ContentPosts from @kala..
Link
@kala shared a link, 1 week, 4 days ago
FAUN.dev()

Claude’s next enterprise battle is not models: it’s the agent control plane

New data shows Microsoft and OpenAI leading agent orchestration, but Anthropic's rising stake signals a shift in control of AI infrastructure. Anthropic's move from model to orchestration layer hints at a strategic battle over agent runtime platforms where operational AI work happens... read more  

Link
@kala shared a link, 1 week, 4 days ago
FAUN.dev()

AI Is Doing the Testing Now

Brijesh Deb's third "comfortable lie" of software testing is that AI is now doing the testing: coverage dashboards hit 80%+, regression suites maintain themselves, and leadership concludes that risk is handled, while the experienced testers who knew the domain quietly get redeployed or made redundan.. read more  

Link
@kala shared a link, 1 week, 4 days ago
FAUN.dev()

How Code works in large codebases: Best practices and where to start

Anthropic breaks down the patterns behind successful Claude Code rollouts in monorepos, legacy systems, and codebases spanning thousands of developers, arguing that Claude Code performs agentic search over a live filesystem instead of relying on a RAG index that drifts out of sync with active engine.. read more  

How Code works in large codebases: Best practices and where to start
Link
@kala shared a link, 1 week, 4 days ago
FAUN.dev()

Tokenomics: the 62.5-minute rule for Claude's cache

Ryan Skidmore works out the tokenomics of Anthropic's prompt cache and lands on a single rule: if you expect to need a cached prefix again within 62.5 minutes, keep refreshing it with cheap reads; past that, let it expire and rewrite, because a 5-minute cache write costs 1.25x base input and a read .. read more  

Tokenomics: the 62.5-minute rule for Claude's cache
Link
@kala shared a link, 1 week, 4 days ago
FAUN.dev()

Create Custom MCP Catalogs and Profiles

Docker made Custom Catalogs and Profiles available for MCP servers. Admins can distribute server catalogs they approve, and teams can package per-developer configurations as OCI artifacts... read more  

Create Custom MCP Catalogs and Profiles
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()

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
@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