Join us

ContentUpdates and recent posts about GPT-5.4..
Link
@kala shared a link, 4 months ago
FAUN.dev()

1,500+ PRs Later: Spotify’s Journey with Our Background Coding Agent

Spotify just gave its internal Fleet Management tooling a serious brain upgrade. They've wired inAI coding agentsthat now handle source-to-source transformations across repos - automatically. So far? Over 1,500 AI-generated PRs pushed. Not just lint fixes - these include heavy-duty migrations. They'.. read more  

1,500+ PRs Later: Spotify’s Journey with Our Background Coding Agent
Link
@kala shared a link, 4 months ago
FAUN.dev()

Writing a good CLAUDE.md

Anthropic’s Claude Code now deprioritizes parts of the root context file it sees as irrelevant. It still reads the file every session, but won’t waste cycles on side quests. The message to devs: stop stuffing it with catch-all instructions. Instead, use modular context that unfolds as needed - think.. read more  

Writing a good CLAUDE.md
Link
@devopslinks shared a link, 4 months ago
FAUN.dev()

How when AWS was down, we were not

During the AWS us-east-1 meltdown - when DynamoDB, IAM, and other key services went dark - Authress kept the lights on. Their trick? A ruthless edge-first, multi-region setup built for failure. They didn’t hope DNS would save them. They wired in automated failover, rolled their own health checks, an.. read more  

How when AWS was down, we were not
Link
@devopslinks shared a link, 4 months ago
FAUN.dev()

Collaborating with Terraform: How Teams Can Work Together Without Breaking Things

When working with Terraform in a team environment, common issues may arise such as state locking, version mismatches, untracked local applies, and lack of transparency. Atlantis is an open-source tool that can help streamline collaboration by automatically running Terraform commands based on GitHub .. read more  

Link
@devopslinks shared a link, 4 months ago
FAUN.dev()

Self Hostable Multi-Location Uptime Monitoring

Vigilant runs distributed uptime checks with self-registeringGo-based "outposts"scattered across the globe. Each one handles HTTP and Ping, reports back latency by region, and calls home over HTTPS. The magic handshake? Vigilant plays root CA, handing outephemeral TLS certson the fly... read more  

Self Hostable Multi-Location Uptime Monitoring
Link
@devopslinks shared a link, 4 months ago
FAUN.dev()

Test Automation Structure for Single Code Base Projects

The authors discuss the development of a new automation infrastructure post-merger, leading to a unified automation project that can handle all cultures, languages, and clients efficiently. They chose Playwright over Cypress for its improved resource usage and faster execution times, aligning better.. read more  

Link
@devopslinks shared a link, 4 months ago
FAUN.dev()

How Netflix optimized its petabyte-scale logging system with

Netflix overhauled its logging pipeline to chew through5 PB/day. The stack now leans onClickHousefor speed andApache Icebergto keep storage costs sane. Out went regex fingerprinting - slow and clumsy. In came aJFlex-generated lexerthat actually keeps up. They also ditched generic serialization in fa.. read more  

How Netflix optimized its petabyte-scale logging system with
Link
@devopslinks shared a link, 4 months ago
FAUN.dev()

The AI Gold Rush Is Forcing Us to Relearn a Decade of DevOps Lessons

Sauce Labs just dropped a reality check:95% of orgshave fumbled AI projects. The kicker?82% don’t have the QA talent or toolsto keep things from breaking. Even worse,61% of leaders don’t get software testing 101, leaving AI pipelines full of holes - cultural, procedural, and otherwise. System shift:.. read more  

Link
@devopslinks shared a link, 4 months ago
FAUN.dev()

The $1,000 AWS mistake

A missingVPC Gateway Endpointsent EC2-to-S3 traffic through aNAT Gateway, lighting up over$1,000in unnecessary data processing charges. All that for in-region traffic hitting an AWS service. Why? AWS defaulted the route to the NAT Gateway. It only takes the free S3 Gateway Endpoint if youtellit to. .. read more  

The $1,000 AWS mistake
Link
@devopslinks shared a link, 4 months ago
FAUN.dev()

A Love Letter to FreeBSD

A Linux user takes FreeBSD for a spin - and comes away impressed. What stands out? Clean, deliberate engineering.Boot environmentsmake updates stress-free. The newpkgbasesystem adds modularity without chaos. And the OS treatsuptimenot just as a metric, but as a design goal. The essay makes a solid c.. read more  

GPT-5.4 is OpenAI’s latest frontier AI model designed to perform complex professional and technical work more reliably. It combines advances in reasoning, coding, tool use, and long-context understanding into a single system capable of handling multi-step workflows across software environments. The model builds on earlier GPT-5 releases while integrating the strong coding capabilities previously introduced with GPT-5.3-Codex.

One of the defining features of GPT-5.4 is its ability to operate as part of agent-style workflows. The model can interact with tools, APIs, and external systems to complete tasks that extend beyond simple text generation. It also introduces native computer-use capabilities, allowing AI agents to operate applications using keyboard and mouse commands, screenshots, and browser automation frameworks such as Playwright.

GPT-5.4 supports context windows of up to one million tokens, enabling it to process and reason over very large documents, long conversations, or complex project contexts. This makes it suitable for tasks such as analyzing codebases, generating technical documentation, working with large spreadsheets, or coordinating long-running workflows. The model also introduces a feature called tool search, which allows it to dynamically retrieve tool definitions only when needed. This reduces token usage and makes it more efficient to work with large ecosystems of tools, including environments with dozens of APIs or MCP servers.

In addition to improved reasoning and automation capabilities, GPT-5.4 focuses on real-world productivity tasks. It performs better at generating and editing spreadsheets, presentations, and documents, and it is designed to maintain stronger context across longer reasoning processes. The model also improves factual accuracy and reduces hallucinations compared with previous versions.

GPT-5.4 is available across OpenAI’s ecosystem, including ChatGPT, the OpenAI API, and Codex. A higher-performance variant, GPT-5.4 Pro, is also available for users and developers who require maximum performance for complex tasks such as advanced research, large-scale automation, and demanding engineering workflows. Together, these capabilities position GPT-5.4 as a model aimed not just at conversation, but at executing real work across software systems.