AI-Powered Competitive Programming: My HackerCup 2024 Experience
Location: Online
- In this talk, Anton will share 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.
+ In 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.
-Anton 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.
+ Anton 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.
- Register now to attend this event.
-
+ Watch the recording now and access Anton's presentation slides here.
+
diff --git a/assets/HackerCup-AI-PS.pdf b/assets/HackerCup-AI-PS.pdf
new file mode 100644
index 000000000000..2841752ef6c5
Binary files /dev/null and b/assets/HackerCup-AI-PS.pdf differ