The GDELT Project

Yesterday we explored boosting Gemini's video capabilities from its native one hour to 2.5 hours by overriding its sampling process…

Google's new Gemini 1.5 Pro LMM model accepts videos up to one hour in length and internally samples them into…

Stay tuned tomorrow for a first look at pushing Gemini beyond its default one hour input limitation for videos by…

The term #MeToo burst into the media in late 2017 , but largely faded from CNN and MSNBC by late…

Yesterday we demonstrated how Google's Gemini 1.5 Pro's video analysis capabilities make it possible to take a 6 minute clip…

One of the more fascinating findings from our experiments with Gemini 1.5 Pro's video capabilities is how strongly it associates…

As we continue to explore Gemini 1.5 Pro's video analysis capabilities, we've examined a number of different prompt approaches to…

As we continue to explore Google's Gemini 1.5 Pro model's native video capabilities, what if we scale our analysis from…

Yesterday we were surprised to discover sharply reduced performance from Gemini 1.5 Pro on our RW-NIAH (Real World Needle In…

Two weeks ago we examined Gemini 1.5 Pro's NIAH (Needle In A Haystack) performance, finding that when asked to identify…

As we continue to explore how various generative AI offerings from different companies perform across global news coverage, one area…

As we continue our experiments with having Google's Gemini 1.5 Pro model visually analyze a 6-minute video clip from Russian…

Yesterday we explored Google's Gemini 1.5 Pro model's video analysis capabilities by asking it to analyze a 6-minute clip of…

One of the most powerful capabilities of Google's new Large Multimodal Model (LMM) Gemini 1.5 Pro model is its ability…

On Wednesday, we announced in collaboration with the Internet Archive TV News Archive the machine transcription of its complete 2.5…

Yesterday we announced the complete machine transcription of the Internet Archive TV News Archive's complete 2.5 million hours of uncaptioned…

The Internet Archive's Television News Archive today preserves global television news coverage encompassing selections from 108 channels spanning 50 countries…

The Washington Post's Philip Bump explores the parallel media universes of cable television news. Read The Full Article.

Stay tuned for a truly incredible announcement coming this week.

The rapid proliferation of impressively capable "free" open source AI models with one-click installations and simplified workflows means companies increasingly…

There are many use cases like diagnosing an intermittent service fault, testing a new service or performing basic analytics like…

Searching social media to find relevant semantic domains often results in large text files, many of which are irrelevant due…

The Atlantic Council's Digital Forensic Research Lab (DFRLab) includes an analysis of Russian television news. Read The Full Article.

The Washington Post's Philip Bump examines media coverage of immigration. Read The Full Article.