Author: Kalev Leetaru
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…
GCP Tips & Tricks: Observations On A Decade Of Running Elasticsearch On GCP: Part 2
We've run Elasticsearch clusters on GCP for almost a decade across many different iterations of hardware and cluster configurations. Yesterday…
GCP Tips & Tricks: Observations On A Decade Of Running Elasticsearch On GCP: Part 1
We've run Elasticsearch clusters on GCP for almost a decade across many different iterations of hardware and cluster configurations. What…
GCP Tips & Tricks: Comparing Extreme Persistent Disks & Hyperdisks To Many Small Disks For Search
One of the most critical questions in supporting IO-centric workloads is determining the right mix of storage devices. For some…
Generative AI Experiments: The Challenges Of Generative Search For Technical Questions & The Limits Of RAG
Generative search in the form of Retrieval Augmented Generation (RAG) has been widely hyped as the future of search, with…
IRINN: Coverage Of Soraya Satellite Launch
Iranian broadcaster IRINN devoted considerable coverage to the successful launch of its Soraya satellite and Iran's space ambitions, offering a…
Generative AI Experiments: What Machine Types Support What Disk Types On GCE?
Google's Compute Engine platform supports an ever-growing and more complex matrix of machine types and block storage options, including newer…
GCP Tips & Tricks: The Compute Engine Metadata Server
The GCP Compute Engine (GCE) metadata server is an extremely powerful and often underappreciated resource. Yesterday we examined how it…
Simple Experiments In GCP Performance: Getting Bearer Tokens The Fast Way On GCE
While nearly all GCP APIs offer library interfaces for many major programming languages like Python, there are many use cases…
Simple Experiments In GCS LS Performance: Comparing GCloud, Python & The GCS JSON API
There are three primary ways to access files in GCS: using the native GCLOUD CLI (replaces GSUTIL), using the GCS…
How Is Gaza Being Covered On Television News?
Hamas’ terrorist attack and hostage-taking in Israel on Oct. 7 led in return to large-scale Israeli military action throughout Gaza….
Simple Experiments In Scalable Queuing: Quickly Getting Started With GCP's Pub/Sub
For those interested in the scalable global queuing system that is GCP's Pub/Sub, but not sure where to start, here's…
Generative AI Experiments: Why LLM-Based Geocoders Struggle
Over the past two days we've explored how advanced LLMs like GPT 4.0 struggle significantly with both candidate extraction and…
Generative AI Experiments: The Surprisingly Poor Performance Of LLM-Based Geocoders, Geographic Bias & Why GPT 3.5 & Gemini Pro Outperform GPT 4.0 In Underrepresented Geographies
Last year we explored the potential of LLMs to be used as general purpose entity extraction models, finding that LLMs…
Generative AI Experiments: The Inability Of Advanced LLMs Like GPT-4 To Reason Spatially
One of the most important tasks that fulltext geocoders perform is disambiguation: taking a placename and determining, out of all…
Generative AI Coverage Steady In Business Press But Fall In Search Interest
Television news coverage of "generative AI" and "large language models" surged on business channels in April 2023, then entered a…