Continue Reading

Large-Token LLMs: Combining GCP's New 32K PaLM Model + ChatGPT To Reword Summaries For Different Audiences

Enterprise production applications of LLMs must often balance the critical tradeoffs between quality and cost. Token costs for the most…

Continue Reading

Creating A Daily Disease Summarizer Using The DOC 2.0 API + PaLM/ChatGPT

Yesterday we explored different workflows for using the DOC 2.0 API to track global disease outbreaks using LLMs to summarize…

Continue Reading

DOC 2.0 API + PaLM/ChatGPT = Weekly Disease Summarization: Single Or Three-Part Prompts?

Following on our experiments with combining the DOC 2.0 API and LLMs like PaLM or ChatGPT to summarize global headlines,…

Continue Reading

More Experiments With LLM Translation: GCP's PaLM Vs ChatGPT For Headline Translation

Continuing our LLM translation experiments, let's compare PaLM to ChatGPT (GPT-3.5) for news headline translation in which the majority of…

Continue Reading

More Experiments With LLM Translation: Translation Stability In GCP's PaLM Vs ChatGPT

Continuing our series evaluating LLM translation capabilities, we'll have PaLM and ChatGPT translate two paragraphs from a Chinese language news…

Continue Reading

More Experiments With LLM Translation: GCP's PaLM Vs ChatGPT Vs Google Translate On News Translation

With the General Availability of Chinese language support in Google's PaLM LLM, let's repeat our full-length news media translation experiments, comparing…

Continue Reading

More Experiments With LLM Translation: GCP's PaLM Vs ChatGPT Vs Google Translate On Social Media Translation

With the General Availability of Chinese language support in Google's PaLM LLM, let's repeat our Weibo social media post translation experiments,…

Continue Reading

Extracting & Codifying Disease Outbreaks Using LLMs: Experiments With Bison, ChatGPT & Claude

Earlier this year we explored the use of LLMs for disease extraction and codification tasks from news coverage, testing how…

Continue Reading

OpenAI's ChatGPT Holding Steady On Business TV News Channels But Little Mention On Others

The timeline below shows TV news coverage of OpenAI and ChatGPT, showing mainstream channels are mentioning ChatGPT little, even while…

Continue Reading

Gender & Race In ChatGPT's CEO Stories & How Embedding Models Rank White Male CEOs First And Women Last

Yesterday we explored how LLM-based embedding models can encode severe gender and racial bias. Earlier this past week we explored…

Continue Reading

More Experiments Using LLMs For Machine Translation: Stability Of ChatGPT Translations Of Chinese-Language News & Social Content

We've previously demonstrated the ability of LLMs to provide highly fluent translations that exceed the fluency and "naturalness" of classical…

Continue Reading

ChatGPT's Puzzling Inability To Solve A Simple Physics Riddle & The Brittleness Of Reasoning

Interviewers, especially at technology companies, have historically often turned to thought puzzles to understand how a candidate reasons under uncertainty….

Continue Reading

OpenAI & ChatGPT Are Fading In The News: Media Shifts From Posterchild "OpenAI" To "Generative AI"

A deep dive into media coverage of the emerging world of generative AI suggests a pivot from OpenAI as the…

Continue Reading

CJR: How The Media Is Covering ChatGPT

The Two Center has an article in today's Columbia Journalism Review (CJR) exploring how the media has covered ChatGPT and…

Continue Reading

Experiments Using ChatGPT + Wikipedia For Media Cataloging

ChatGPT offers a general purpose summarization and Q&A workflow that can be applied to any textual input sources, with especial…

Continue Reading

Charleston Conference: The Future Of Scholarly Communication In A ChatGPT World

Kalev spoke today at the Charleston Conference's Charleston In Between event "The Future Of Scholarly Communication In A ChatGPT World":…

Continue Reading

This Week: Charleston Conference: The Future Of Scholarly Communication In A ChatGPT World

Kalev will be speaking at the Charleston Conference's Charleston In Between event "The Future Of Scholarly Communication In A ChatGPT…

Continue Reading

Using ChatGPT + CSPAN To Automatically Identify Mentions Of House Resolutions & Bills In Congressional Transcripts

Could we use ChatGPT to analyze a CSPAN broadcast of a House of Representatives session and automatically identify all mentions…

Continue Reading

Using ChatGPT + CSPAN To Enhance The Transcripts Of Our Nation's Congressional Lawmaking

Yesterday we demonstrated the ability of ChatGPT to enhance hand-typed television news transcripts by converting them from endless streams of…

Continue Reading

Using ChatGPT To Enhance Hand-Generated Television News Closed Captioning

Hand-generated television news closed captioning in the US is typically exclusively upper or lower case and is often riddled with…

Continue Reading

Hallucination In Summarization: When ChatGPT Hallucinated New Stories In An Evening News Broadcast

Yesterday we compared how OpenAI's ChatGPT and Google's Bard summarize a television evening news broadcast. Look closely and you'll spot…

Continue Reading

Google's Bard Vs OpenAI's ChatGPT: Summarizing An ABC Evening News Broadcast

Last month we explored using OpenAI's ChatGPT to summarize an ABC Evening News broadcast, testing its ability to look across…

Continue Reading

Fully Autonomous Diplomacy + Counter-Messaging Experiments With ChatGPT + GDELT + Midjourney v5

Yesterday we demonstrated the use of ChatGPT in a fully autonomous counter-messaging pipeline, designed to automatically monitor television news coverage…

Continue Reading

Replacing Bespoke AI Categorization Models By Using ChatGPT To Create Instant Models

Could ChatGPT be used to create instant categorization models that perform the same task as bespoke models trained on large…