Category: Uncategorized
Generative AI Experiments: "Where Is This Image" & The Critical Importance Of Tuning Models Against Over-Confidence
From their text-only roots as LLMs (Large Language Models), most major GenAI vendors now offer LMM (Large Multimodal Model) APIs…
Generative AI Experiments: Using GPT-4 And Gemini 1.5 Pro To Analyze Imagen 2 Images
With the public availability of Gemini 1.5 Pro, let's compare how two major LMM's (GPT-4 and Gemini 1.5 Pro) describe…
How Has Valentine's Day Been Covered On Television News Over The Past Decade?
How has Valentine's Day been covered on television news over the past decade? As the timeline below captures, mentions have…
Visual Explorer: Another 30 Million Minutes Transcribed Through Google's Chirp Transcription Model
Our massive collaborative initiative to transcribe the entire Internet Archive Television News Archive added another 30 million minutes of transcribed broadcasts…
Generative AI Experiments: More Experiments In Image Describing Coming Soon
Given the rapid advances in Large Multimodal Modal (LMM) models, stay tuned for a forthcoming series revisiting how far these…
AKAS: International Court Of Justice Media Coverage
AKAS released this chart tracking global media mentions of the International Court Of Justice (ICJ) via their iiiTracker (International Institutions…
Generative AI Experiments: Debugging A Networking Issue With GenAI Copilots Vs Stack Overflow & GitHub
Recently, we were forced to diagnose and address an extremely specialized edge case networking issue with a third party utility…
Generative AI Experiments: GenAI Coding Copilots: Asking GPT-4 & Gemini Ultra To Help Brainstorm A Trivial Video Quality Filter
The wonderful world of digital video is a vast, complex, nuanced and often arcane landscape of containers, formats, codecs, bitrate,…
Generative AI Experiments: GenAI Coding Copilots: More Networking Code Troubles
As we continue to evaluate the capabilities of advanced Generative AI coding copilots, we find that they offer reasonable performance…
AI In Production: A Deep Dive Into The Costs Of Multimodal Embedding Search Over 3 Billion Images
As we continue our behind-the-scenes series looking at AI technologies in real world production use cases, we've been estimating the…
Behind The Scenes: Building Resilient Infrastructure Through Hard Timeouts
One of the quickest lessons developers learn building true global-scale production applications is how quickly systems break down under extreme…
Generative Image AI: Asking DALL-E To Visualize A "Television News Archive"
Continuing our generative image AI series, we decided to ask DALL-E just what a "television news archive" looks like. Here…
Experiments With Speech Transcription: Classical Versus LSM Speech Transcription – An English Accent Example
Here is a fascinating brief example of just how much of an improvement Large Speech Models (LSMs) offer over classical…
Generative AI Experiments: Using Large Language Models To Correct Large Speech Model Transcripts
Large Speech Models (LSMs) offer massive accuracy gains over previous generation ASR systems, but like all automated systems are far…
How Television News Is Covering Taylor Swift
How is Taylor Swift being covered on cable television news? The timeline below shows monthly mentions of her across CNN,…
AI In Production: The Uncertainties For Large Enterprises Around Embedding Model Depreciation
Semantic search, Retrieval Augmented Generation (RAG), multimodal search – what do all of these technologies have in common? They all…
AI In Production: How To Think About The Ongoing Cost Of Rerunning Models As They Improve
One of the few certainties in the digital world is that the breathtaking pace of AI advancements over the past…
GCP Tips & Tricks: The Cost Of Storing 3PB In 6 Million Files In GCS In Different Storage Classes
Last week we examined the surprisingly cost-effective economics of GCS' different storage classes. Let's look at a real-world example: the…
GCP Tips & Tricks: The Networking That Supports GCS As A Global Storage Fabric For GCE
The modern public cloud makes it possible to create truly astonishingly scalable and high-performance global distributed computing architectures. Rather than…
GCP Tips & Tricks: The Surprisingly Cost-Effective Economics Of GCS Storage Classes For Backups
Most new users of Google's Cloud Storage (GCS) likely focus on its "Standard" offering: a high performance massively scalable global…
Our Journey Towards User-Facing Vector Search: Evaluating Elasticsearch's ANN Vector Search RAM Costs
As we continue our journey towards offering realtime user-facing semantic search over our growing collection of embedding datasets, we are…
Generative AI Experiments: LLM Knowledge Freshness & GSUTIL vs GCLOUD – The Dangers Of LLMs For Fast-Moving Fields
As LLMs are increasingly positioned as "coding copilots" for developers, we've been exploring their potential utility to help with the…
Generative AI Experiments: The Limits Of Advanced GenAI Coding Copilots For Writing Complex Code Like Networking
As we continue our evaluations of advanced LLM-driven generative AI coding copilots, we've found them to be useful for generating…
GCP Tips & Tricks: Observations On A Decade Of Running Elasticsearch On GCP: Part 3 – Future Storage Options
We've run Elasticsearch clusters on GCP for almost a decade across many different iterations of hardware and cluster configurations. Earlier…