--- schema: 1 type: video title: 'Building ambitious software — Jonathan Kelley, Dioxus Labs & Cognition' description: >- The Dioxus team got excited, maxed out their coding agent subscriptions, and turned out tens of thousands of lines of Rust covering features they had wanted for years. Almost none of it cleared the bar for merging. Those lines sat in draft, and Jonathan Kelley says they are sitting there still. He calls the failure mode becoming a slop cannon. Kelley founded Dioxus Labs five years ago, spending his last undergraduate summer on a cross platform Rust app framework instead of taking an internship, and the project now carries roughly 37,000 GitHub stars and an estimated 200 million cumulative end users across apps from voting software to collision avoidance for satellites. Getting there meant building almost everything from scratch, including a rendering engine with a browser grade CSS engine lifted out of Firefox, and a hot reload engine that patches running native code in place in about 100 milliseconds. The interesting turn is what changed when the agents got good at Rust. Kelley's team spent five years trying to file down Rust's learning curve, and now treats that curve as a feature, because the agents absorb the borrow checker and the edge cases on the developer's behalf. He is specific about where this pays and where it does not. Deeply integrated Kotlin and Swift build plugins went from years of hand written work to weeks. Release checklists, backports, and documentation accuracy became tractable for a team of three. Tests did not, because agents write tests for any API but rarely the right ones, though they excel at fuzzing harnesses. His verdict: code is cheap now, quality is not, and architecture is where the time goes. Speaker info: - https://www.linkedin.com/in/jonathan-r-kelley - https://jonathan-kelley.com - https://github.com/dioxuslabs/dioxus Timestamps: 0:00 - Five years ago, a first commit 2:49 - Where the project stands now 4:35 - Blitz and Subsecond 6:15 - The moment agents got good at Rust 7:07 - Why a hard language became an advantage 10:32 - Agents as patient specialists 13:04 - The mundane work worth automating 15:37 - Where tests fall short, where fuzzing wins 16:28 - Architecture is still an art 17:19 - Reading code over writing code --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/H7vFrcNWXzs-youtube-3f75483912b55b5ce56b Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- canonical: 'https://liquidgold.cc/watch/H7vFrcNWXzs' markdown: 'https://liquidgold.cc/watch/H7vFrcNWXzs.md' llms: 'https://liquidgold.cc/watch/H7vFrcNWXzs/llms.txt' parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T03:47:35.737Z' language: null children: [] videoId: H7vFrcNWXzs durationSeconds: 1154 publishedAt: '2026-09-11T20:00:06.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 24 endSeconds: 176 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=24' heldReason: rights - ordinal: 1 text: null startSeconds: 24 endSeconds: 176 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=24' heldReason: rights - ordinal: 2 text: null startSeconds: 176 endSeconds: 188 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=176' heldReason: rights - ordinal: 3 text: null startSeconds: 188 endSeconds: 276 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=188' heldReason: rights - ordinal: 4 text: null startSeconds: 276 endSeconds: 288 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=276' heldReason: rights - ordinal: 5 text: null startSeconds: 288 endSeconds: 382 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=288' heldReason: rights - ordinal: 6 text: null startSeconds: 382 endSeconds: 392 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=382' heldReason: rights - ordinal: 7 text: null startSeconds: 427 endSeconds: 440 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=427' heldReason: rights - ordinal: 8 text: null startSeconds: 440 endSeconds: 634 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=440' heldReason: rights - ordinal: 9 text: null startSeconds: 634 endSeconds: 644 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=634' heldReason: rights - ordinal: 10 text: null startSeconds: 644 endSeconds: 788 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=644' heldReason: rights - ordinal: 11 text: null startSeconds: 644 endSeconds: 788 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=644' heldReason: rights - ordinal: 12 text: null startSeconds: 644 endSeconds: 788 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=644' heldReason: rights - ordinal: 13 text: null startSeconds: 788 endSeconds: 800 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=788' heldReason: rights - ordinal: 14 text: null startSeconds: 800 endSeconds: 943 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=800' heldReason: rights - ordinal: 15 text: null startSeconds: 943 endSeconds: 954 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=943' heldReason: rights - ordinal: 16 text: null startSeconds: 954 endSeconds: 988 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=954' heldReason: rights - ordinal: 17 text: null startSeconds: 998 endSeconds: 1045 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=998' heldReason: rights - ordinal: 18 text: null startSeconds: 1056 endSeconds: 1154 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=1056' heldReason: rights - ordinal: 19 text: null startSeconds: 1056 endSeconds: 1154 watch: 'https://liquidgold.cc/watch/H7vFrcNWXzs?t=1056' heldReason: rights --- # Building ambitious software — Jonathan Kelley, Dioxus Labs & Cognition The Dioxus team got excited, maxed out their coding agent subscriptions, and turned out tens of thousands of lines of Rust covering features they had wanted for years. Almost none of it cleared the bar for merging. Those lines sat in draft, and Jonathan Kelley says they are sitting there still. He calls the failure mode becoming a slop cannon. Kelley founded Dioxus Labs five years ago, spending his last undergraduate summer on a cross platform Rust app framework instead of taking an internship, and the project now carries roughly 37,000 GitHub stars and an estimated 200 million cumulative end users across apps from voting software to collision avoidance for satellites. Getting there meant building almost everything from scratch, including a rendering engine with a browser grade CSS engine lifted out of Firefox, and a hot reload engine that patches running native code in place in about 100 milliseconds. The interesting turn is what changed when the agents got good at Rust. Kelley's team spent five years trying to file down Rust's learning curve, and now treats that curve as a feature, because the agents absorb the borrow checker and the edge cases on the developer's behalf. He is specific about where this pays and where it does not. Deeply integrated Kotlin and Swift build plugins went from years of hand written work to weeks. Release checklists, backports, and documentation accuracy became tractable for a team of three. Tests did not, because agents write tests for any API but rarely the right ones, though they excel at fuzzing harnesses. His verdict: code is cheap now, quality is not, and architecture is where the time goes. Speaker info: - https://www.linkedin.com/in/jonathan-r-kelley - https://jonathan-kelley.com - https://github.com/dioxuslabs/dioxus Timestamps: 0:00 - Five years ago, a first commit 2:49 - Where the project stands now 4:35 - Blitz and Subsecond 6:15 - The moment agents got good at Rust 7:07 - Why a hard language became an advantage 10:32 - Agents as patient specialists 13:04 - The mundane work worth automating 15:37 - Where tests fall short, where fuzzing wins 16:28 - Architecture is still an art 17:19 - Reading code over writing code --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/H7vFrcNWXzs-youtube-3f75483912b55b5ce56b Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- Canonical: https://liquidgold.cc/watch/H7vFrcNWXzs · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks > Missing: no stored document chunks are available.