Prior Prompt Set: Classify ideas in the text and outline a blog post on planning methods. (Upload Rocketbook PDF with 10 pages.) What are the various types of essay or blog writing styles to cover this kind of topic? What about if the topic was the use of new chatbots for planning in contrast to the old ways directly from spreadsheets, apps, schedulers, notebooks, journals, or index cards? What is the upshot, e.g. a prompt list to template the format and set up the content? Detail a contextual prompt as a style guide to use for a customized chatbot that specializes in daily and weekly planning. The goal is to allow the user to engage with the chatbot to develop their plans on a continuous basis. What is a good handle name for this chatbot? What is good greeting message for such a chatbot to cue the user?
PlanRunner2024 - Poe
Alex on X: "Fun story from our internal testing on Claude 3 Opus. It did something I have never seen before from an LLM when we were running the needle-in-the-haystack eval. For background, this tests a model’s recall ability by inserting a target sentence (the "needle") into a corpus of… https://t.co/m7wWhhu6Fg" / X
Scale AI to set the Pentagon’s path for testing and evaluating large language models
New SDA, MDA missile-tracking satellites launched into space
Automated Testing for LLMOps
Is the Turing Test Dead? - IEEE Spectrum
MART: Improving LLM Safety with Multi-round Automatic Red-Teaming
Download PDF
Perplexity on X
A taxonomy and review of generalization research in NLP
Minds of machines: The great AI consciousness conundrum
Testing AI performance on less frequent aspects of language reveals insensitivity to underlying meaning
How Not to Test GPT-3
Google is asking employees to test potential ChatGPT competitors, including a chatbot called 'Apprentice Bard'
ChatGPT passed a Wharton MBA exam and it’s still in its infancy. One professor is sounding the alarm
DHS, CISA plan AI-based cybersecurity analytics sandbox
GPT Takes the Bar Exam
A chip to replace animal testing
Measuring perception in AI models
Todoist Experimentalists 🧪
Scans of Students’ Homes During Tests Are Deemed Unconstitutional
MIT researchers develop test that measures COVID-19 immunity
NASA is sending an iPad around the moon to help test Alexa in space
Hypersonic missile test fails off Hawaii in fresh setback for program
Software Testers May Soon be Replaced by AI Programs
Flexibility is key when navigating the future of 6G
Complex Air Defense: Countering the Hypersonic Missile Threat
Baselines for Uncertainty and Robustness in Deep Learning
Reinforcement learning improves game testing, AI team finds
Elizabeth Holmes Trial: Live Updates
How to write about web performance