We explored approaches with varying amounts of automation and human effort. In the simplest case, we generated thousands of yes-no questions for diverse behaviors just by instructing an LM (and filtering out bad examples with another LM). Random examples of LM-written evals:
AUTOMATION
-

Automated Language Model Evaluations Using AI-Generated Tests
By
–
It’s hard work to make evaluations for language models (LMs). We’ve developed an automated way to generate evaluations with LMs, significantly reducing the effort involved. We test LMs using >150 LM-written evaluations, uncovering novel LM behaviors. https://
anthropic.com/model-written-
evals.pdf
… -

Maximize Profits with Artificial Intelligence Pricing Optimization
By
–
Learn how to maximize profits with artificial intelligence. Read the use case: https://
h2o.ai/solutions/use-
case/pricing-optimization/?utm_medium=Organic-Social&utm_source=twitter&utm_campaig=usecase
… -
ChatGPT Frontend Automation Now Widely Hacked
By
–
Everyone already hacked the front end of ChatGPT to automate it yes, super easy
-

AI Bots Automatically Replying to Tweets Using ChatGPT
By
–
I had a gut feeling but now I proved it: People now have A.I. bots running that use ChatGPT to automatically reply to people's tweets
-

IBM Launches Digital Self-Serve Co-Create Experience for AI Applications
By
–
We’re excited to introduce the new Digital Self-Serve Co-Create Experience (DSCE) from #IBM Build Lab: https://t.co/gGek0zvYht
— IBM Data, AI & Automation (@IBMData) 19 décembre 2022
^ a prescriptive, wizard-driven experience designed to onboard, scale and differentiate partner applications with embeddable #AI.
—#AIOps #MLOps pic.twitter.com/F81oBh9W7AWe’re excited to introduce the new Digital Self-Serve Co-Create Experience (DSCE) from #IBM Build Lab: https://
ibm.co/3Wpgbbn ^ a prescriptive, wizard-driven experience designed to onboard, scale and differentiate partner applications with embeddable #AI.
—
#AIOps #MLOps -
Are ChatGPT-style replies becoming common on social media?
By
–
Increasingly seeing ChatGPT style replies to my tweets, did AI write this?
-

Operation Power Off: DDoS Attack Sites Shutdown
By
–
Operation 'Power Off'! Shutdown of sites offering ability to launch #DDoS attacks for a fee! http://
bit.ly/WebPowerOff More on #CyberSecurity #risk & #education http://
bit.ly/DDoSRise @NETSCOUT #Security #partner #AI #100DaysOfCode #DevOps #data #DataScience #IoT #ML -
Digital Twins Transform Manufacturing Industry
By
–
How Digital Twins Will Transform Manufacturing https://
industrytoday.com/how-digital-tw
ins-will-transform-manufacturing
…
