BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//PyTorch - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:PyTorch
X-ORIGINAL-URL:https://pytorch.org
X-WR-CALDESC:Events for PyTorch
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20240101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20250124T130000
DTEND;TZID=UTC:20250124T140000
DTSTAMP:20260430T100331
CREATED:20250209T101310Z
LAST-MODIFIED:20250328T113138Z
UID:10000026-1737723600-1737727200@pytorch.org
SUMMARY:AI-Powered Competitive Programming: My HackerCup 2024 Experience
DESCRIPTION:Speaker: Anton Pidkuiko\, Software Engineer\, Meta\nLocation: Online \nIn this talk\, Anton shared how he built an AI agent that ranked #1 in the finals of Meta HackerCup 2024 (AI division). Anton developed a workflow that could solve the hardest competitive programming problems quickly and reliably. Anton will walk through how he used state-of-the-art reasoning LLM models\, curated RAG\, and leveraged cloud infrastructure to safely test and execute solutions at scale. This approach highlights the massive potential of test-time compute scaling and provides insights into AI’s future role in programming. \nAnton Pidkuiko is a Software Engineer at Meta\, Reality Labs in London. He is currently working on applying the power of Large Language Models to Metaverse Avatar product experiences. \nWatch the recording now and access Anton’s presentation slides here.
URL:https://pytorch.org/event/ai-powered-competitive-programming-my-hackercup-2024-experience/
CATEGORIES:PyTorch-hosted
END:VEVENT
END:VCALENDAR