Gotcha – yeah I've been hoping to avoid that amount of accounting myself, but it may be the best option Frustrating that the OpenAI APIs don't return that "usage" block when used in streaming mode – thankfully the Anthropic ones do
AI
-
GPT-4V Medical Imaging Still Lags Behind Human Doctors
By
–
AIs are very proficient at text-based medical problems, often outperforming doctors, but the multimodal GPT-4V system is still much worse than humans at medical images.
-

Naming Phenomena in Academia: Entropy and Conceptual Clarity
By
–
Highly recommend that academics spend the time to come up with good names for phenomena they study. And this is great: “In the second place, and more important, nobody knows what entropy really is, so in a debate you will always have the advantage."”
-
Two-Stepping: A Technique to Improve AI Prompt Results
By
–
If your prompts aren’t quite giving you the results you want, here’s something to try. I call it "two-stepping". The key here is to get the AI to output something bad before it outputs something good. Here's how two-stepping works: First, prompt the AI with your initial
-
Mitigations Against Prompt Injection Attacks
By
–
What mitigations do you have in place against prompt injection attacks?
-
Bimanual robots need traditional engineering for reliability
By
–
I agree Animesh: these are impressive bimanual tasks (esp repairing the robot gripper!) but we may need to incorporate some GOFE (good old fashioned engineering) into these systems to reach acceptable reliability levels… https://t.co/13d36G6cU0
— Ken Goldberg (@Ken_Goldberg) 16 avril 2024I agree Animesh: these are impressive bimanual tasks (esp repairing the robot gripper!) but we may need to incorporate some GOFE (good old fashioned engineering) into these systems to reach acceptable reliability levels…
-
JSON Stability: Why Unchanged Format Ensures Universal Compatibility
By
–
The JSON spec hasn't changed since it was first informally published in 2006 Not changing is one of its most valuable features – it means that if you publish data in no-trailing-commas original JSON you can be certain it will be usable in every language with a JSON parser
-
What Prompts Do You Use for Relevance Judgements?
By
–
What kind of prompts do you use for relevance judgements?
-
GPT-4 Outperforms Majority of Physicians in Psychiatry
By
–
“GPT-4 ranked higher than the majority of physicians in psychiatry… it performed similarly to the median physician in general surgery & internal medicine… GPT-4 performance was lower in pediatrics & OB/GYN but remained higher than a considerable fraction” of active doctors.
-
Balancing Cost and Performance in Model Selection
By
–
It's pretty much for when I want it as fast and cheap as possible but I can't quite get the results I need from the least expensive model