Can AI Learn Your Voice? Let's Find Out Live
Summary
Can AI learn your unique voice? In this session, AI engineer & educator Harper Carroll (Stanford, Meta) fine-tunes an open-source model on her own X posts, and tests the result live. While the model trains, she breaks down the science behind what's happening: how AI models are just probability machines, why smaller models can outperform larger ones for specific tasks (and what this means for you, your business, & your wallet), open vs. closed-source models, and how fine-tuning fundamentally changes a model's output compared to prompt engineering alone. This is for all levels of understanding.
- Format: Presentation
- Category: Presentation
- Event Type: panel
- Presented By: n/a
Contributors
- Harper Carroll
Raw Event JSON
Large nested arrays are compacted for page readability. Full payload remains in dataset files.
Open JSON payload
{
"id": "PP1150687",
"track": "Tech & AI",
"focus_area": null,
"category": "Presentation",
"event_id": "PP1150687",
"event_type": "panel",
"format": "Presentation",
"genre": null,
"subgenre": null,
"name": "Can AI Learn Your Voice? Let's Find Out Live",
"presented_by": null,
"publish_at": "2026-02-19T17:08:00.000-06:00",
"reservable": true,
"reservable_id": "PP1150687",
"reserved": false,
"date": "2026-03-16",
"end_time": "2026-03-16T11:00:00.000-05:00",
"start_time": "2026-03-16T10:00:00.000-05:00",
"message": null,
"image": null,
"credentials": [
{
"name": "Platinum Badge",
"type": "platinum"
},
{
"name": "Innovation Badge",
"type": "innovation"
}
],
"contributors": [
{
"id": 95613,
"company": "Harper Carroll AI",
"credential_types": [
"innovation"
],
"entity_id": 2258655,
"name": "Harper Carroll",
"speaker_types": [
"Speaker"
],
"title": "AI Engineer/Educator",
"image": {
"alt_text": "Harper Carroll",
"credit": null,
"url": "https://images.sxsw.com/_hBCnWdjmcHhJAGiwa5VjKy-9Lo=/665x531:4537x4403/600x600/images.sxsw.com/48/a8cbe8b0-3bdb-4f55-aac2-9126cca794c4/pcid-1644998"
},
"speaker_type": "Speaker",
"details": "Harper Carroll is an AI engineer and educator with a decade of experience who makes complex AI concepts accessible.\r\rShe has deep technical expertise: Harper holds two Computer Science degrees from Stanford University (M.S. + B.S. specializing in AI), built machine learning systems at Facebook/Meta (News Feed Ranking, Integrity Intelligence, Wearables), and was the Founding Engineer and Head of AI/ML at a startup acquired by NVIDIA. Her model fine-tuning coding guides became the most popular on Google in 2023.\r\rShe is also a polished communicator, bringing 7 years of acting training from the Lee Strasberg Theater & Film Institute and 4 years of experience hosting a weekly live TV show.",
"links": {},
"type": "person"
}
],
"venue": {
"accessible": false,
"age_policy": null,
"floor": "3",
"id": "V1349",
"indoor_outdoor": null,
"mixhalo_url": "https://translate.mixhalo.rocks/430?venue_id=430&partner=true",
"name": "Salon AB",
"parent_id": "V0403",
"parent_venue_name": "JW Marriott",
"venue_entry_info": null,
"formats": null,
"location": {
"address": "110 E 2nd St.",
"lat_lon": [
30.2645713,
-97.743198
],
"city": "Austin",
"postal_code": "78701",
"state": "TX",
"name": "JW Marriott"
},
"root": {
"id": "V0403",
"name": "JW Marriott",
"mixhalo_url": null
},
"events": "[omitted 5 venue events]"
},
"description": "Can AI learn your unique voice? In this session, AI engineer & educator Harper Carroll (Stanford, Meta) fine-tunes an open-source model on her own X posts, and tests the result live.\n\nWhile the model trains, she breaks down the science behind what's happening: how AI models are just probability machines, why smaller models can outperform larger ones for specific tasks (and what this means for you, your business, & your wallet), open vs. closed-source models, and how fine-tuning fundamentally changes a model's output compared to prompt engineering alone. This is for all levels of understanding.",
"experience_level": "Intermediate",
"audio_url": null,
"accessibility": [
"Closed captioned"
],
"accessible_venue": false,
"add_bcl_url": false,
"add_slido": false,
"after_midnight": null,
"age_policy": null,
"american_sign_language": false,
"apple_url": null,
"audio_description": false,
"caption_url": null,
"captioned_qa": false,
"closed_captioned": true,
"cpe_credit": false,
"event_status": "none",
"has_subtitles": false,
"hash_tags": [],
"high_sensory_experience": false,
"live": false,
"long_description": "Can AI learn your unique voice? In this session, AI engineer & educator Harper Carroll (Stanford, Meta) fine-tunes an open-source model on her own X posts, and tests the result live.\n\nWhile the model trains, she breaks down the science behind what's happening: how AI models are just probability machines, why smaller models can outperform larger ones for specific tasks (and what this means for you, your business, & your wallet), open vs. closed-source models, and how fine-tuning fundamentally changes a model's output compared to prompt engineering alone. This is for all levels of understanding.",
"meeting_url": null,
"meeting_url_live": false,
"mentorly_url": null,
"mobile_audio_url": null,
"open_captioned": false,
"playlist_tag": null,
"rebroadcast": false,
"recommended_ids": [],
"search_conversions": null,
"short_program": false,
"slido_url": null,
"sort": "CAN AI LEARN YOUR VOICE? LET'S FIND OUT LIVE",
"source": "Official",
"squad_up_url": null,
"stream_embed": null,
"stream_id": null,
"stream_url": null,
"strobe_warning": false,
"subdiscipline": null,
"summit": null,
"summit_display_name": null,
"tags": [],
"talent_attending": null,
"title_only": false,
"track_display_name": "Tech & AI track sponsored by IBM",
"trailer_id": null,
"trailer_url": null,
"video_on_demand": null,
"vimeo_id": null,
"vod": false,
"xr_project_type": null,
"youtube_id": null,
"related_events": [],
"related_sales_client": null
}