1. A An agent can propose a trade amendment without being allowed to apply it. Keon Shahab of Anthropic ... An agent can propose a trade amendment without being allowed to apply it. Keon Shahab of Anthropic walks through permissions, human approval and evals. 83 seconds from AI Engineer 10/20 07:00 ♡
2. First AIE Code Summit speakers: @poteto, Principal Engineer @ SpaceX @steve_yegge, Engineer, Writer... First AIE Code Summit speakers: @poteto , Principal Engineer @ SpaceX @steve_yegge , Engineer, Writer, Advisor @zachbruggeman , Principal Software Engineer @ Ramp Nov 10-12, SF. Co 10/20 04:17 ♡
3. H How much of a large context window is actually useful? @steveonjava asks the question. Neeraj Deshm... How much of a large context window is actually useful? @steveonjava asks the question. Neeraj Deshmukh of Blitzy explains how code graphs connect dependencies and retain their sour 10/20 02:00 ♡
4. S Should every agent wait in the same approval queue? @jxxf contrasts a ticket summarizer with an age... Should every agent wait in the same approval queue? @jxxf contrasts a ticket summarizer with an agent that can deploy to production. One review process can delay small experiments 10/19 22:00 ♡
5. 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 ♡
6. 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 ♡
7. 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 ♡
8. 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 ♡
9. 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 ♡
10. 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 ♡
