Search Results for: chatgpt
ChatGPT Experiments: Summary And Q&A About The Protests In Peru
Following our analysis this morning of protests in France using ChatGPT, what might it tell us about protests in Peru?…
ChatGPT Experiments: Summary And Q&A About The Protests In France
How might OpenAI's ChatGPT help analyze protest news coverage monitored by GDELT? To explore this further, we used GDELT's Web…
ChatGPT Experiments: Summarization And Q&A About Iranian Television News Take Two (When Things Go Wrong & The Importance Of Prompt Engineering)
To explore the impact of prompt engineering, increased attention and brittleness on OpenAI's ChatGPT, we applied it to the same…
ChatGPT Experiments: Summarization And Q&A About Iranian Television News
In similar fashion to our exploration of ChatGPT's ability to summarize and answer questions about Russian television news, how might…
ChatGPT Experiments: Summarization And Q&A About Russian Television News
As part of our continued experiments with OpenAI's ChatGPT, what would it look like to ask it to summarize a…
ChatGPT Experiments: Summarizing An ABC Evening News Broadcast
OpenAI's ChatGPT large language model has attracted considerable attention for its ability to generate human-fluency responses in an interactive Q&A…
What OpenAI's Whisper Teaches Us About The Future Of Large Language Models Like ChatGPT
While specialty AI models like OpenAI's Whisper ASR speech recognition and translation target a more technical and niche audience, they…
Why Gemini 1.5 Pro Describes President Biden As "Confused" & "Disoriented" And What It Tells Us About Training Data
One of the more fascinating findings from our experiments with Gemini 1.5 Pro's video capabilities is how strongly it associates…
Early Findings With Gender, Racial & Cultural Bias In Generative AI Embeddings, Models & Guardrails
As we continue to explore how various generative AI offerings from different companies perform across global news coverage, one area…
Gemini 1.5 Pro's 1 Million Token Model + Chirp: Fully Autonomous Diplomacy Through AI Watching Television
Earlier today we demonstrated the incredible ability of Google's new Gemini 1.5 Pro foundation model and its one million token…
Generative AI Experiments: GenAI Coding Copilots: More Networking Code Troubles
As we continue to evaluate the capabilities of advanced Generative AI coding copilots, we find that they offer reasonable performance…
Larger Generative AI Models Don't Equal Better Results: Disease Outbreak Codification With Bison, Unicorn, Gemini, GPT 3.5 & GPT 4.0
This past February we explored the use of LLMs for extracting and codifying disease outbreaks, finding potential but significant limitations…
More Experiments In Automated Diplomacy: Countering Bad News About Ukraine Part 2
Yesterday we explored the concept of fully automated counter-messaging powered by LLMs, using ChatGPT to write an automated rebuttal to…
More Experiments In Automated Diplomacy: Countering Bad News About Ukraine
Earlier this year we explored the concept of fully autonomous diplomacy: using LLMs to autonomously monitor media coverage of a…
What Do The Major Generative Search Engines Say About Hamas Attacking Israel & Israel's Reaction?
Given that the general public is increasingly turning to LLMs and generative search engines like ChatGPT, Bing and Bard for…
How LLM Guardrails Defeat RAG-Based Generative Search Applications For Global Events
Retrieval Augmented Generation (RAG) has become perhaps the dominate mechanism through which to expand and update the memories of LLMs….
Summarizing Global Reaction To Gaza With DOC 2.0 API + LLM: Major News Story Headline Summarization
Earlier this year we explored how the DOC 2.0 API could be used to search for coverage of a specific…
Gender & Race Bias In Multimodal Image Embedding Models: A Case Study Of OpenAI's CLIP & How White Men Are Doctors & CEOs Not Black Women
Over the past few months we've documented innate existential racial and gender bias in many of the textual embedding models…
The Perils Of LLMs For Translation Tasks On Lower-Resource Languages: Estonian Noun Declension
One of the great promises of large language models (LLMs) is their ability to revolutionize translation and linguistic tasks. A…
More Experiments With DOC 2.0 API + LLMs = Summarizing Headlines: Turkish Investment, Inflation & The Niger Coup
Last month we explored using ChatGPT (GPT-3.5) to summarize search results from the DOC 2.0 API for at-scale landscape summarization…
More Experiments With LLM Translation: GCP's PaLM On Government Translation
With the General Availability of Chinese language support in Google's PaLM LLM, let's repeat our earlier tests of LLM-based translation…
Experiments With Meta's SeamlessM4T Open Machine Translation Model: Social Media Posts
Continuing our series of evaluating Meta's new SeamlessM4T multimodal translation model. Let's try translating some Weibo social media posts that…
DOC 2.0 API + LLMs = Summarizing Headlines: Turkish Investment, Inflation & The Niger Coup
The DOC 2.0 API allows rich keyword search over English machine translations of GDELT's online news monitoring in 65 languages….
Understanding Hallucination In LLMs: A Brief Introduction
There is a lot of confusion and misunderstanding about what "hallucination" is in large language models (LLMs), how it can…