Finally got access to Custom GPTs What should I build? Boarding a plane in 30 minutes…
AGENTS
-
Learning World Models Beyond PID Controller Tuning
By
–
It's a *lot* more than adjusting the coefficients of your PID controllers.
Building a model of your own dynamics is acquiring a kind of knowledge, but it's relatively simple.
However, learning a model of the world and of your possible interactions with it is fiendishly complex. -
Cornell researchers address AI model updating challenges
By
–
no but I know some people at Cornell have been working on the updating problem: http://
arxiv.org/abs/2307.10323 -
Supporting Founders and Developers in the Tech Ecosystem
By
–
Founders and developers are in many cases our own friends, former colleagues, or just like minded builders. These are people who we all unequivocally want to see be successful in what they are building.
-
Knowledge in Execution: Learning Without Language
By
–
The point is that there is a *huge* amount of knowledge in the execution.
Arguably, almost *all* the knowledge is in the execution.
Animals learn to execute complex actions as quickly as humans without the help of language. So whatever knowledge in contained in language must be -
Flowise: LLM Orchestration Platform Enabling Custom AI Workflows
By
–
Flowise is a horizontal platform, catering different LLM ochestration, models, to enable users craft their own agent/workflow. Although OpenAI is on the lead, but we will soon see more improvement on other LLMs, enabling more possibilities.
-
Building Email Bots with LLM Technology at H2O GenAI World
By
–
"Never reply to an email again!" Luiz Pizzato, Executive Manager #AI at @CommBank walked the audience through how to build their own email bot using #LLM. #H2OGenAIWorld
-
LLMs Develop Apps Through Agent-Based Models and Strategy
By
–
LLMs can develop code-based apps, manage complex tasks, and construct business models with proper strategy. MetaGPT and Baby AGI models use distinct agents, guided by human SOPs for precision for the former.
-
Mastering Open Source h2oGPT with RAG and Agents
By
–
Technical speaker session underway! Jon McKinney (
@pseudotensor
) and @ArnoCandel delve deep into Mastering Open Source #h2oGPT with Retrieval Augmented Generation (#RAG), web search, and agents. #H2OGenAIWorld -
Meta Embodied AI Group: LLMs Not Involved in Stair Climbing
By
–
So has the Embodied AI group at Meta.
The point is that the LLM is absolutely not involved in the stair climbing skill.