New8 min read
Claude Tag API: Manage Claude in Slack Channels From Code
The Claude Tag API beta lets Enterprise admins turn Claude on per Slack channel, set instructions, models and guest policy, and attach Access bundles from code.
Page 2 of 100
Read
Deep dives into AI agents, coding tools, and building with LLMs.
1189 articles844 topics
New7 min read
CleanYourTV: Debloat Your TV With Claude Code, Safely
CleanYourTV is a prompt plus scripts that has Claude Code strip ads and telemetry from an Android TV over Wi-Fi. What it does, where it breaks, and a safe-run checklist.
Read more
New7 min read
GVS5H: Can Qwen3.8-27B Match Fable 5 on Coding?
GVS5H claims five Qwen3.8-27B instances match Fable 5 on LiveCodeBench Hard. What the harness does, why Hacker News doubts the benchmark, and what to copy.
Read more
New7 min read
Flint on Ollama: Best Local Coding LLM for Claude Code?
Recursive's Flint is a 40B open-weight coding model with 2.5B active parameters. How to run it on Ollama and point Claude Code at it, plus the benchmark caveats.
Read more
New8 min read
Claude Code MCP Tasks: Long-Running Tools That Ask You Things
Claude Code now supports MCP Tasks and elicitations. What the docs say a tool call needs to become a task, where it does not work, and what a server author changes.
Read more
New7 min read
Claude Code Monitor Tool: Now on Bedrock, Vertex and Foundry
Claude Code 2.1.310 brings the Monitor tool and plugin monitors to Bedrock, Vertex and Foundry. How Monitor works, its limits and 30-minute cap, and the setup.
Read more
New6 min read
Claude vs Claude Code: What the Difference Is and Which to Use (2026)
Claude vs Claude Code: one app for chat, docs and general work, one agent for your codebase. Same model family and shared plan limits, different jobs.
Read more
New8 min read
Google Agent Compute Engine: A MicroVM Per Agent, Explained
Google Agent Compute Engine gives every agent its own microVM with no credentials inside. What Google says it does, what is still unpublished, and what a builder can copy today.
New8 min read
AI Formal Verification: Claude Proved 123 Libraries Crash-Free
Anthropic used Claude to prove no-crash properties for 123 OSS-Fuzz libraries. What the proofs cover, where they stop, and the fuzz-target habits worth copying on Monday.
Read more
New8 min read
Claude Security Continuous Scanning: Fix Tracking, API and MCP
Claude Security now rescans repos as commits land, marks findings fixed when the fix ships, and adds an API, MCP connector and webhooks. Setup, limits and cost.
New7 min read
Codex CLI 0.164: /presets and Inline /model Flags
Codex CLI 0.164.0 adds ten /presets slots, inline /model and /permissions arguments, and credential masking for remote commands. What to try and what to check.
Read more
New8 min read
Codex Reset: Banked vs Automatic vs Paid, and When to Use Each
Codex has three kinds of usage reset - banked, automatic and paid - and they move your weekly refresh date in different ways. What OpenAI documents, the 80% rule, and what to do Monday.
Showing 13-24 of 1189 articles
Get new articles in your inbox
Deep dives on AI agents, coding tools, and building with LLMs - delivered weekly. No spam.
Free forever. Unsubscribe anytime.
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever