Updates and recent posts about GPT-5.4..

Posts
Description

Link

@kala shared a link, 1 week, 3 days ago

FAUN.dev()

Realtime Prompting Guide

OpenAI shipsgpt-realtimeand declares GA for theRealtime API. It's a speech-to-speech model that tightens instruction-following, steadiestool calling, and lifts voice fidelity. Latency drops. True realtime agents become possible. The release prescribesprompt skeletons,JSON envelopetool outputs,sessio.. read more

Link

@kala shared a link, 1 week, 3 days ago

FAUN.dev()

The Pentagon is making a mistake by threatening Anthropic

Anthropic's Claude Gov, optimized for national security uses, has fewer restrictions than regular versions. The Pentagon is threatening retaliation if Anthropic does not waive these restrictions by Friday, including invoking the Defense Production Act or declaring Anthropic a supply chain risk. Anth.. read more

Link

@kala shared a link, 1 week, 3 days ago

FAUN.dev()

Introducing helm

helm usesTypeScripttypes to registerskillsas typed functions with structured I/O. Permissions follow a clear precedence: exact→wildcard→skill→global. Agents get a keywordsearchtool and a code-execution tool that runs JS inside anSESsandbox. A recursiveproxyforwards calls overIPCto the parent, which .. read more

Link

@kala shared a link, 1 week, 3 days ago

FAUN.dev()

Do you need an MCP to build your native app?

Do you need an MCP to build your native app? Surprisingly, modern agents succeed either way. The real difference is how much time, cost, and context you waste along the way... read more

Link

@kaptain shared a link, 1 week, 3 days ago

FAUN.dev()

I Built a Production-Grade Kubernetes Platform in 48 Hours.

A dev built a production-grade Kubernetes platform in 48 hours, encountering challenges and solutions along the way. The setup included multiple layers such as infrastructure, cluster, platform, delivery, and observability, each requiring troubleshooting and adjustments. The process involved deployi.. read more

Link

@kaptain shared a link, 1 week, 3 days ago

FAUN.dev()

Spotlight on SIG Architecture: API Governance

Kubernetes SIG Architecture’s API Governance crew is tightening the screws on stability, consistency, and cross-cutting sanity across the whole API surface. Not just REST. They’re eyeing the overlooked stuff too - CLI flags, config formats, anything that shapes how users and tools touch the system. .. read more

Link

@kaptain shared a link, 1 week, 3 days ago

FAUN.dev()

From Chaos to Clarity: How We Built a Self-Healing CI/CD Pipeline That Talks to JIRA

Transitioning JIRA tickets to trigger deployments was key for this team struggling with manual deploys, leading to significant savings in time and reduction in errors. The architecture involved a JIRA Controller Pipeline, a Project Deployment Pipeline, and a JIRA Manager Pipeline, all aimed at seaml.. read more

Link

@kaptain shared a link, 1 week, 3 days ago

FAUN.dev()

Before You Migrate: Five Surprising Ingress-NGINX Behaviors You Need to Know

The K8s blog exposesIngress-NGINXdefaults that clash withGateway API. These include case-insensitive prefix regexes. Host-wide annotation effects. Path rewrites. Slash redirects. URL normalization. Kubernetes retiresIngress-NGINXinMarch 2026.Gateway API 1.5graduatesListenerSetand theHTTPRoute CORS.. read more

Link

@devopslinks shared a link, 1 week, 3 days ago

FAUN.dev()

Rendering 100M pixels a second over ssh

A massively multiplayer snake game accessible over ssh, capable of handling thousands of concurrent players and rendering over a hundred million pixels a second. The game utilizes bubbletea for rendering frames and custom techniques to reduce bandwidth usage to around 2.5 KB/sec. Performance improve.. read more

Link

@devopslinks shared a link, 1 week, 3 days ago

FAUN.dev()

LLMs Are Good at SQL. We Gave Ours Terabytes of CI Logs.

Mendral's agent runs ad‑hocSQLagainst compressedClickHouselogs. It traces flaky tests across months and scans up to 4.3B rows per investigation. They denormalize 48 metadata columns per log line. They compress 5.31 TiB down to ~154 GiB (~21 bytes/line) — a 35:1 ratio. That turns arbitrary filters in.. 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.