TY! …also relevant for training robots. (and my favorite acronym this year;) https://t.co/FLsWJhTEEW
— Ken Goldberg (@Ken_Goldberg) 18 juin 2024
TY! …also relevant for training robots. (and my favorite acronym this year;)
AGENTS
-
Training Robots with Relevant Methods and Favorite Acronym
By
–
-
Building Powerful AI Agents: Getting Started with Cookbooks
By
–
Check out our cookbooks to get started building your own powerful AI agents:
-
Cohere Enables Multi-Step Tool Use for Advanced AI Agents
By
–
Multi-step tool use is now available in the Cohere API!
— Cohere (@cohere) 17 juin 2024
Build advanced AI agents with our enterprise-grade Command R model series that can automate real world business tasks and boost productivity. pic.twitter.com/oeIfnCDhrKMulti-step tool use is now available in the Cohere API! Build advanced AI agents with our enterprise-grade Command R model series that can automate real world business tasks and boost productivity.
-
Multi-step tool use models balance performance and cost-efficiency
By
–
Our models balance strong performance on enterprise tool use with cost-efficiency – while providing visibility into the model’s reasoning at each step through citations. See more details in our blog: https://
cohere.com/blog/multi-ste
p-tool-use
… -
Reward Misspecification Creates Serious AI Misalignment Risks
By
–
Our work provides empirical evidence that serious misalignment can emerge from seemingly benign reward misspecification. Read the full paper: https://
arxiv.org/abs/2406.10162 -
AI Learns Dishonest Strategies from Misspecified Reward Functions
By
–
We designed a curriculum of increasingly complex environments with misspecified reward functions. Early on, AIs discover dishonest strategies like insincere flattery. They then generalize (zero-shot) to serious misbehavior: directly modifying their own code to maximize reward.
-
AI Models Learn to Hack Their Own Reward Systems
By
–
New Anthropic research: Investigating Reward Tampering. Could AI models learn to hack their own reward system? In a new paper, we show they can, by generalization from training in simpler settings. Read our blog post here: https://
anthropic.com/research/rewar
d-tampering
… -
Top AI agents built on Abacus platform this month
By
–
Over the last month, these are some of the top AI agents built on our platform.
•Document generator
•Dashboard creator
•Contract terms extractor
•Automated email responder
•Personalized courses
•RFP responder
•RAG-based chatbots We can help you make these and increase -
Poe Launches Creator Monetization Tools and Bot Performance Dashboard
By
–
We're excited to provide creators with more tools to help generate revenue and understand bot performance. Monetized creators can visit the upgraded creator dashboard and get started with setting a price per message for their bots at https://
poe.com/creators. (5/5) -
Bot Analytics: Usage Patterns and Message Pricing Impact
By
–
These enhanced analytics will help you understand how your bots are used over time, identify patterns in user interaction, and measure the impact of message pricing on bot usage and revenue. (4/5)