<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel><description>https://joshuacrowley.com/ – Software Designer. Builds lots of prototypes, mostly web. Sometimes games. Nintendo &amp; Apple tragic. He/him.</description><link>https://bsky.app/profile/joshuacrowley.com</link><title>@joshuacrowley.com - Joshua Crowley</title><item><link>https://bsky.app/profile/joshuacrowley.com/post/3liuxaxd6ms2x</link><description>Hi @jesseyuen.bsky.social added you to this handy starter pack, hope that&#39;s okay -&gt; go.bsky.app/GXihHDK&#xA;&#xA;[contains quote post or other embedded content]</description><pubDate>23 Feb 2025 23:08 +0000</pubDate><guid isPermaLink="false">at://did:plc:fjp7grfglf3l5474v4cqrr5b/app.bsky.feed.post/3liuxaxd6ms2x</guid></item><item><link>https://bsky.app/profile/joshuacrowley.com/post/3letjzjxzv22p</link><description>Multimodal 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.</description><pubDate>03 Jan 2025 11:58 +0000</pubDate><guid isPermaLink="false">at://did:plc:fjp7grfglf3l5474v4cqrr5b/app.bsky.feed.post/3letjzjxzv22p</guid></item><item><link>https://bsky.app/profile/joshuacrowley.com/post/3lej6lmtkfc2e</link><description>I 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?</description><pubDate>30 Dec 2024 09:07 +0000</pubDate><guid isPermaLink="false">at://did:plc:fjp7grfglf3l5474v4cqrr5b/app.bsky.feed.post/3lej6lmtkfc2e</guid></item><item><link>https://bsky.app/profile/joshuacrowley.com/post/3ldzsczlzxs25</link><description>Collaboratively plan all your last minute Christmas todos with your significant other and tinytalkingtodos.com. It&#39;s a local-first voice assistant with a focus on privacy and families.</description><pubDate>24 Dec 2024 06:17 +0000</pubDate><guid isPermaLink="false">at://did:plc:fjp7grfglf3l5474v4cqrr5b/app.bsky.feed.post/3ldzsczlzxs25</guid></item><item><link>https://bsky.app/profile/joshuacrowley.com/post/3ldvgerh2vc2l</link><description>Gemini&#39;s Flash 2.0 is great, a true multimodal model I&#39;ve been waiting for. Just finished upgrading TTT to use the new websocket live api today, just in time for Christmas. Here&#39;s a demo of tool callings and it&#39;s audio understanding.&#xA;&#xA;vimeo.com/1041500694&#xA;https://vimeo.com/1041500694?share=copy</description><pubDate>22 Dec 2024 12:33 +0000</pubDate><guid isPermaLink="false">at://did:plc:fjp7grfglf3l5474v4cqrr5b/app.bsky.feed.post/3ldvgerh2vc2l</guid></item><item><link>https://bsky.app/profile/joshuacrowley.com/post/3ldu6plajlc2g</link><description>I’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.</description><pubDate>22 Dec 2024 00:43 +0000</pubDate><guid isPermaLink="false">at://did:plc:fjp7grfglf3l5474v4cqrr5b/app.bsky.feed.post/3ldu6plajlc2g</guid></item><item><link>https://bsky.app/profile/joshuacrowley.com/post/3ldmjynikb226</link><description>One nice quality of building an assistant app is you can just ask for mock data to test your features, as you build them. &#34;Can you try and delete a todo with a fake id&#34;.</description><pubDate>18 Dec 2024 23:44 +0000</pubDate><guid isPermaLink="false">at://did:plc:fjp7grfglf3l5474v4cqrr5b/app.bsky.feed.post/3ldmjynikb226</guid></item><item><link>https://bsky.app/profile/joshuacrowley.com/post/3ldespu74us2y</link><description>MCP 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.&#xA;https://modelcontextprotocol.io/tutorials/building-mcp-with-llms</description><pubDate>15 Dec 2024 21:58 +0000</pubDate><guid isPermaLink="false">at://did:plc:fjp7grfglf3l5474v4cqrr5b/app.bsky.feed.post/3ldespu74us2y</guid></item><item><link>https://bsky.app/profile/joshuacrowley.com/post/3ld5lsfwsf22n</link><description>Here&#39;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&#39;s realtime websocket approach.&#xA;https://www.youtube.com/watch?v=b61UaIpUbiE&amp;list=PL4qKegW3WEE7jII3juTcPUPnN_ciohkFC&amp;index=2&amp;t=1026s</description><pubDate>13 Dec 2024 01:06 +0000</pubDate><guid isPermaLink="false">at://did:plc:fjp7grfglf3l5474v4cqrr5b/app.bsky.feed.post/3ld5lsfwsf22n</guid></item><item><link>https://bsky.app/profile/joshuacrowley.com/post/3lbosnzspos2r</link><description>Is 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&#39;t recall where I found this props.&#xA;https://platform.openai.com/docs/guides/function-calling#step-5-provide-the-function-call-result-back-to-the-model</description><pubDate>24 Nov 2024 10:34 +0000</pubDate><guid isPermaLink="false">at://did:plc:fjp7grfglf3l5474v4cqrr5b/app.bsky.feed.post/3lbosnzspos2r</guid></item><item><link>https://bsky.app/profile/joshuacrowley.com/post/3lbdwnrqlok2k</link><description>I&#39;m building tinytalkingtodos.com a family voice assistant. My partner and I are constantly planning our week on the go. What&#39;s for dinner, who&#39;s doing pickup? Talkies captures our convos, photos and urls into todos. Talkies creates custom lists, so we always have an answer for &#34;What&#39;s next&#34;?</description><pubDate>20 Nov 2024 02:46 +0000</pubDate><guid isPermaLink="false">at://did:plc:fjp7grfglf3l5474v4cqrr5b/app.bsky.feed.post/3lbdwnrqlok2k</guid></item></channel></rss>