I'd argue that the janky "queen = king – man + woman" thing is definitely related. It's not doing language generation, but you're trying to query the latent factors the model has used to minimise the surface objective
AI
-
Using nlp.pipe() for faster batched predictions in spaCy
By
–
Nice example! Here's a tip for next time as well: the nlp.pipe() function operates over a sequence of inputs, and lets the model make batched predictions, making it much faster:
-
5G Innovation Transforms Digital Infrastructure and SDG Impact
By
–
How #5G #innovation transforms #SDGs impact & #DigitalTransformation of #infrastructure See #UK #5GTrailblazers inc Prof @Dsimeo https://
bit.ly/3SWW9mq @ericsson #DataScience #womenintech @ipfconline1 #AI @DeepLearn007 #Bristol #EricssonAmbassador #CES2023 @dinisguarda -
Neural Radiance Fields (NeRF) for Unconstrained Photo Collections
By
–
Paper: Neural Radiance Fields (NeRF) for Unconstrained Photo Collections https://
nerf-w.github.io -
Miscommunication: Root Cause of All Problems?
By
–
Miscommunication is at the source of all our problems!
— Pascal Bornet (@pascal_bornet) 30 décembre 2022
Do you agree?#communication #management pic.twitter.com/0m4ULdropqMiscommunication is at the source of all our problems! Do you agree? #communication #management
-
Google AI Interpolates 3D Worlds from Online Photos
By
–
Google AI starts to interpolate the world into 3D spaces based entirely on photos found online pic.twitter.com/rTaqtWNcFq
— AI Breakfast (@AiBreakfast) 30 décembre 2022Google AI starts to interpolate the world into 3D spaces based entirely on photos found online
-
Validator AI: AI-Powered Business Idea Validation Tool
By
–
You can use Validator AI to get your business ideas validated by an AI. https://
futurepedia.io/tool/validator
-ai
… #AI #business #ChatGPT -
AI Prompts vs. Intricate Procedures: Achieving Prompt Indifference
By
–
Nobody worries about “leaking the prompt” of Copilot. Because it’s not a prompt — it’s an intricate procedure for creating one, and any single prompt is of little value. Aspire to that level of indifference toward your app’s prompt leaking.
-
GPT-3 Prompt Engineering Mitigations and Strategic Value
By
–
Mitigations like these are really for avoiding embarrassment. If it’s actually strategically important that your competitors don’t know what GPT-3 prompt you’re using in a public-facing app, you’re in trouble. You need to add value elsewhere.
-
Defending Your Prompts from Leaks and Plagiarism
By
–
I keep seeing prompt leaks. Dozens, now. I know of one startup whose prompt is plagiarized from another’s that leaked — revealed when theirs also leaked. Defend your prompt. Regex-filter your generations and throw an error if they contain snippets of your instructions.