tokens to natively reason over audio input. Neither can yet provide text and audio tokens that come from the same inference pass, and presumably wont ever. So that presents a flaw in these models no one seems to be discussing. 100
Joshua Crowley @joshuacrowley.com · 30/12/2024I don’t know what agentic ai really means for users. I can see how an immediate barrier for deeper LLM experiences is access to user data. So will agents just be for integrating your service into a user’s auth/cloud/filesystem? a crutch for interoperability? 110
Joshua Crowley @joshuacrowley.com · 24/12/2024Collaboratively plan all your last minute Christmas todos with your significant other and tinytalkingtodos.com. It's a local-first voice assistant with a focus on privacy and families. 110
Joshua Crowley @joshuacrowley.com · 22/12/2024Gemini's Flash 2.0 is great, a true multimodal model I've been waiting for. Just finished upgrading TTT to use the new websocket live api today, just in time for Christmas. Here's a demo of tool callings and it's audio understanding. vimeo.com/1041500694vimeo.comTiny Talking TodosPerfect way to coordinate your christmas todos 020
Joshua Crowley @joshuacrowley.com · 22/12/2024I’ll be trying Gemini 2 for code gen soon in my app, specifically to test its visual understanding. I’ve been pretty happy Claude Sonnet 3.5, especially because my current workflow is just to one shot via the users prompt. But excited to see where multiple fast iterations on a workflow gets us. 210
Joshua Crowley @joshuacrowley.com · 18/12/2024One nice quality of building an assistant app is you can just ask for mock data to test your features, as you build them. "Can you try and delete a todo with a fake id". 000
Joshua Crowley @joshuacrowley.com · 15/12/2024MCP has a page explaining how to best configure your LLM so it can pair with you on building out your implementation. First time I’ve seen this for an open source project.modelcontextprotocol.ioBuilding MCP with LLMs - Model Context ProtocolSpeed up your MCP development using LLMs such as Claude! 000
Reposted by Joshua CrowleySunil Pai @threepointone.bsky.social · 13/12/2024the todo app that... does are you getting it 4532
Joshua Crowley @joshuacrowley.com · 13/12/2024Here's a dev talk I gave on building voice agents in the browser at SydJS. In the talk I try and breakdown the different services you might use, and show how users can BYO keys, for a client based approach. I also demo using OpenAI's realtime websocket approach.youtube.comJoshua Crowley - Tiny Talking ToDosYouTube video by SydJS 100
Reposted by Joshua CrowleyCasey Newton @caseynewton.bsky.social · 12/12/2024Clio is Anthropic's new system for identifying AI risks that it hadn't thought to look for — what it calls the unknown unknowns. I talked with team that built it and share for the first time the top three ways people use Claude www.platformer.news/how-claude-u... 612613
Reposted by Joshua CrowleySimon Willison @simonwillison.net · 06/12/2024This is a neat new variant on RAG - no vectors, not even full-text search, instead showing the model a header hierarchy and giving it a tool to read the relevant sections My notes here: simonwillison.net/2024/Dec/6/r...simonwillison.netRoaming RAG – make the model find the answersNeat new RAG technique (with a snappy name) from John Berryman: > The big idea of Roaming RAG is to craft a simple LLM application so that the LLM assistant … 1216020
Reposted by Joshua CrowleyBrad Frost @bradfrost.com · 05/12/2024We beat Super Mario Wonder! My daughter and I have been chipping away, and I'm so impressed w/ how good she got. There's a lot of coordination, pattern recognition, problem solving, and strategy involved, and it's been REALLY cool to really see her achieve mastery. These skills will serve her well. 141432
Reposted by Joshua CrowleyTheo Sanderson @theo.io · 30/11/2024Pentametron was one of the great web art projects, retweeting couplets of accidentally iambic tweets. Thanks to Bluesky's open feed, I have resurrected the concept.. Behold @iambic.bot! 361350419
Joshua Crowley @joshuacrowley.com · 24/11/2024Is there any up to date advice on tool call responses? Seems like a powerful concept, but unclear how to approach it. Atm I have acknowledgment, action_summary, result and next_steps properties – though I can't recall where I found this props.platform.openai.comOpenAI PlatformExplore developer resources, tutorials, API docs, and dynamic examples to get the most out of OpenAI's platform. 100
Joshua Crowley @joshuacrowley.com · 20/11/2024I'm building tinytalkingtodos.com a family voice assistant. My partner and I are constantly planning our week on the go. What's for dinner, who's doing pickup? Talkies captures our convos, photos and urls into todos. Talkies creates custom lists, so we always have an answer for "What's next"? 2131