Skip to content

AI Dynamics

Global AI News Aggregator

Rechercher

PROMPT ENGINEERING

Universal Self-Adaptive Prompting for Zero-Shot LLM Learning

By

@googleai

–

09 December 2023 6h43

Visit the #EMNLP2023 Google booth today at 3:30 PM to learn about Universal Self-Adaptive Prompting, an automatic method tailored for zero-shot learning (while compatible with few-shot) that uses a small amount of unlabelled data & an inference-only LLM. pic.twitter.com/m8tRtXt1pL
— Google AI (@GoogleAI) 9 décembre 2023

Visit the #EMNLP2023 Google booth today at 3:30 PM to learn about Universal Self-Adaptive Prompting, an automatic method tailored for zero-shot learning (while compatible with few-shot) that uses a small amount of unlabelled data & an inference-only LLM.

→ View original post on X — @googleai

9 December 2023
Optimizing AI Workflows with Custom GPTs and Zapier Integration

By

@testingcatalog

–

08 December 2023 23h05

Moreover, I'm utilizing one of my custom GPTs specifically designed to fine-tune instructions for the others. To enhance this process, I'm integrating @zapier custom actions to streamline the transfer of these refined prompts directly into Notion, thereby minimizing manual work.

→ View original post on X — @testingcatalog

8 December 2023
Integrating Custom GPTs for Automated Content Publishing Pipelines

By

@testingcatalog

–

08 December 2023 23h04

In my efforts to fully automate my content publishing pipeline, I've been focusing on creating various custom #GPTs. A critical element in this process is ensuring that all these GPTs have consistent context for optimal functionality. To address this, I've integrated these GPTs

→ View original post on X — @testingcatalog

8 December 2023
Replicate Launches Stable Diffusion Guide for Developers

By

@fofrai

–

08 December 2023 22h23

We've just launched guides on Replicate. Starting with a basics guide to Stable Diffusion: https://
replicate.com/guides/stable-
diffusion
… But what should we do next?
What do you need an in-depth guide on?

→ View original post on X — @fofrai

8 December 2023
Prompting Subscriptions Will Replace Tipping Culture

By

@localghost

–

08 December 2023 19h00

the new hotness will be prompting months instead of tipping

→ View original post on X — @localghost

8 December 2023
ChatGPT Performance Degradation: System Prompt and Behavioral Factors

By

@localghost

–

08 December 2023 18h54

There’s a fun theory I saw about degraded ChatGPT performance: It’s worse because the system prompt says it’s December (holidays), in the same way that “tipping” it $200 makes it better.

→ View original post on X — @localghost

8 December 2023
Flowise v1.4.4 Integrates LangChain Hub for Prompt Management

By

@flowiseai

–

08 December 2023 18h08

Switching between LLMs often involves changing the underlying prompt.

For example, Llama2 performs better with special syntax like [INST]🤖

Flowise v1.4.4 is now supporting @LangChainAI Hub! Users can view and load prompts contributed by community 🫶 pic.twitter.com/AeHs9ly7mB
— FlowiseAI (@FlowiseAI) 8 décembre 2023

Switching between LLMs often involves changing the underlying prompt. For example, Llama2 performs better with special syntax like [INST] Flowise v1.4.4 is now supporting @langchain Hub! Users can view and load prompts contributed by community

→ View original post on X — @flowiseai

8 December 2023
RAG Performance Limits and Multi-Assistant Solutions

By

@officiallogank

–

08 December 2023 17h41

RAG performance will degrade beyond that point, better to use multiple assistants today but it’s possible we’ll expand the limit in the future!

→ View original post on X — @officiallogank

8 December 2023
CLIP’s Strategy for Handling Unmentioned Visual Concepts in Images

By

@_yutaroyamada

–

08 December 2023 10h12

Thus, when an image includes two concepts (e.g. a lemon and an eggplant) while the text prompt only mentions one concept (e.g. lemon), CLIP attempts to account for the unmentioned concept (like the eggplant) by saying 'purple', a color commonly associated with eggplants.
3/5

→ View original post on X — @_yutaroyamada

8 December 2023
Gemini Multimodal Prompting: Creating with Image and Text

By

@oriolvinyalsml

–

07 December 2023 23h13

Really happy to see the interest around our “Hands-on with Gemini” video. In our developer blog yesterday, we broke down how Gemini was used to create it. https://t.co/50gjMkaVc0

We gave Gemini sequences of different modalities — image and text in this case — and had it respond… pic.twitter.com/Beba5M5dHP
— Oriol Vinyals (@OriolVinyalsML) 7 décembre 2023

Really happy to see the interest around our “Hands-on with Gemini” video. In our developer blog yesterday, we broke down how Gemini was used to create it. https://
developers.googleblog.com/2023/12/how-it
s-made-gemini-multimodal-prompting.html
… We gave Gemini sequences of different modalities — image and text in this case — and had it respond

→ View original post on X — @oriolvinyalsml

7 December 2023

←Previous Page

1 … 907 908 909 910 911 … 1,161

INNOVATION GENERATIVE AI RESEARCH LLMS TOOLS MACHINE LEARNING CODE MARKET TRENDS TECHNOLOGY BUSINESS BIG TECH ETHICS ENTERPRISE AI SOFTWARE AGENTS AUTOMATION APPS COMPUTING DATA POLICY OPEN SOURCE MULTIMODAL AI REGULATION CULTURE CREATIVE AI PROMPT ENGINEERING SOCIETY ECONOMY SAFETY EDUCATION INVESTMENT AI HARDWARE AGI HARDWARE JOBS STARTUPS INDUSTRY ROBOTICS WORKFORCE SECURITY CYBERSECURITY HEALTHCARE AI SYSTEMS SUSTAINABILITY WEB3 DECENTRALIZED AI

AI Dynamics

Global AI News Aggregator

About
Archives
Contact

Rechercher