11. A AI Engineering = Evals Returning NYC keynoter @aparnadhinak made the strongest case that as code tr... AI Engineering = Evals Returning NYC keynoter @aparnadhinak made the strongest case that as code trends to free, and even if evals trend to free, the job that never goes away is th 10/17 03:22 ♡
12. 81.3% numerical accuracy. 85% required. The gate failed. A practical follow-up to AI Engineer New Y... 81.3% numerical accuracy. 85% required. The gate failed. A practical follow-up to AI Engineer New York from Doneyli De Jesus of @langfuse . Test each model or prompt change before 10/16 04:00 ♡
13. Thank you, New York. We brought a bell. You brought the questions. Thanks to everyone who joined A... Thank you, New York. We brought a bell. You brought the questions. Thanks to everyone who joined AI Engineer New York, our speakers, sponsors and crew. Presented by @ArizeAI . What 10/15 23:00 ♡
14. AI Engineer New York, between sessions. The expo floor had a barber. And a puppy. A few scenes fro... AI Engineer New York, between sessions. The expo floor had a barber. And a puppy. A few scenes from Tuesday. What was your best find between talks? A demo you tried or someone you& 10/15 06:30 ♡
15. One last keynote block. 4:30 PM: Michael Manapat + Jack McDonald, Apollo's AI approach 4:48 PM: @mi... One last keynote block. 4:30 PM: Michael Manapat + Jack McDonald, Apollo's AI approach 4:48 PM: @mitch_troy on checking agent decisions 5:06 PM: Cristóbal Valenzuela, @runwayml 10/15 04:00 ♡
16. F From the stage to the expo floor. AI Engineer New York, in motion. #AIEngineerNY From the stage to the expo floor. AI Engineer New York, in motion. #AIEngineerNY Your browser does not support the video tag. 🔗 View on Twitter 💬 0 🔄 1 ❤️ 6 10/15 02:45 ♡
17. What stops a bad agent from shipping? Doneyli De Jesus of @langfuse on test cases, domain evaluator... What stops a bad agent from shipping? Doneyli De Jesus of @langfuse on test cases, domain evaluators and a pass/fail gate before deployment. Today at AI Engineer New York. 2:55 PM 10/15 01:30 ♡
18. A A minute inside AI Engineer New York. Talks, demos and the conversations between them. #AIEngineer... A minute inside AI Engineer New York. Talks, demos and the conversations between them. #AIEngineerNY Your browser does not support the video tag. 🔗 View on Twitter 💬 10/14 23:15 ♡
19. Your retrieval got better. Did the answer? Manimala Kumar of @NVIDIA compares RAG with and without ... Your retrieval got better. Did the answer? Manimala Kumar of @NVIDIA compares RAG with and without reranking, then checks answer quality and latency. Today at AI Engineer New York. 10/14 22:00 ♡
20. Your last day in New York. 9 AM: @tryramp 11:30 AM: @NVIDIA 2:55 PM: @langfuse 4:30 PM: final keyno... Your last day in New York. 9 AM: @tryramp 11:30 AM: @NVIDIA 2:55 PM: @langfuse 4:30 PM: final keynotes Model gaps. RAG answers. Deployment gates. Apollo, Basis and Runway. All time 10/14 20:00 ♡