Claude coverage.

How are you managing Claude project files that need frequent updates?

I've been using markdown files in Claude projects heavily for context and instructions, but updating them is more friction than I expected. No in-place editing, so it's delete and …

Claude can now build your entire weekly meal plan with real grocery prices from your actual store FOR FREE. Here's how

I saw this viral thread on X going around about using Claude as a dietitian. Tried all 12 prompts directly. Nutrition logic was genuinely impressive. macro calculations, meal timin…

Long Running Agents: How Outtake built a cyber investigator on Claude - Anthropic

Long Running Agents: How Outtake built a cyber investigator on Claude Anthropic…

Claude Code Tracker for Garmin

One command sets up a Claude AI workstation better than anything I've built manually

Holy*****, where has this been all year?…

Show HN: Async multi-person collaboration skill for Claude Code

Do the "*Claude-4.6-Opus-Reasoning-Distilled" really bring something new to the original models?

No offense to the fine-tune model providers, just curious. IMO the original models were already trained on massive amount of high quality data, so why bother with this fine-tune? J…

Claude-Powered Agent Apparently Deletes Company Database, Debases Itself Further in Confession

AI agents are powered by the same obsequious LLMs as consumer chatbots.…

I switched from Gemini to Claude and it’s a mixed bag

Claude isn't better or worse than Gemini. It's just different. Different enough that I can't switch fully, so I'll just use both.…

Claud is missing the 2. Sense – Transcribe the web

4 incidents, 4 règles : comment mon CLAUDE.md s'est écrit tout seul

Si tu as 30 secondes. Un CLAUDE.md efficace ne documente pas, il contraint — chaque règle répond à...…

4 incidents, 4 rules: how my CLAUDE.md wrote itself

If you have 30 seconds. An effective CLAUDE.md doesn't document, it constrains — each rule answers a...…

"Use Claude Code for FREE" is a Trap

Claude MCP Explained: Building Enterprise AI Integrations That Actually Scale

What the Model Context Protocol actually is, why it changes enterprise AI architecture and how to...…

What Claude Shannon Knew in 1950 That We're Pretending Is New

AI didn’t arrive yesterday; it just changed its outfit…

Claude Code IDE – A Local Web IDE Wrapping Claude Code's CLI

Contribute to Powellga/Claude-Code-IDE development by creating an account on GitHub.…

Tell HN: Claude flags questions about biology / biotech

Apple integrates Claude and Codex into Xcode 26.3 for 'agentic coding'

How to Build a Self-Verification Loop in Claude Code (3 Layers, 20 Minutes)

Claude Code's Stop hook blocks the agent from finishing until verification passes. Combine it with...…

AI giant Anthropic hires Australian boss as it opens local office

The company behind chatbot Claude is opening its Sydney doors as workers grow increasingly anxious about AI’s impact on their jobs.…

Claude-powered AI coding agent deletes entire company database in 9 seconds — backups zapped, after Cursor tool powered by Anthropic's Claude goes rogue

Used a Claude Code skill to fine-tune Qwen3-1.7B from 327 noisy traces, matches GLM-5

Had 327 production traces from a restaurant-reservation agent I wanted to retrain. The plan was to fine-tune a smaller self-hostable model so I could ditch the frontier-API bill. T…

Anthropic's Claude remote uses Nested-If-Else-Statements-v8.4 [SATIRE]

Anthropic's Claude remote uses GLM-4.7

I just noticed this after a bug wasn't getting fixed. If you start a Claude code remote environment the default model (hidden on mobile) is glm 4.7 I assumed anthropic only used th…

EvanFlow – A TDD driven feedback loop for Claude Code

A TDD-driven iterative feedback loop for software development. 16 cohesive Claude Code skills walk an idea from brainstorm → plan → execute → tdd → iterate, with checkpoints throug…

The cost math behind routing Claude Code through Ollama (~90% cut)

Pair Claude Desktop on Anthropic with Claude Code routed through Ollama. Visual walkthrough + copy-paste prompt that cuts your Claude Code bill ~90%. - Coherence-Daddy/use-ollama-t…

What is the best coding agent (CLI) like Claude Code for Local Development

Hey all: I am trying to set up claude code to work with llama.cpp, I am using the Qwen3.6-35B-A3B. I usually use claude code + ZLM subscription i got lucky with $30 yearly - the se…

Opencode-power-pack – Claude Code skills ported to OpenCode

I switched from Claude Code to OpenCode a few weeks ago and realized most of Anthropic's official Claude Code plugins don't transfer directly. The reason is that those plugins put …

Claude just got another superpower...

Enjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube.…

Is Claude Code going to cost $100/month? Probably not - it's all very confusing

Anthropic today quietly (as in silently , no announcement anywhere at all) updated their claude.com/pricing page (but not their Choosing a Claude plan page , which shows up first f…

An update on recent Claude Code quality reports

An update on recent Claude Code quality reports It turns out the high volume of complaints that Claude Code was providing worse quality results over the past two months was grounde…

Qwen 3.6 27B in Claude Code says it will do something then stops and prompts for user reply (not failing a tool call)

I'm running Qwen/Qwen3.6-27B-FP8 via vLLM using this command: vllm serve Qwen/Qwen3.6-27B-FP8 --tensor-parallel-size 4 --gpu-memory-utilization 0.95 --max-num-seqs 8 \ --enable-aut…

Claude 4.7 named a journalist from 125 words of unpublished writing

Surprised this isn't a bigger topic but you tell me! In short: writer Kelsey Piper pasted 125 words of an unpublished political column into 4.7 and got her own name back. She'd log…

Is running multiple Claude chats actually making you more productive?

I’ve been seeing a lot of people talk about running multiple Claude chats in parallel — basically multitasking with several prompts/tasks at the same time. Whether it’s working on …

Renda — built with Claude Code, for Claude Design users. Renders HTML exports as clean social PNGs.

If you've used Claude Design for slides, ad sets, or social posts, you've probably hit this: the design is great, the export is HTML, and getting actual usable PNGs out of it is an…

I add CatchEm and now i catch this cool characters while working with Claude

developing with Claude code is great. it feels like a game where you always want to go back and do “just one more thing”. but in games you get rewards — tokens, characters… so i de…

I built Claude Code skills for writing agent prompts, grounded in prompt research

I've been building agentic systems for a while and wanted a more systematic approach to writing prompts. So I gathered papers, did some deep research and created guides on structur…

What Claude Design does really well (and not so well)

I did a deep dive on Claude Design and below are my thoughts. What it does extremely well: Improves your prompt - similar to "ask me questions" when chatting to an LLM. Can make th…

I made a Claude skill for claude.ai web (free tier) that outputs a heredoc command for code changes instead of wasting tokens reprinting your whole file

Whenever I asked Claude to make a code change it would reprint the entire file with like 400 lines of unchanged code just to swap out one component. Burning through your daily limi…

How do you decide which Claude Code tasks to run with Opus vs Sonnet vs Haiku?

Been vibe coding full-time for a few months. One workflow question I haven't nailed down yet: how do you decide which model to use for which task in Claude Code? I know Opus is ove…

Claude snuck in a new email sign off

I don’t usually use AI to draft emails but today I had to pull some info from a number of sources so had Claude draft something. I did lol when I saw the sign off under my email si…

Three things I've measured about Claude's behavior in long sessions — with reproducible test cases

Running production Claude agents for 35 days. Some behavioral patterns I've confirmed with reproducible tests: **Pattern 1: Constraint adherence weakens at high token depth*\ * Tes…

Claude for Personal USE

Anybody out here using Claude for daily personal usage- like weekly grocery, personal training or finances ? Would love to hear !!…

Stt.ai MCP Server

Model Context Protocol server for STT.ai — transcribe URLs, list/search transcripts, summarize, analyze, generate, and chat with transcripts from Claude Desktop / Cursor / any MCP …

Is the Google Drive connector in Claude.ai just… broken for everyone?

**Claude.ai MCP connectors seem to be silently degrading — Google Drive broken, Gmail now only reads metadata. Anyone else?** I use Claude as a personal finance assistant. Two conn…

Claude in excel is the best thing AI has brought to my life

What are regular folks using Claude for? Pictures and designs are not my interest. I’d like to use Claude more but I can’t find where else to exploit Claude capabilities besides MS…

Claude Cowork Now Runs Any LLM. Test It Free

OpenAI, Gemma, Kimi K2, or run locally. Free via OpenRouter. Anthropic shipped it quietly.…

How I personally deal with Claude's limits without giving up on Opus

I only use Sonnet as my main model. I instruct it to delegate indexing and similar grunt work to Haiku, and whenever something genuinely needs deeper thinking, I tell it to "consul…

two years ago this sub had 12k members asking "is claude better than chatgpt for writing" and now the company is worth a trillion dollars

I joined this sub when claude 3 opus dropped and it was a completely different world in here, small group of people who'd stumbled onto something that felt genuinely different from…