Join us

ContentUpdates and recent posts about GPT-5.3-Codex..
Link
@kaptain shared a link, 2 weeks, 4 days ago
FAUN.dev()

v1.36: Declarative Validation Graduates to GA

Declarative validation graduated toGAin Kubernetesv1.36, replacing handwritten Go validation with+k8s:marker tags on field definitions... read more  

Link
@kaptain shared a link, 2 weeks, 4 days ago
FAUN.dev()

v1.36: Server-Side Sharded List and Watch

Alpha inv1.36, server-side sharded list and watch adds ashardSelectorfield toListOptionsso the API server uses an FNV-1a hash onmetadata.uidormetadata.namespaceto send each controller replica only its slice of the resource collection. This eliminates the cost of every replica deserializing the full .. read more  

Link
@kala shared a link, 2 weeks, 4 days ago
FAUN.dev()

Orchestrating AI Code Review at scale

Cloudflare engineers built an AI code review platform on OpenCode. They split GitLab integration, model providers, prompts, and policy into separate plugins. A coordinator assigns up to seven domain reviewers across security, performance, code quality, documentation, release checks, and AGENTS.md co.. read more  

Orchestrating AI Code Review at scale
Link
@kala shared a link, 2 weeks, 4 days ago
FAUN.dev()

How We Built an AI Second Brain for 60K Knowledge Workers

Meta built an AI agent system internally called the AI Second Brain that now has over 63,000 installs and ~10,000 daily active users across engineering, PM, design, legal, finance, comms, and sales, growing from zero in roughly three months after a non-technical PM's adoption post. The architecture .. read more  

How We Built an AI Second Brain for 60K Knowledge Workers
Link
@kala shared a link, 2 weeks, 4 days ago
FAUN.dev()

Running local models on an M4 with 24GB memory

Local LLMs work best as supervised coding assistants. The writer ran Qwen 3.5 9B (Q4) in LM Studio on a 24GB MacBook Pro and got about 40 tokens per second, with thinking mode, tool use, and a 128K context window. The author saw mixed results: Qwen helped with simple Elixir linter edits, then failed.. read more  

Running local models on an M4 with 24GB memory
Link
@kala shared a link, 2 weeks, 4 days ago
FAUN.dev()

The AWS MCP Server is now generally available

AWS now offers AWS MCP Server as a managed remote MCP server in US East (N. Virginia) and Europe (Frankfurt). MCP-compatible clients can use existing IAM credentials to access more than 15,000 AWS API operations. For GA, AWS added IAM context keys, documentation retrieval without authentication, low.. read more  

The AWS MCP Server is now generally available
Link
@kala shared a link, 2 weeks, 4 days ago
FAUN.dev()

Democratizing Machine Learning at Netflix: Building the Model Lifecycle Graph

Netflix's Saish Sali, Nipun Kumar, and Sura Elamurugu describe the Metadata Service (MDS), a graph layer built to connect siloed ML tooling (model registry, pipeline orchestrator, experimentation platform, feature store, dataset platform, identity) across personalization, studio, payments, and ads. .. read more  

Link
@devopslinks shared a link, 2 weeks, 4 days ago
FAUN.dev()

Why Queues Don’t Fix Scaling Problems

Queues do not create capacity, they delay the moment insufficient capacity becomes visible, and sustained overload turns a queue from a smoothing buffer into a cascading failure that takes down databases, connection pools, and consumer instances before it ever hits the queue's own limits... read more  

Link
@devopslinks shared a link, 2 weeks, 4 days ago
FAUN.dev()

Incidents *Will* Happen. Are You (Actually) Prepared?

Joe Mckevitt, CTO of Uptime Labs, argues that incident prevention and incident preparation are not substitutes, and that organizations relying on the heroic engineer who knows the infrastructure at 2amhave a habit, not a strategy. The piece pushes for a deliberate playbook (practiced communication, .. read more  

Link
@devopslinks shared a link, 2 weeks, 4 days ago
FAUN.dev()

S3 Files and the changing face of S3

AWS launchedS3 Files, an EFS-backed feature that mounts any S3 bucket or prefix as an NFS filesystem on EC2, containers, or Lambda, with changes batched back to S3 roughly every 60 seconds. Rather than collapsing file and object semantics into a single model (an early design attempt called "EFS3" th.. read more  

S3 Files and the changing face of S3
GPT-5.3-Codex is OpenAI’s advanced agentic coding model, designed to go beyond writing code and operate as a general-purpose collaborator on a computer. It builds on GPT-5.2-Codex by combining stronger coding performance with improved reasoning and professional knowledge, while running about 25% faster. The model is optimized for long-running tasks that involve research, tool use, and complex execution, and it performs at the top of industry benchmarks such as SWE-Bench Pro and Terminal-Bench.

Unlike earlier Codex models that focused primarily on code generation and review, GPT-5.3-Codex can reason, plan, and act across the full software lifecycle. It supports activities such as debugging, deploying, monitoring, writing product requirement documents, creating tests, and analyzing metrics. It can also autonomously build and iterate on complex applications and better interpret underspecified prompts, producing more complete and production-ready results by default.

A defining feature of GPT-5.3-Codex is its interactive, agentic workflow. Users can steer the model while it is working, receive progress updates, and adjust direction without losing context, making it feel more like a teammate than a batch automation tool. The model was even used internally to help debug its own training and deployment processes. GPT-5.3-Codex is available through paid ChatGPT plans in the Codex app, CLI, IDE extension, and web, with API access planned for the future.