ContentPosts from @oz4you..
Link
@faun shared a link, 2 weeks, 4 days ago

LLM Evaluation: Practical Tips at Booking.com

Booking.com built Judge-LLM, a framework where strong LLMs evaluate other models against a carefully curated golden dataset. Clear metric definitions, rigorous annotation, and iterative prompt engineering make evaluations more scalable and consistent than relying solely on humans. **The takeaway**:..

Link
@faun shared a link, 2 weeks, 4 days ago

The LinkedIn Generative AI Application Tech Stack: Extending to Build AI Agents

LinkedIn tore down its GenAI stack and rebuilt it for scale—with agents, not monoliths. The new setup leans on distributed, gRPC-powered systems. Central skill registry? Check. Message-driven orchestration? Yep. It’s all about pluggable parts that play nice together. They added sync and async modes..

The LinkedIn Generative AI Application Tech Stack: Extending to Build AI Agents
Link
@faun shared a link, 2 weeks, 4 days ago

Vibe coding has turned senior devs into ‘AI babysitters,’ but they say it’s worth it

Fastly says95% of developersspend extra time fixing AI-written code. Senior engineers take the brunt. That overhead has even spawned a new gig: “vibe code cleanup specialist.” (Yes, seriously.) As teams lean harder on AI tools, reliability and security start to slide—unless someone steps in. The re..

Vibe coding has turned senior devs into ‘AI babysitters,’ but they say it’s worth it
Link
@faun shared a link, 2 weeks, 4 days ago

GitHub Copilot on autopilot as community complaints persist

GitHub's biggest debates right now? Whether to shut down AI-generated "noise" fromCopilot—stuff like auto-written issues and code reviews. No clear answers from GitHub yet. Frustration is piling up. Some devs are ditching the platform altogether, shifting their projects toCodebergor spinning upself-..

GitHub Copilot on autopilot as community complaints persist
Link
@faun shared a link, 2 weeks, 4 days ago

Understanding LLMs: Insights from Mechanistic Interpretability

LLMs generate text by predicting the next word using attention to capture context and MLP layers to store learned patterns. Mechanistic interpretability shows these models build circuits of attention and features, and tools like sparse autoencoders and attribution graphs help unpack superposition, r..

Link
@faun shared a link, 2 weeks, 4 days ago

Accelerate serverless testing with LocalStack integration in VS Code IDE

The AWS Toolkit for VS Code now hooks straight into **LocalStack**. Run full end-to-end tests for **serverless workflows**—Lambda, SQS, EventBridge, the whole crew—without bouncing between tools or writing boilerplate. Just deploy to LocalStack from the IDE using the **AWS SAM CLI**. It feels like ..

Accelerate serverless testing with LocalStack integration in VS Code IDE
Link
@faun shared a link, 2 weeks, 4 days ago

Magical systems thinking

AI now writes over **25% of Google’s** and as much as **90% of Anthropic’s** code. That’s not a trend—it’s a regime change. Still, the mess in large public systems reminds us: clever analysis isn’t enough. Complex systems don’t behave; they misbehave. When the machines are churning out code, the ..

Magical systems thinking
Link
@faun shared a link, 2 weeks, 4 days ago

Writing an operating system kernel from scratch

A barebonestime-sharing OS kernel, written inZig, running onRISC-V. It leans onOpenSBIfor console I/O and timer interrupts. Threads? Statically allocated, each running inuser mode (U-mode). The kernel stays insupervisor mode (S-mode), where it catchessystem callsandcontext switchesvia timer ticks. ..

Writing an operating system kernel from scratch
Link
@faun shared a link, 2 weeks, 4 days ago

Scaling Prometheus: Managing 80M Metrics Smoothly

Flipkart ditched its creakyStatsD + InfluxDBstack for afederated Prometheussetup—built to handle 80M+ time-series metrics without choking. The move leaned intopull-based collection,PromQL's firepower, andhierarchical federationfor smarter aggregation and long-haul queries. Why it matters:Prometheus..

Scaling Prometheus: Managing 80M Metrics Smoothly
Link
@faun shared a link, 2 weeks, 4 days ago

PostgreSQL maintenance without superuser

PostgreSQL’s moving in on superusers. As of recent releases—starting way back in v9.6 and maturing through PostgreSQL 18 (coming 2025)—there are now **15+ built-in admin roles**. No need to hand out superuser just to get things done. These roles cover the ops spectrum: monitoring, backups, fil..

PostgreSQL maintenance without superuser