AI - AI Dynamics

→ View original post on X — @tamaramccleary

Skills to Navigate Technology’s Future of Work

By

@tamaramccleary

–

27 August 2023 17h10

‘Change is the only certainty in tech’: Skills to keep pace with the #FutureofWork https://
bit.ly/45SYhmo via @siliconrepublic

→ View original post on X — @whats_ai

MetaGPT Redefines Multi-Agent Collaboration for Complex Tasks

By

@whats_ai

–

27 August 2023 17h07

After two weeks off, here's a new video about a very exciting work by @DeepWisdom2019 ! MetaGPT: Redefining Multi-Agent Collaboration for Complex Tasks Learn more: https://
youtu.be/YtxMderNrzU #MetaGPT #GPT #ChatGPT #Agents

→ View original post on X — @terence_mills

AI and LLMs Streamlining Financial Services and Payments

By

@terence_mills

–

27 August 2023 17h00

How AI And LLMs Are Streamlining Financial Services
#payments #fintech #paymentsolutions @briansolis @Xbond49 @VitalikButerin @DataScienceCtrl @Benioff @johnnosta @IrmaRaste @Tiffani_Bova http://
ow.ly/4hgf30swTtN

→ View original post on X — @aibreakfast

LLMs training on self-generated text as machine learning inbreeding

By

@aibreakfast

–

27 August 2023 16h46

LLMs generating new text that they will then use to further train LLMs is the machine learning version of inbreeding.

Language-to-Rewards System for Robotic Skill Synthesis

By

–

27 August 2023 16h32

10/ Language to Rewards for Robotic Skill Synthesis – proposes a new language-to-reward system that utilizes LLMs to define optimizable reward parameters to achieve a variety of robotic tasks.https://t.co/8ztl4MMyjS
— DAIR.AI (@dair_ai) 27 août 2023

10/ Language to Rewards for Robotic Skill Synthesis – proposes a new language-to-reward system that utilizes LLMs to define optimizable reward parameters to achieve a variety of robotic tasks.

Survey of LLM-Based Autonomous Agents and Applications

By

–

27 August 2023 16h32

7/ A Survey on LLM-based Autonomous Agents – presents a survey of LLM-based autonomous agents; delivers a systematic review of the field and a summary of various applications of LLM-based AI agents in domains like social science and engineering.

Prompt2Model: Automated Small Model Training Pipeline

By

–

27 August 2023 16h32

8/ Prompt2Model – takes a prompt describing a task and trains a small model that is conducive to deployment; the pipeline automatically collects and synthesizes knowledge through three channels: dataset retrieval, dataset generation, and model retrieval.

LegalBench: Legal Reasoning Benchmark for LLMs

By

–

27 August 2023 16h32

9/ LegalBench – a collaboratively constructed benchmark for measuring legal reasoning in LLMs; it consists of 162 tasks covering 6 different types of legal reasoning.

Giraffe: Extended Context Length LLMs from Llama Base Models

By

–

27 August 2023 16h32

5/ Giraffe – new models that are fine-tuned from base Llama and Llama 2; extends the context length to 4K, 16K, and 32K; explores the space of expanding context lengths in LLMs so it also includes insights useful for practitioners and researchers.