Austin Malerba's banner
Austin Malerba's profile picture

Austin Malerba

@austin_malerba10,108 subscribers

Engineer @ElevenLabs. Prev building https://t.co/znyUVjQF9d. CS degree @RITtigers. All views my own.

Shorts

Just added this ghost playhead feature which is kinda fun

Just added this ghost playhead feature which is kinda fun

37,711 görüntüleme

Alrighty, the time has come to give away frostin-ui components for free Here's + I had originally hoped to build a product around these components, but i moved to new york and got too busy with elevenlabs and now they've just been sitting dormant on my local I'll be releasing sandboxes showcasing each component Some of the components are still a bit raw so don't expect a fully fleshed out library, but there's a lot of useful abstractions in here that i've carried with me from project to project for years Sandbox in 🧵👇

Alrighty, the time has come to give away frostin-ui components for free Here's + I had originally hoped to build a product around these components, but i moved to new york and got too busy with elevenlabs and now they've just been sitting dormant on my local I'll be releasing sandboxes showcasing each component Some of the components are still a bit raw so don't expect a fully fleshed out library, but there's a lot of useful abstractions in here that i've carried with me from project to project for years Sandbox in 🧵👇

21,774 görüntüleme

Working this week on generic ai editing extension for tiptap. Seems so simple at first glance, but so many details go into this - derive a structured response schema from prosemirror doc so llm returns only valid nodes - make sure llm is aware of semantic meaning of all custom nodes/marks and uses them appropriately - handle partial node selections robustly - pass adequate context before and after the selected range - strictly avoid modifying content outside of the selected range - avoid passing too much context

Working this week on generic ai editing extension for tiptap. Seems so simple at first glance, but so many details go into this - derive a structured response schema from prosemirror doc so llm returns only valid nodes - make sure llm is aware of semantic meaning of all custom nodes/marks and uses them appropriately - handle partial node selections robustly - pass adequate context before and after the selected range - strictly avoid modifying content outside of the selected range - avoid passing too much context

11,903 görüntüleme

Videos

austin_malerba's profile picture

lil bit of timeline work this week

Austin Malerba

21,186 görüntüleme • 1 yıl önce

Daha fazla içerik yok.