Total Articles: 17 from 7 sources
AWS News
1. AWS Weekly Roundup: Price reduction of GPT models in Bedrock, CloudWatch managed collectors for Prometheus metrics, and more (August 3, 2026)
Published: 2026-08-03 16:12
Summary:
Last week I had the joy of participating in Amazon’s “Bring Your Kids to Work Day” with my 7 year old son We commuted together into the New York City office, his first real rush hour train ride, and spent the day exploring how Amazon uses AI, machine learning, and robotics to deliver packages to […]
2. AWS Weekly Roundup: Local Zone in Athens, Claude Opus 5 on AWS, Lambda durable execution for .NET, and more (July 27, 2026)
URL: https://aws.amazon.com/blogs/aws/aws-weekly-roundup-july-27-2026/
Published: 2026-07-27 14:54
Summary:
Last week I had the privilege of spending three days in São Paulo with technical builders from across Latin America, brought together for a regional tech event full of deep-dive sessions, hands-on workshops, and conversations with customers and partners What struck me most wasn’t any single session, it was the energy of a technical community […]
3. AWS Weekly Roundup: One-click Lambda setup prompt, OpenAI GPT-5.6 models on Bedrock, and more (July 20, 2026)
Published: 2026-07-20 16:37
Summary:
Last week, my team visited Seoul to meet AWS Korea User Group (AWSKRUG) leaders AWSKRUG is the largest cloud developer community in Korea, with 20 meetup groups organized by topic and area that collectively host over 100 events each year, primarily in Seoul My team regularly visits countries across the Asia-Pacific region, listens to feedback […]
Dropbox Engineering
1. How our universal content processing platform Riviera evolved for AI and beyond
Published: 2026-07-20 15:00
Summary:
Riviera is the Dropbox content processing platform that’s been iteratively improving content transformation in our products for roughly a decade.
GitHub Blog
1. Don’t stop early: Case-folding source code at memory speed
Published: 2026-07-31 16:00
Summary:
How a branch-free loop and byte-space arithmetic let GitHub case-fold every byte of code search at >45 GiB/s on a single core The post Don’t stop early: Case-folding source code at memory speed appeared first on The GitHub Blog.
2. Stacked sessions and pull requests in the GitHub Copilot app
Published: 2026-07-30 17:30
Summary:
Learn how I modernized an old codebase of mine using stacked sessions and pull requests in the GitHub Copilot app The post Stacked sessions and pull requests in the GitHub Copilot app appeared first on The GitHub Blog.
3. Tame Dependabot: Group your updates, slow the cadence, keep security fast
Published: 2026-07-29 16:00
Summary:
Dependabot keeps your dependencies current, but its defaults can flood your repository with pull requests Here’s how grouping updates, slowing the cadence, and keeping security fixes fast cut the noise on a Microsoft open source project The post Tame Dependabot: Group your updates, slow the cadence, keep security fast appeared first on The GitHub Blog.
Google Developers
1. Measuring What Matters with Jules
URL: https://developers.googleblog.com/measuring-what-matters-with-jules/
Published: 2026-08-04 11:21
Summary:
AI coding agents are rapidly shifting from reactive assistants that complete tasks when prompted to …
2. Build reliable multi-agent applications with ADK Go 2.0. Discover our new graph-based workflow engine, built-in human-in-the-loop, and dynamic orchestration
URL: https://developers.googleblog.com/announcing-adk-go-20/
Published: 2026-08-04 11:21
Summary:
The Agent Development Kit (ADK) for Go 2.0 has been released, introducing a first-class, graph-based workflow engine to help developers compose complex, multi-agent applications This update adds built-in primitives for human-in-the-loop (HITL) orchestration, dynamic execution using plain Go code, and automated resilience features like exponential backoff retries By unifying the execution model, both single-agent applications and intricate graphs now run on the same runtime, simplifying telemetry and state persistence.
3. Driving the Agent Quality Flywheel from Your Coding Agent
URL: https://developers.googleblog.com/driving-the-agent-quality-flywheel-from-your-coding-agent/
Published: 2026-08-04 11:21
Summary:
Building AI agents often leaves developers uncertain if prompt tweaks to fix single errors will accidentally cause widespread regressions in production To bridge this gap, Google has introduced a new developer skill for coding agents that automates a five-stage evaluation flywheel: preparing data, running inference, grading with adaptive AutoRaters, analyzing failure clusters, and executing targeted optimizations Running continuously against production traffic or on-demand via synthetic scenarios, this tool allows developers to describe testing goals in plain language while an independent evaluation service safely validates and counts actual performance improvements.
Meta Engineering
1. GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model
Published: 2026-08-03 18:00
Summary:
Meta’s Generative Ads Recommendation Model (GEM), the foundation model behind ads recommendations across Instagram and Facebook, now trains at LLM scale on several thousand of the latest-generation GPUs This post goes into the details on how we achieved: doubling end-to-end (E2E) training efficiency to 20–25% Model FLOPs Utilization (MFU) while scaling training FLOPs 4x in […] Read More The post GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model appeared first on Engineering at Meta.
2. Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
Published: 2026-07-15 17:00
Summary:
Hierarchical Interest Representation is a research area for Meta Ads The innovations in Hierarchical Interest Representation are […] Read More The post Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization appeared first on Engineering at Meta.
3. Modernizing the Meta Ads Service With an Open-Source Kernel Scheduler
Published: 2026-07-13 16:00
Summary:
TL; DR At Meta’s scale, a few milliseconds of latency degradation can have a significant negative impact on ads performance When a Linux kernel upgrade risked regressing latency across Meta’s ad serving fleet, we turned to sched_ext — the upstream, BPF-based extensible scheduling framework — to build a scheduling policy customized to the Ads delivery […] Read More The post Modernizing the Meta Ads Service With an Open-Source Kernel Scheduler appeared first on Engineering at Meta.
Netflix TechBlog
1. Modeling Device Capabilities for Analytics
Published: 2026-07-31 16:01
Summary:
To ensure the best possible user experience, we rely on a deep understanding of device capabilities We use a cumulative table to process information about the device’s capabilities By relying on data-driven insights, we can make informed decisions about which features to enable on specific devices, ensuring both performance and reliability.Modeling Device Capabilities for Analytics was originally published in Netflix TechBlog on Medium, where people are continuing the conversation by highlighting and responding to this story.
2. GenRec: Towards LLM-Native Recommendation at Netflix
Published: 2026-07-30 20:10
Summary:
Raw logs of user history, item metadata, and context are transformed via context engineering into natural-language prompts and fed into the GenRec, which runs on vLLM in prefill-only mode and outputs scores for each catalog item, yielding a recommendation ranking.At a high level, GenRec:Verbalizes user histories, item metadata, and context as text.Post‑trains a Netflix‑adapted foundation LLM for ranking.Adds a catalog‑aware scoring head over Netflix titles.Uses reward signals to align with long‑term member value and business goals.Runs in prefill‑only mode on Netflix’s LLM serving stack for cost efficiency.In a large‑scale A/B test against a well‑tuned production ranker, GenRec achieves statistically significant improvements in both short‑term and long‑term online metrics, while using only a small fraction of the Phase‑2 labeled data and input signals As we increased Phase‑2 training data and enriched the input signals, GenRec’s offline metrics continued to improve.Online, we ran a large A/B test on batch‑compute recommendation surfaces, covering ~10% of Netflix traffic over ~4 weeks By verbalizing user histories, context, and item metadata, adding a catalog‑aware ranking head, using reward‑weighted objectives aligned to long‑term satisfaction and business goals, and serving efficiently on our LLM infrastructure, we obtain a model that improves on a strong production ranker while using far fewer Phase‑2 labels and input signals.GenRec is an early but promising step toward a more LLM‑centric recommendation stack at Netflix
3. In-House LLM Serving at Netflix
Published: 2026-07-17 21:32
Summary:
Serving Architecture OverviewDesign Decisions and ImplementationFour decisions shape this platform — engine, packaging, API surface, and rollout — presented in dependency order, since each one constrains the next.vLLM as the Paved-Path EngineThe platform was originally built on TensorRT-LLM, a performant inference engine at the time and already integrated with Triton — the compute backend in use within MSS.By summer 2025, two things had shifted: open-source engines had largely closed the performance gap with specialized stacks, and our workload mix had broadened to include embedding generation, prefill-only inference for ranking and retrieval, autoregressive decoding, and custom models with non-trivial per-step constraint logic The platform has to pin compatible versions when baking the service image, and prevent model authors from overriding the vLLM version at packaging time.Custom model logic We git-subtreed and patched the frontend to translate response_format into vLLM’s guided decoding parameters at request time.Deployment StrategiesWith API surface and engine in place, the question that remains is how new versions roll out without dropping requests
Stripe Engineering
1. Analyzing the evidence that helps businesses win “product not received” disputes
Published: 2026-07-21 00:00
Summary:
To understand what can influence win rates, we analyzed evidence packets from one million disputes over a 16-week period Here’s what the data shows and what it means for how you mitigate disputes.
Generated on 2026-08-04 11:21:08