GOES

• Register for GSAW – done

SBIR

• More status report

GPT Agents

• Started digging into the GPT-3 documentation. They have a playground which lets you interactively try prompts on the different models. I think this could knowledge could be pulled out in a pretty straightforward way through multiple probes and regex. Here’s some examples:

The great religions of the world are:

Judaism

Christianity

Islam

Hinduism

Buddhism

Sikhism

Jainism

Confucianism

Shinto

A list of the closest religions to Judaism:

Christianity (30%)

Islam (30%)

Buddhism (5%)

Sikhism (5%)

Hinduism (3%)

A list of the closest religions to Christianity:

Judaism

Islam

Hinduism

Buddhism

Agnosticism

Atheism

Christianity

Orthodox

Catholic

Theism

God

• Note that the Judaism and Christianity lists support each other. This could look a lot like the original mapping Java mapping code?
• It does not know about the pandemic (prompt is bold): “coronavirus is a member of the Coronaviridae family, which includes animals and birds as known hosts. The virus is a single-stranded, positive-sense RNA virus with a genome of approximately 30 kb. The genome is organized into three segments: S, M, and L.“
• 3:00 meeting today
  • See if I can train up monthly models
  • Create prompts and evaluate their default
  • Run prompts with Ecco for ranking with our relative terms
  • We’re going to try for the social sensing workshop:
    • The social sensing workshop (started in 2015) is a multidisciplinary meeting place that brings together social scientists and computer scientists, interested in social media analysis, around research that interprets social media as measurement instruments. Social media democratized information production offering an unprecedented view into human habits, customs, culture, stances, and indeed descriptions of physical events that transpire in the world. They also give unprecedented opportunities to spread misinformation, influence opinion, distract from the truth, or advance specific agendas, hidden or overt. The potential of social media to influence populations has brought about an interest in understanding information operations; namely, coordinated efforts on social media meant to alter people’s opinions, emotions, or understanding of events. What are scientific foundations for modeling this new communication, measurement, and influence channel? How to utilize information media signals to better understand social systems, communities, and each other? How to identify and mitigate misuse of this medium? What specifically can one measure or influence, what underlying theoretical framework allows one to do so, and what applications are enabled by the endeavor?  Since measurement and influence operations are well-studied in many physical domains, what can one learn from the physical domain (e.g., from the signal processing literature) to enable novel social media analysis methods? This scope brings about new interdisciplinary research challenges and opportunities at the intersection of communication and sensing, social network analysis, information theory, data mining, natural language processing, artificial intelligence, and social sciences.