Best practices guide for customizing Gemini models via Reinforcement Learning (RL)
Reinforcement learning (RL) has been a keystone of modern LLM post-training, but it demands large training clusters and access to model internals that external customers can't have with proprietary models like Gemini. So here at Google Cloud, we packaged it into a managed RL fine-tuning service (RLFT service) — you bring prompts and a reward function; we handle the infrastructure and the…
Read the full story on Google Cloud BlogHave you worked with this?
The story is what was announced. Nobody has discussed it yet, so if it touches your team, a short post about what you’ve seen helps the next reader.
More from Google Cloud
Recent updates from Google Cloud, so you can tell whether this is a one-off or part of a pattern.
Unlock 3x QPS and microsecond latency with Memorystore for Valkey 9.1
At Google Cloud, we are committed to delivering the best managed experience backed by open source software. Today, we’re announcing the general availability of Memorystore for Valkey 9.1 , which achieves up to 3x queries per second (QPS) at microsecond latency compared to Memorystore for Redis Cluster. Our support for Valkey dates back to 2024 , when Redis Inc. shifted its licensing away from the…
Storage Intelligence advisor: Know what changed in your storage estate and act on it
The volume of data being generated today brings both opportunity and massive operational complexity. Most teams that operate at scale don't discover issues until they appear on an invoice — and by the time an unusual access pattern shows up as a line item, it has often been running for weeks. Understanding what happened means exporting inventory, joining it against access logs, and hoping someone…
What’s new with Google Cloud
Want to know the latest from Google Cloud? Find it here in one handy location. Check back regularly for our newest updates, announcements, resources, events, learning opportunities, and more. Tip : Not sure where to find what you’re looking for on the Google Cloud blog? Start here: Google Cloud blog 101: Full list of topics, links, and resources . aside_block <ListValue: []> Sept 21 - Sept 25…
More in Containers & Kubernetes
What other companies in Containers & Kubernetes are doing. The category page shows who’s active, side by side.
Bringing enterprise Linux to the robotics frontier: ROS2 adds Red Hat Enterprise Linux as a tier-1 supported platform
The convergence of enterprise IT and physical computing is accelerating. As artificial intelligence transitions from purely digital environments into autonomous systems, industrial automation, and smart edge devices, the software foundation behind these systems must be as resilient as the physical machines themselves.To power this next generation of intelligent systems, we’re pleased that Red Hat…
Breaking the AI productivity paradox: an intelligent migration factory to modernize infrastructure and applications
The rise of generative AI promised a silver bullet, but for most enterprises, especially banks, digital transformation remains a slow, complex, and costly endeavor. Early reports suggested massive developer productivity gains. But when AI is applied to complex enterprise systems, organizations often collide with what we call the AI productivity paradox.According to a Stanford software engineering…
AI Reliability Engineering for Dependable Humans | Solo.io
Learn AI reliability engineering (AIRE): how AI agents help SRE and platform teams triage incidents faster and stay dependable.
ShinyHunters Renewed Mass Exploitation Campaign Targeting Oracle PeopleSoft
Introduction As an update to the June 2026 post, ShinyHunters Targets Education Sector with Oracle PeopleSoft Exploit , Mandiant and Google Threat Intelligence Group (GTIG) have identified renewed mass exploitation of CVE-2026-35273 by UNC6240 (ShinyHunters), along with expanded global targeting across multiple sectors. In June, the threat actor exploited this vulnerability as a zero-day…