⚔️ Ai
Are LLMs good at handling geo-political conflicts? Nice deep-dive on this topic in @MLamparth's paper: Human vs. Machine: Language Models and Wargames simulating a US-China conflict
TL;DR: Please don’t do this 😬
1
23
Nibo.AI retweeted
Wow! This is cool, for anyone using Self-consistency-like methods. This paper discovers a non-monotonic relationship between the number of LLM calls and performance. Contrary to what one might intuitively expect, making more calls to a LLM not always = performance improvements
This surprised us. If you call #chatgpt multiple times and take the consensus, the quality of the answer can get worse as the # of #LLM calls increases.
We explain why this happens in our new paper and also show how to estimate the optimal # of LLM calls arxiv.org/pdf/2403.02419.pdf
Nibo.AI retweeted
Plan and Solve it probably the most powerful improvement over Zero-Shot CoT's "Let's think step by step". Actually so powerful that sometimes it matches few-shot CoT
Nibo.AI retweeted
STEP-BACK PROMPTING is a method to improve the reasoning abilities of LLMs by prompting to first abstract high-level concepts / principles before reasoning towards the solution.
Demonstrated substantial performance++ across a range of challenging reasoning-intensive tasks.
Nibo.AI retweeted
A funny one from @SFResearch : The FlipFlop effect
Introduced the FlipFlop experiment* : a multi-turn conversation setup where LLMs first provide an answer to a classification task and are then challenged with a follow-up phrase like "Are you sure?".
authors here: @PhilippeLaban @CaimingXiong , @murakhovska, @jasonwu0731
Nibo.AI retweeted
I was using GPT4 Advanced Data Analysis to explore some data and it suggested to do Sentiment Analysis. It worked from the 1st try (!) but the moment I saw the results it was obviously a cool situation where the "pure" LLM would do a much more satisfying job. Some caveats bellow:
Nibo.AI retweeted
2. I found that when using the above prompt, GPT4 provided better outputs compared to Claude. However, I still preferred using Claude due to its 100k context window. This allowed me to quickly classify a few hundred rows without the need to divide them into multiple prompts.
Nibo.AI retweeted
So when using llm agents, the ability to know when they need help is crucial for human-AI collaboration. We got inspired by a cool idea from a Deepmind robotics paper
Enriching inter-departmental operations in the modern workplace linkedin.com/in/michael-eder…
#automation #worktogether #kanban #collaboration
2
Waiting for an #approval can cancel most of the benefits of an #automation, so we explore a few ways to make this #efficient.
blog.nibo.ai/managing-approv…
#bot #conversatioanlUI #chatbot #digitaltransformation #processautomation #processengineering #workflowmanagement
Hola!
"Construyendo una plataforma de automatización" por @vmuaddib#PlanetaChatbot planetachatbot.com/construye…
What's the most common UI you interact with every day?
Design insights from @ioanahalunga - Transitioning from a classic interface to a #conversationalUI.
blog.nibo.ai/chat-inputs-vs-…
#chatbot #Bot #Automation #ux #uidesign #design
Web app design tips from @ioanahalunga. Worth the read 📚
buff.ly/2plT7wc
#design #ui #ux #userinterface #UserExperience
A friendly #bot 🤖, a four in one matching #algorithm 🐙 and a #cloud #automation engine ⚡ walk into a bar...
buff.ly/2D9uLiK















