1. W What happens when a throwaway tool needs to last? @mkanat explains why disposable and durable softw... What happens when a throwaway tool needs to last? @mkanat explains why disposable and durable software sit on a spectrum, and why making engineering rigor cheaper helps when your p 10/19 07:00 ♡
2. S Should an agent approve its own actions? Allie Howe of @KeycardAI asks about the CEO's email. @Dick... Should an agent approve its own actions? Allie Howe of @KeycardAI asks about the CEO's email. @DickHardt explains separating the worker from its supervisor, with deterministic 10/19 02:00 ♡
3. A At Arca, the agents are the ones asking people to act. Aman Singh of @arca_wealth explains how agen... At Arca, the agents are the ones asking people to act. Aman Singh of @arca_wealth explains how agents prepare work and bring people in when a decision is needed. His example is pre 10/18 22:00 ♡
4. C Catch more fraud. Decline fewer legitimate payments. Freddy Lecue of @WellsFargo reports better fra... Catch more fraud. Decline fewer legitimate payments. Freddy Lecue of @WellsFargo reports better fraud detection and fewer false positives than their production XGBoost model. His A 10/18 02:00 ♡
5. Y Your users say search is bad. How do you turn that complaint into an eval? Aaron Linsky explains ho... Your users say search is bad. How do you turn that complaint into an eval? Aaron Linsky explains how Bridgewater built a benchmark of about 200 examples in under a week, then used 10/17 22:00 ♡
6. W Why did code quality matter in the first place? @mkanat brings it back to two questions: what does ... Why did code quality matter in the first place? @mkanat brings it back to two questions: what does the system actually do, and how do you change it safely? 57 seconds from AI Engin 10/17 06:00 ♡
7. 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 ♡
8. 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 ♡
9. 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 ♡
10. 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 ♡
