Continue Reading

Visual Explorer: Computer Chronicles 1982-2002 Archive Transcribed

Earlier this year in collaboration with the Internet Archive, we made available in the Visual Explorer the complete 1982-2002 archive…

Continue Reading

Last Week: 35th MINDS Conference Toronto: The Promise & Perils Of AI For Journalism: Lessons Learned From A Quarter-Century Of Using AI To Catalog The Planet Through News

It was an incredible honor to speak last week at the 35th MINDS Conference in Toronto! From the large language…

Continue Reading

This Week: AI @ IA : Research in the Age of Artificial Intelligence: A Decade Of TV News Archive Research

Kalev will be speaking at this week at the Internet Archive's annual gala on a decade of his collaborations with…

Continue Reading

Next Week: Data For Peace 2023: Using Data And AI For Conflict Early Warning And Crisis Prevention

Kalev will be speaking next Monday on the afternoon plenary panel at the Data For Peace 2023 conference on "Using…

Continue Reading

Visual Explorer: World War II US War Department Films Selection Transcribed

This past February we unveiled a small collection of US War Department films from World War II in the Visual Explorer's interface…

Continue Reading

Coming Soon: 11M Minutes Transcribed Through Google's Chirp

Our massive collaborative initiative to transcribe the entire Internet Archive Television News Archive has reached 11 million minutes of transcribed…

Continue Reading

Today: 35th MINDS Conference Toronto: The Promise & Perils Of AI For Journalism: Lessons Learned From A Quarter-Century Of Using AI To Catalog The Planet Through News

Kalev is speaking today at the 35th MINDS Conference in Toronto! From the large language models at the vanguard of…

Continue Reading

ZeroHedge: Media Coverage Of Ukraine War Dwindles

ZeroHedge republishes Kalev's RealClearPolitics article on media coverage of Ukraine. Read The Full Article.

Continue Reading

Media Coverage of Ukraine War Dwindles

As the Russia-Ukraine war grinds on more than a year and a half after the initial invasion, U.S. economic and…

Continue Reading

Generative AI Experiments: At-Scale TV News Summarization Experiments Coming Soon

Yesterday we explored summarizing an entire day of Russian television news using Google's new 32K PaLM LLM model. Stay tuned…

Continue Reading

Generative AI Experiments: Using LLMs To Summarize Any SRT Closed Captioning File Using GCP's 32K PaLM Model

The SRT closed captioning format is a wide-used file format for storing the machine-readable closed captioning transcripts of videos. A…

Continue Reading

Summarizing An Entire Day Of Russian TV News Using Google's New 32K PaLM LLM Model

Last month we demonstrated the use of Google's new 32K PaLM LLM to summarize entire evening news and CSPAN broadcasts…

Continue Reading

35th MINDS Conference Toronto This Week

A reminder that Kalev will be speaking at the 35th MINDS Conference in Toronto this week. Learn More.

Continue Reading

Next Week: AI @ IA : Research in the Age of Artificial Intelligence: A Decade Of TV News Archive Research

Kalev will be speaking at next week at the Internet Archive's annual gala on a decade of his collaborations with…

Continue Reading

Recession Coverage Remains Steady On TV News, Declining In Online News

The timeline below shows mentions of a recession spiking during the early pandemic shutdowns, then again in February of last…

Continue Reading

How Is Nagorno-Karabakh Being Covered On Television News?

The timeline below shows the total seconds of airtime over the past two weeks in which Nagorno-Karabakh has been mentioned…

Continue Reading

How Is The Murder Of Hardeep Singh Nijjar Being Covered In The News?

How are the story of Hardeep Singh Nijjar's murder and Canada's accusations being covered in the news? The timeline below…

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

Large-Token LLMs: Using GCP's New 32K PaLM Model To Summarize Two CSPAN Broadcasts

Earlier this month we explored using Google's new 32K PaLM LLM model to summarize an entire evening news broadcast. Let's…

Continue Reading

Hallucinating Detail In Simple Summaries: Why LLM "Grounding" Doesn't Work To Combat Hallucination

One of the most commonly recommended methods of reducing hallucination in LLMs is called "grounding" in which the LLM is…

Continue Reading

Deep Linking Democracy: An Index Of Half A Million Legislative Mentions On CSPAN Spanning 2009-2023

Today in collaboration with the Internet Archive's TV News Archive, we are immensely excited to announce a massive new index…

Continue Reading

Visual Explorer: Live Transcription Of All 24 Active Uncaptioned Channels Through Google's Chirp

Last week we announced a massive historical backfile of 9.5 million minutes of machine-generated multilingual transcripts of global television news…

Continue Reading

Experiments In Summarizing Global Media Tenor: Views Towards China – Part 2

Continuing our experiments with using LLMs to summarize global media coverage, let's use the final workflow that yielded the best…

Continue Reading

Experiments In Summarizing Global Media Tenor: Views Towards China – Part 1

How might we use LLMs to summarize at-scale media tone and portrayals of countries? Let's look at a few different…