6 hours in, it self reports ~800 kLOC written (unclear if this includes core dump output, i bet it does) and then as I was typing this suddenly ended its session, well before its 24hr max runtime per session. it's not supposed to end this early and this is likely a bug. i've
SAFETY
-
LLM Agent Solutions and Training Data Contamination Concerns
By
–
my biggest concern is that an LLM Agent can solve it in 1-2 years but by then related forks and code and discussions seep into its training data in an undefined way, making the result unsatisfying.
-
AI Browser Safety: No Cheating Detected Yet
By
–
my biggest concern actually was that it would use its browser and find your work. so far so good, no cheating.
-
AI Safety: Teaching Chatbots to Disengage Appropriately
By
–
One smart thing that Copilot/Bing does well is giving the AI the ability to hang up on you. Otherwise, you can end up in a dead-end place where you “offended” the AI which will just keep looping through refusals & recriminations. Clearing the context window is the way forward.
-
Stressful Self-Driving Car Test in Autonomous Vehicle Innovation
By
–
Stressful Self-Driving Car Test
— Ronald van Loon (@Ronald_vanLoon) 8 avril 2024
by @IntEngineering#AutonomousVehicles #AI #ArtificialIntelligence #Innovation #Technology #Tech #Automation #Automotive #Transport #SelfDrivingCars
cc: @pascal_bornet @pbalakrishnarao @ravikikan pic.twitter.com/WzT1OFlDqWStressful Self-Driving Car Test
by @IntEngineering #AutonomousVehicles #AI #ArtificialIntelligence #Innovation #Technology #Tech #Automation #Automotive #Transport #SelfDrivingCars cc: @pascal_bornet @pbalakrishnarao @ravikikan -
Claude 3 simulates DOS games but struggles with unconventional approaches
By
–
Claude 3 does a pretty good job simulating early 1980s DOS adventure games, it is pretty amusing to use the most sophisticated technology available today to play an Infocom knock-off. But it really doesn't like it when you try too "unconventional" an approach to problem solving.
-
Stanford AI100 Report Assesses Progress and Risks
By
–
September 2021: The 100-year study on AI (AI100), administered out of @StanfordHAI
, released its second report. The report concludes that AI’s rapid integration into daily life underscores the need to grasp its potential drawbacks. #MondayMilestones 13/n https://
hai.stanford.edu/news/new-repor
t-assesses-progress-and-risks-artificial-intelligence
… -
AI-Powered Solution Monitors Unsafe Acts in Workplace
By
–
It is an #AI-powered solution that monitors unsafe acts
— Ronald van Loon (@Ronald_vanLoon) 8 avril 2024
by @IntEngineering#AI #ArtificialIntelligence #Tech #Innovation #EmergingTech #FutureOfWork
cc: @guzmannutrition @maxjcm @pascal_bornet pic.twitter.com/w7ahXlnXUTIt is an #AI-powered solution that monitors unsafe acts
by @IntEngineering #AI #ArtificialIntelligence #Tech #Innovation #EmergingTech #FutureOfWork cc: @guzmannutrition @maxjcm @pascal_bornet -
Driverless Delivery Trucks: Autonomous Vehicles and AI Automation
By
–
#Driverless delivery trucks
— Ronald van Loon (@Ronald_vanLoon) 8 avril 2024
via @mvollmer1#AI #ArtificialIntelligence #RPA #Automation #AutonomousVehicles #SelfDrivingCars
cc: @maxjcm @pascal_bornet pic.twitter.com/UNGfxYNYm4#Driverless delivery trucks
via @mvollmer1 #AI #ArtificialIntelligence #RPA #Automation #AutonomousVehicles #SelfDrivingCars cc: @maxjcm @pascal_bornet -
Fast and Safe Drone Delivery for Medical Samples
By
–
Fast and safe delivery of samples via #Drone
— Ronald van Loon (@Ronald_vanLoon) 8 avril 2024
by @IntEngineering#AI #ArtificialIntelligence #Healthcare #HealthTech #Tech #Technology
cc: @johnnosta @nathealings @guzmannutrition pic.twitter.com/IXD9K5vKN1Fast and safe delivery of samples via #Drone
by @IntEngineering #AI #ArtificialIntelligence #Healthcare #HealthTech #Tech #Technology cc: @johnnosta @nathealings @guzmannutrition