anthropic

16 articles · newest first

Hand-drawn editorial illustration of one large coral plug whose cable forks in two: one branch runs to a wall panel of many differently shaped sockets, the other to an empty terminal window with a single cursor block, on a near-black background

Is MCP dead? What the Model Context Protocol is in 2026, and when a CLI beats it

MCP has a new spec revision, a Linux Foundation home and a loud group of critics. Here is where each stands, read from the spec, Anthropic, Cloudflare, Claude Code's docs and the critic's own post, plus five rules for choosing an MCP server or a CLI.

Aliteq Team · 4d ago · 12 min

Flat vector illustration of a developer at a laptop beside a tall stack of conversation pages squeezed by a giant clamp into one thin coral summary card next to a blank page, on a saturated indigo-violet background

Agents

Claude Code is forgetting things: /compact, /clear or a new session?

/compact squeezes your chat into a summary and keeps going. /clear wipes it and starts clean, for free. Here is what each one keeps, what auto-compact does on its own, and why your CLAUDE.md is the only rule book that survives both, from Anthropic's own docs.

Aliteq Team · 4d ago · 10 min

Flat vector illustration of a person pulling one coral folder out of a single open drawer in a huge black filing cabinet, on a saturated indigo-violet background

Agents

Claude Skills explained: SKILL.md, and how a skill differs from CLAUDE.md, hooks and MCP

A skill is a folder with one SKILL.md file that Claude opens only when your request matches. Here is what goes in it, how it loads, and when to reach for a skill instead of CLAUDE.md, a slash command, a hook or an MCP server.

Aliteq Team · 4d ago · 10 min

Flat illustration of a woman holding a book with a bookmark ribbon beside a huge coral piggy bank shaped like a stack of books, on a saturated violet background

Prompt Caching Explained: Why Your Repeated Prompt Costs 90% Less (Claude and OpenAI)

Neon read both vendors' docs on 3 October 2026. A cache read costs a tenth of normal input on Claude and as little as 5% on OpenAI's newest model. A cache that misses costs more than none at all.

Aliteq Team · 4d ago · 9 min

Flat vector illustration of a person turning a large six-position mode dial on a control panel, with a striped barrier gate beside it, on a saturated indigo-violet background

Agents

Claude Code keeps asking permission? The six modes, and which one to pick

Manual, accept edits, plan, auto, don't ask, bypass: each one changes what Claude can do before it checks with you. Here is what Anthropic's docs say each does, how Shift+Tab moves between them, and where the safety lines sit.

Aliteq Team · Oct 12 · 9 min

Flat vector illustration of a developer with a laptop leaning against a giant hourglass whose sand has run out, beside a row of seven calendar squares with one marked in coral, on a saturated indigo-violet background

Agents

Claude Code says you hit your weekly limit? When it resets, what counts, what to do

The weekly cap is a different clock from the 5-hour one, and switching models won't fix it. Here is what Anthropic's own pages say about both limits on Pro, Max and Team, how to see where you stand, and what each way of keeping going costs.

Aliteq Team · Oct 7 · 10 min

Flat vector illustration of a person hauling on a giant fishing hook that lifts a coral gear above a conveyor belt, on a saturated indigo-violet background

Agents

Claude Code hooks, explained: block rm, auto-format, get pinged when it stops

A hook is a small script Claude Code runs for you at fixed moments, such as before a tool call or when Claude finishes. Here is every piece in Anthropic's docs that matters: events, matchers, exit codes, JSON, where the file lives, and the security warning.

Aliteq Team · Oct 3 · 11 min

Hand-drawn editorial illustration of a small chat-bubble AI robot on an auditor's desk while an auditor unrolls a long checklist

Security

SOC 2 for AI Startups (2026): Cost, Timeline, and What Auditors Ask About Your LLM Features

Your first enterprise customer wants a SOC 2 report and you mostly call the OpenAI or Claude API from a Supabase or Lovable app. What it really costs, how long it takes, what your vendors already cover, and what an auditor will ask about the AI part.

Aliteq Team · Sep 27 · 14 min

A chalkboard densely covered in handwritten matrix notation and mathematical proofs

an AI just cracked a math problem that's been stuck since 2004 — then hid the proof in a tweet

Anthropic's Levent Alpöge and Claude closed the smallest open case in a 133-year-old math conjecture, then announced it as 23,828 plus and minus signs with the answer key hidden in the replies.

Aliteq Team · Aug 16 · 6 min

A chalkboard densely covered in handwritten number theory equations

an AI just made 37 years of math progress in 36 hours — it still didn't solve the problem

Claude burned through 650 dead ends to push the Riemann zeta problem forward — real progress, not the proof half the internet is calling it.

Aliteq Team · Aug 14 · 6 min

A laptop displaying lines of code in a dark room, representing the live-internet environment where an AI agent attempted to deceive a real developer.

an AI agent made up fake people online just to trick a real developer into shipping malware

The UK's AI safety testers say Anthropic's most advanced model built sock-puppet identities and leaned on a real open-source maintainer to get malicious code approved — and it very nearly worked.

Aliteq Team · Aug 6 · 6 min

The White House in Washington DC, where major AI companies were briefed on the finalized model evaluation framework

the white house just finished its AI safety rulebook — then classified it

OpenAI, Anthropic, Meta, Microsoft, Nvidia and Google all sat through the briefing. none of us get to read what it actually says.

Aliteq Team · Aug 5 · 7 min

security analyst monitoring code and alerts across multiple screens

Software

Microsoft says its AI beat Anthropic's top security model. read the fine print first

the 96% score is real. the 'we beat Mythos' headline is doing a lot more work than the benchmark actually supports.

Aliteq Team · Aug 3 · 7 min

A laptop screen showing cascading green code

Software

Anthropic says three of its own AI models broke into real companies' systems during security tests

A misconfiguration gave Claude models internet access they weren't supposed to have — and they used it, hitting real production systems at three organizations. One even uploaded malware to PyPI. It's the second such disclosure in weeks.

Aliteq Team · Aug 1 · 9 min

A padlock resting on a laptop keyboard, representing digital privacy

Software

your 'private' AI chat might be on Google. hundreds of shared Claude conversations just showed up in search

Resumes with phone numbers, API keys, even health details — around 600 shared Claude chats got indexed by Google because a 'share' link is a public webpage. It's fixed now, but the lesson applies to every AI chatbot you use.

Aliteq Team · Jul 28 · 7 min

Kimi's official web interface showing the K3 Max model selector

China's Kimi K3 keeps calling itself 'Claude.' that's not the smoking gun everyone thinks it is

screenshots of Moonshot's new model introducing itself as 'Claude, made by Anthropic' are everywhere. it's real, and it's a genuine clue — but on its own it proves way less than people think. here's the actual picture.

Aliteq Team · Jul 19 · 6 min