AGENTS - AI Dynamics

LangChain SequentialChain generates entire app automatically

By

–

20 July 2023 17h00

An AWESOME trace by @kreneskyp generating an entire app with a single SequentialChain https://
smith.langchain.com/public/92835ea
d-e1da-45b2-b99d-4ff1a0f6c301/r
… We add a new #cool-langsmith-traces channel in our discord to share fun things like this. How crazy can it get?

→ View original post on X — @hwchase17

20 July 2023

Neural CAs and Open-Ended Evolution: Towards AGI Through ALife

By

@hardmaru

–

20 July 2023 9h55

Interesting work that uses Neural CAs to study open-ended evolution and complexification by simulating an artificial ecosystem.

I think we need ALife as a stepping stone to reach “AGI” (or highly adaptive AI). Artificial Life >> Artificial Intelligence‼️https://t.co/D3kEuOsbRk https://t.co/G7IVUAWYID
— hardmaru (@hardmaru) 20 juillet 2023

Interesting work that uses Neural CAs to study open-ended evolution and complexification by simulating an artificial ecosystem. I think we need ALife as a stepping stone to reach "AGI" (or highly adaptive AI). Artificial Life >> Artificial Intelligence https://google-research.github.io/self-organising-systems/2023/biomaker-ca/
…

→ View original post on X — @hardmaru

20 July 2023

AI-First Agencies Opportunity: Revolutionary Campaigns with Advanced Tools

By

@bentossell

–

20 July 2023 9h20

There’s opportunity for AI first agencies to launch, embrace ai tools and build wild campaigns for clients that want it. Think http://
sandwich.co with ai first tooling

→ View original post on X — @bentossell

20 July 2023

Auto-GPT vs ChatGPT: Autonomy, Self-Tasks, and Limitations

By

@ingliguori

–

20 July 2023 9h17

Auto-GPT acts autonomously to achieve goals using GPT models, while ChatGPT requires manual prompts. Auto-GPT can self-assign sub-tasks, but as a closed system lacks true self-improvement. ChatGPT converses naturally but must be guided. Via @ingliguori #AutoGPT #ChatGPT #AI

→ View original post on X — @ingliguori

20 July 2023

LLMs as Workers in Human-Computational Crowdsourcing Algorithms

By

@_akhaliq

–

20 July 2023 7h01

LLMs as Workers in Human-Computational Algorithms? Replicating Crowdsourcing Pipelines with LLMs paper page: https://
huggingface.co/papers/2307.10
168
… LLMs have shown promise in replicating human-like behavior in crowdsourcing tasks that were previously thought to be exclusive to human

→ View original post on X — @_akhaliq

20 July 2023

Android in the Wild: Large-Scale Dataset for Device Control

By

@_akhaliq

–

20 July 2023 6h04

Android in the Wild: A Large-Scale Dataset for Android Device Control paper page: https://
huggingface.co/papers/2307.10
088
… There is a growing interest in device-control systems that can interpret human natural language instructions and execute them on a digital device by directly controlling

→ View original post on X — @_akhaliq

20 July 2023

Unified Agent Framework with Foundation Models for Multimodal AI

By

@_akhaliq

–

20 July 2023 4h28

Towards A Unified Agent with Foundation Models paper page: https://
huggingface.co/papers/2307.09
668
… Language Models and Vision Language Models have recently demonstrated unprecedented capabilities in terms of understanding human intentions, reasoning, scene understanding, and planning-like

→ View original post on X — @_akhaliq

20 July 2023

Apple GPT with personal data will win consumer AI

By

@aibreakfast

–

20 July 2023 3h53

Apple GPT coming to your iPhone next year. Imagine a language model that has access to years worth of your iMessage exchanges, emails, photos, and health data. This is why Apple, while late to the game, will win consumer AI.

→ View original post on X — @aibreakfast

20 July 2023