Category: Uncategorized
Prompt Evolver & The Limits Of Prompt Engineering For LLM-Based Summarization
Earlier today we unveiled a glimpse of Prompt Evolver, our internal workflow for fully unsupervised autonomous LLM prompt engineering and…
Google's Chirp, Large Speech Models And The Future Of Globalized Speech Transcription For Video – A Brief Example
Google's Chirp speech transcription system is an example of the new generation of Large Speech Models that are transforming globalized…
Presenting Prompt Evolver: Fully Autonomous LLM-Driven Prompt Evolution/Optimization: Crafting The Ultimate Summarization Prompt & The Limits Of LLM Summarizers
Today, the majority of LLM prompts are written and laboriously optimized by human beings through manual prompt engineering. What if…
Global Perspectives On The Future Of AI: Governance & Industry
One of the most fascinating dimensions of my travels over the last few months has been the incredible opportunity to…
Generative Image AI: How OpenAI's DALL-E Imagines A Collection Of Conferences From Their Descriptions
Given the trivial accessibility of modern generative image AI that can create images from textual descriptions, what might the descriptions…
Prompt Evolver: Using An LLM To Autonomously Construct Its Own Prompts From Example Inputs/Outputs: Translation & Summarization
Yesterday we explored autonomous prompt construction, in which LLMs are given a set of examples and asked to construct an…
WashPost: Crime Is Down, Though Fox News Viewers Might Not Be Aware
The Washington Post's Philip Bump examines how the media has covered crime. Read The Full Article.
Prompt Evolver: Using An LLM To Autonomously Construct Its Own Prompts From An Example Input/Output: Disease Extraction
Over the last two days we've explored using LLMs for automated biosurveillance, feeding them news articles and having them extract…
Personas, Prompt Engineering, Instruction & Multishot Prompting Don't Guarantee Better Results: Disease Outbreak Codification With Bison, Unicorn, Gemini, GPT 3.5 & GPT 4.0
Yesterday we reexamined LLM-powered global disease outbreak codification, testing how five major commercial LLMs (Google's Bison, Unicorn and Gemini Pro…
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…
Generative AI Experiments: Creativity As Prompt Vs Temperature In Google's Bison, Unicorn & Gemini Pro Models
Historically, the concept of "creativity" was largely embedded in LLMs through a combination of their prompt-level specification and API-level temperature…
Generative AI Experiments: Comparing Google's Bison, Unicorn & Gemini Pro Models For Summarization
The majority of our past LLM experimentation with GCP models have been with the PaLM Bison model, since this was…
Why We Need To Acknowledge The Limitations Of Generative AI: Bias, Hallucination & RAG
One of the strangest aspects of the generative AI revolution is the vast disconnect between the hype expressed in public…
The Hidden Dangers Of Generative Coding (CodeGen) Guardrails
One of the most intriguing findings from our generative code modernization (codegen) experiment earlier today was the degree to which…
Experiments With Generative Coding: Modernizing Legacy BigQuery Code & CodeGen Guardrails
Modern generative coding systems have garnered immense hype, frequently presented as drop-in replacements for human coders. Yet, the majority of…
WashPost: To Whom Will Republican Lawmakers Listen, Zelensky Or Republican Voters?
The Washington Post's Philip Bump looks at US Congressional support for Ukraine Read The Full Article.
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…
TRT World: Exclusive interview With Founder Of GDELT Project Kalev Leetaru
A brief clip from one of my interviews at TRT World Forum 2023 was published today: Watch The Video.
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…
Generative AI Experiments: Deep Dive Comparisons Series Coming Next Week
Stay tuned for a deep dive series re-examining the state of LLM capabilities next week across a range of domains…
Generative AI Experiments: Gemini Pro & Unicorn Examples Coming Next Week
Stay tuned for a set of experiments evaluating the GCP Unicorn and Gemini Pro models next week.
Video: TRT World Forum 2023: All-Knowing AI: Creative Potential or Disruptive Evil?
The video of today's panel "All-Knowing AI: Creative Potential or Disruptive Evil?" at TRT World Forum 2023 in Istanbul is…
Early CodeGen Examples Coming Next Week
Stay tuned for some early generative AI code generation (codegen) examples to come next week.
Google Developer Expert (GDE) 2024
It is a tremendous honor to be a Cloud GDE (Google Developer Expert) since 2015, marking now 9 years in the…