Claude Code in the Media

GitHub - Vincentwei1021/video-shotcraft: AI video skill for Claude Code & Codex — cinematic product videos with Remotion: 152 shot recipe cards, 209 motion previews, a production

AI video skill for Claude Code & Codex — cinematic product videos with Remotion: 152 shot recipe cards, 209 motion previews, a production-ready template - Vincentwei1021/video-shotcraft

Agentic SDLC with the Claude Code Plugin

Watch Claude Code us

China Blasts “False Information For Political Purposes” After Anthropic Claude Code Logs Allegedly Unmask A 26-Year-Old Hacker Of Nine South Korean Banks, Who Now Says He’s Being Framed

The primary suspect blamed for recent attacks on South Korean banks is now denying that he committed those acts. Meanwhile, Anthropic's Claude Code session files have seemingly revealed his identity after he asked the LLM to update his resume with his hacking-related prowess. And now China's Foreign

CyberXero Combines Claude Code, PentAGI and Cobalt Strike in AI-Augmented Cyberattacks

CyberXero has emerged as an initial access broker that combines familiar hacking tools with artificial intelligence to run large-scale intrusions. The Russian-speaking operator targeted WordPress and e-commerce sites worldwide while separately probing Ukrainian energy and utility organizations. T

The smartest Claude code feature is not for its users

Zohaib Ansari is a software engineer building full-stack systems, Android apps, and AI products.

I ditched Claude Code and Codex’s rate limits by switching to this open-source agent with 75 model providers

This open-source tool lets me use Claude Code and Codex without worrying about rate limits.

Claude Code on Autopilot: Schedule It Once and Walk Away

#188: Part 4 - Claude Code 24/7

What Claude Code Can and Can't Do with Full Access Inside a Docker Sandbox

Claude Code can do more than suggest a fix. It can edit files, install dependencies, run tests, and start your application. But letting it finish a task on its own raises a practical question: how muc

I analyzed 1,100+ job posts with Claude Code. Here's what B2B marketers get paid.

B2B startup marketing salary and equity benchmarks. Plus Claude skills to explore the salary data.

Barclays Accelerates AI Rollout With Anthropic’s Claude Code

British universal bank Barclays expects half of its developers to be using Anthropic’s agentic artificial intelligence coding tool Claude Code by the end of the year, and most of them to be using it by the end of 2027, Anthropic said in a Thursday (Oct. 1) press release. The growing adoption of C

Codex Users Are Fleeing to Claude Code

Codex users are leaving for Claude Code. OpenAI cut the Pro 200 plan from 20x to 10x the Plus allowance at DevDay... Read More... </

How to Make Videos with Claude Code

Claude Code can't generate video directly. It isn't a video model like Veo or Sora. It writes text and code. You can... Read More... </

Claude Code for SEO: 35 Use Cases

35 practical ways to use Claude Code for SEO, from content briefs and Search Console analysis to internal linking and technical fixes, with real examples. Read more ›

Claude Code’s Next Era — Thariq Shihipar, Anthropic

Shipping Opus/Sonnet 5.5, Mods, Plugins, Projects, Tag while Pacing the Frontier

'I broke something': A Claude Code AI agent deleted 48,000 files in just over 100 seconds — then apologized for doing so

A developer had an AI agent run 11 tasks. One messed up dearly.

Anthropic rolls out up to $250 in free Claude Code credits, but only for cloud sessions

Anthropic now allows you to run Claude Code via cloud sessions without signing up for the research preview, and it's offering up to $250 in free usage credits, so more users can give it a try. [...]

AI Coding Agents Are Leaking Credentials: Cursor, Claude Code, Copilot, and MCP

Cursor, Claude Code, and GitHub Copilot leave credentials scattered across config files, logs, and shell history that repository and CI scanners never see. Here's where that trail actually lives, and how to close it.

Claude Code deleted 48,000 files in 103 seconds in a dire AI agent warning

A developer lost 48,000 files in 103 seconds when Claude Code mass-deleted their ongoing work.

Anthropic’s Claude Opus 5.5 Appears In Claude Code, Indicating Imminent Release, As Trump Renames AI To “Super Intelligence” Or SI

It seems Anthropic is not following its own call to pace the development of AI, as indicated by the imminent launch of Claude Opus 5.5, which would mark just around three weeks since the AI lab released Claude Fable 5.1. Meanwhile, as the conversation around AI safety continues unabated, with Anthro

Claude Code Just Designed A 12-Actuator Quadruped Robot With 99 Parts From Scratch While Writing The Entire Firmware, But The Real Test Is If It Actually Works

The use of Claude Code in the field of robotics can prove to be a real productivity booster because a developer shows that he spent the last three months building MechFaber, a desktop application that hands the entire hardware design process over to AI, rather than using it as a simple coding assist

Engineer says Claude Code has made his job "soul-sucking" as workers spend 12-hour days pressing enter

<img height="560" src="https://www.techspot.com/images2/news/ts3_thumbs/2026/09/2026-09-22-ts3_thumbs-36e.jpg" style="padding: 15px 0;" title="Engineer says Claude Code has made his job

AWS open-sources an AI agent it says is 45% cheaper than Claude Code and Codex

Claude Code Agent Allegedly Deletes 48,000 Files in 103 Seconds

A Claude Code user has reported a severe data-loss incident in which an autonomous coding agent allegedly deleted 48,218 live files from a Windows project tree and destroyed the repository’s Git object store. The deletion reportedly occurred in just 103 seconds, between 10:10:31 p.m. and 10:12:14

Meta’s Muse Agent Sparks ‘Claude Code’ Moment For CPUs, As 40:1 CPU-To-GPU Ratio Poised To Reshape Intel, AMD, And Arm’s Fortunes

Personal AI agents such as Meta's Muse, who interact with websites and apps just as humans do so, are apparently the next big step-up in AI-driven productivity, and expected to unleash a super cycle for CPUs to the benefit of Intel, AMD, and Arm. Why personal agents such as Muse from Meta, Instinct

Unity launches official plugins for Claude Code and OpenAI Codex to stop AI agents from using outdated tutorials

Unity has released official plugins for Claude Code and OpenA

Antigravity excels at one task, but Claude Code and Codex dominate everywhere else

Three coding agents walked into a workflow, and only one of them stayed for free

Plugin4Shell Zero-Click RCE Hits Claude Code, Codex, Copilot and Gemini CLI

A newly disclosed vulnerability known as Plugin4Shell reveals a supply chain weakness in major AI coding agents. This flaw allows attackers to replace trusted, SHA-pinned plugins with malicious code, enabling remote code execution without user interaction. Researchers Or Nevo, Dor Granat, and Niv

Plugin4Shell Zero-Click RCE Hits Claude Code, Codex, Copilot and Gemini CLI

Plugin4Shell is a high-severity, zero-click remote code execution vulnerability affecting major AI coding agents, including Anthropic Claude Code, OpenAI Codex, GitHub Copilot, and Google Gemini CLI. The flaw allows a malicious plugin update to execute attacker-controlled code without requiring a

Anthropic Rebuilds Claude Code Projects to Run Parallel Agents on Opus by Default

Anthropic's new Claude Code Projects splits a goal into parallel cloud threads, each a full session. Every thread runs Opus at high effort by default, and a thread limit you ask for is only a preference.

Claude Code Is Turning AI Agents Into A Coordinated Team

Claude Code is reportedly turning Projects into shared workspaces where multiple AI agents can coordinate software tasks in parallel.

Anthropic keeps pushing Claude Code toward autonomous coding with new parallel agent workflows

Anthropic has rebuilt Projects in Claude Code. A coordinator now splits

Anthropic launches Claude Code Projects, an ‘always-on’ conversation that remembers and delegates your long-running dev work

Anthropic today launched Claude Code Projects, a new way for developers using its hit "vibe coding" harness Claude Code to stay organized as they build something — an app, website, or other development job — that will require ongoing, persistent development work. <a href="https://

Same Flaw Found in Claude Code, Codex, Gemini CLI and GitHub Copilot

While the AI industry ties itself in knots over models it thinks will pose security threats to the internet and perhaps to humanity itself, researchers are warning about flaws in AI coding agents from Anthropic, OpenAI, Google and Microsoft that pose immediate risk to businesses. For

Anthropic’s new Claude Code feature could drain your plan before lunch

Anthropic is giving C

Developers Find Ways to Use Claude Code Without Anthropic Models

Boris Cherney , the head of Anthropic’s coding tool Claude Code , last month found himself in the middle of an online spat that highlighted how some developers are finding workarounds to using Claude Code with cheaper non-Anthropic models, including those of rival OpenAI

Anthropic cuts Claude Code capacity 17% as Astra lands; memory squeezes laptops

GPT-6 Astra cleared every chamber of Valve's Portal on its own, 3,336 tool calls and $571.18 in tokens.

Logitech MX Keypad puts Claude Code and OpenAI Codex controls on your desk

<img alt="Logitech MX Keypad puts Claude Code and OpenAI Codex controls on your desk" class="attachment-large size-large wp-post-image" height="471" src="https://nerds.xyz/wp-content/uploads/202

Anthropic Adds a Claude Code Audit for Skills That Waste Context

Anthropic spent the summer telling developers their Claude configuration was too long. On September 4 it shipped a command that finds the excess. /skill-doctor reports which loaded skills a session never used, and what each one costs in context on every turn.

I tried Claude Code, Codex, and Lovable, but this underrated tool is the true king of vibe coding

The ideal balance of AI control.

GitSpawn Flaws Let Malicious Repositories Execute Code in Claude Code, Codex, Cursor, and Grok

A newly disclosed class of vulnerabilities, dubbed GitSpawn, allows a booby-trapped repository to silently execute code on a developer’s machine the moment it is opened with an AI coding agent, no prompt typed, no approval clicked, and in some cases before the user has even authenticated. S

Quit Blabbing, Claude Code! Shorter Answers with Output Styles

A note from the author: Just before this post was set to be published, a new feature was released on Claude Code that makes this post somewhat obsolete: Claude’s new “Concise” output style. I was sick of scanning through walls of text each time I asked Claude Code a question. Sk

Claude Code Auto Mode Turns a Routine Web Summary Into Code Execution

A researcher tricked Claude Code Opus 5 in default Auto Mode into arbitrary code execution simply by asking it to summarize a website. The multi-step chain achieved 60-80% success a

Anthropic Beats OpenAI To The Punch With A Nominally Cheaper Claude Fable 5.1, As Samsung Bets Its Chip Designs On Claude Code

In the ongoing seemingly never-ending one-upmanship between Anthropic and OpenAI, the former has just taken an incremental step forward by releasing the Claude Fable 5.1 and Mythos 5.1 models ahead of OpenAI's much-anticipated Astra-class ones. Meanwhile, Anthropic's Claude Code - the coding-focused

How One Go CLI Tames Claude Code’s Multi-Agent Chaos

The Go-based codes CLI brings profile switching, project workspaces, autonomous agent teams and a 43-tool MCP server to Claude Code users. Built on simple file state and YAML templa

I gave Claude Code a deny list, and stopped watching every command it tried to run

I can finally continue working while Claude code works on a task

A researcher hijacked Claude Code by asking it to summarise a web page

Ask Claude Code to summarise a web page, and it can end up running an attacker’s code on your machine. A security researcher got that result in up to 80% of his attempts. Jes

Meta’s Claude Code rival exits beta with three new subscription tiers — and it’s pushing hard on price

<img alt="An illustration of a credit card machine with a receipt, depicting the concept of price." class="webfeedsFeaturedVisual wp-post-image wp-stateless-item" height="819" src="https://cdn.thenewstack.io/media/2026/09/93db7838-tri-wiranto-gfv_lfaayac-unsplash-1024x819.jpg" style="display: block;

Anthropic trims Claude Code weekly limits; ChatGPT ads reach $1 billion

Anthropic signed a $35 billion cloud deal with Lambda on August 31, and Nvidia put $3.5 billion into MediaTek.

I asked Claude Code, Codex, and Antigravity to build the same game, and one absolutely crushed the others

I wanted a game, so I made three

I trained Claude Code on my home server logs, and now it understands my infrastructure better than I do

Claude is helping me fill in the gaps in my knowledge every day

Anthropic's Claude Code limit change is a raise on paper but a cut in practice

Anthropic is effectively cutting Claude Code's weekly usage limits by 1

Researcher shows how Claude Code can be tricked simply by asking it to summarize a website

More prompt-injection hijinks from wunderwuzzi

Claude Code runs malware despite “Auto Mode” security, tries to fix it, gets denied

Claude Code runs malware despite “Auto Mode” security

Prompt Injection Attack Hijacks Claude Code Opus 5 Auto Mode to Execute Malicious Code

A recent demonstration of prompt-injection research has revealed that Claude Code Opus 5, when running in its default Auto Mode, can be manipulated to execute malicious code via a seemingly harmless website summary request. Security researcher Johann Rehberger, who writes under the name “wu

Claude Code Opus 5 Auto Mode Hijacked via Prompt Injection to Execute Malicious Code

Claude Code Opus 5 in Auto Mode can be tricked into running malicious code via a simple website summary request. In a limited lab test, the attack reportedly succeeded in 60% to 80% of attempts. The finding from Embrace The Red is significant because Anthropic previously highlighted testing in wh

Breaking Claude Code Opus 5 Auto Mode

Breaking Claude Code Opus 5 Auto Mode Anthropic are putting a great deal of faith in Claude Code's auto mode for protecting their coding agent users against prompt injection atta

Aider, Claude Code, and OpenClaw ran an identical model. Token use varied 70-fold.

<img alt="Collage of a woman climbing progressively taller stacks of coins, with arrows tracing her upward path." class="webfeedsFeaturedVisual wp-post-image wp-stateless-item" height="712" src="https://cdn.thenewstack.io/media/2026/08/40e08666-pablo-merchan-montes-ky6yrouqe44-unsplash-1024x712.jpg"

Quiz: Getting Started With Claude Code

Test your Claude Code basics: install it, set it up, work with CLAUDE.md, and use Git to stay in control of your changes.

I use Claude Code for planning but a local model for building, and I never hit my usage limits anymore

My usage limits finally stopped being a problem

How to use Claude Code as a GTM leader

Fin CX leader Dee Kapila unpacks her best AI GTM workflows and how Fin’s GTM team became AI-first

I gave the same bug to Claude Code, Codex, Antigravity, and their open-source rival — only one handled it like a pro

Reliability is not a guarantee

I used Claude Code to improve my operating system, and here's how it made me more efficient

Coding was only the beginning

Shopify’s CEO threatened to ban Claude Code. Anthropic had already closed the feature request.

Shopify CEO T

X Ads MCP gives Grok and Claude Code 23 tools to run ad campaigns

Ten of the 23 tools write to live ad accounts, though every campaign an agent creates starts paused until a person activates it. Who logs the change, and when?

Windows veteran's vibe-coded Task Manager now also runs on Mac and Linux — downloadable app is the result of a 107-page spec fed to Claude Code

Legendary Windows developer Dave Plummer has been busy finessing his revamped Task Manager, now dubbed TMOG.

Samsung thinks Claude Code can help it boost chip design — but admits the AI still makes some worryingly big mistakes

Samsung's chip division is finding out what agentic coding tools do when you leave them alone: when asked to deal with a stubborn error, Claude reclassified it as an informational notice to be 'rid' of the issue

I ran Claude Code against Archon on the same bug six times, and the run that failed told me the most

The fix was never the problem

Weekly Cyber Security Newsletter Bulletin – Entra ID RCE, Claude Code Ransomware, T-Mobile Cable, Azure Credential Theft +20 Stories

This week’s bulletin captures a cybersecurity landscape increasingly shaped by artificial intelligence, both as a weapon and a shield. A ransomware affiliate weaponized Claude Code to autonomously steal LDAP credentials, backdoor VPNs, and exfiltrate SQL databases, while a separate criminal

I gave Claude Code its own disposable computer, and stopped caring what it installed

I can finally stop approving commands.

Spline rebuilt its entire 3D editor. Then it handed the keys to Claude Code.

<img alt="An illustrated eye with a keyhole at its center, surrounded by concentric digital rings — evoking surveillance, identity security, and the human element in cybersecurity." class="webfeedsFeaturedVisual wp-post-image wp-stateless-item" height="745" src="https://cdn.thenewstack.io/media/2026

How to build an E-E-A-T checker with Claude Code

Build an AI-powered E-E-A-T auditor that crawls websites, applies Google's quality guidance and gener

Anthropic’s Stubborn Stand on AGENTS.md Leaves Claude Code Developers Frustrated

Anthropic's refusal to support the popular AGENTS.md standard in Claude Code has frustrated developers for over a year despite thousands of upvotes. The company insists on its own C

Anthropic’s Claude Code Watermark Easily Bypassed by Simple Developer Tools

Anthropic’s new invisible watermark for Claude-generated code was quickly bypassed by developers using simple tools like formatters, random comments, or intermediary models to laund

Claude Code Works Best on Five DaVinci Resolve Studio Editing Tasks

Claude Code can operate inside DaVinci Resolve Studio. The useful question is which jobs it handles well, and where the editor still has to intervene.

Claude Code kept asking the same questions until I showed it this one markdown file

CLAUDE.md is what I was missing.

Crypto Scammer Uses Claude Code to Screen 100,000+ Phone Numbers in Phishing Operation

Rapid7 found a crypto scammer used Claude Code on more than 100,000 phone numbers in a phishing and vishing operation targeting cryptocurrency holders. The post Crypto Scammer Uses Claude Cod

A Claude Code skill was eating 200,000 tokens before answering a single question

<img alt="Abstract digital artwork resembling a glitching computer interface, with fragmented windows and overlapping shapes in red, pink, yellow and blue." class="webfeedsFeaturedVisual wp-post-image wp-stateless-item" height="556" src="https://cdn.thenewstack.io/media/2026/08/c3134c2c-egor-komarov

Anthropic Launches New /design Skill for Claude Code UI Workflows

Anthropic has introduced a new /design skill for Claude Code, expanding its developer-focused AI platform into user interface design workflows. The feature is currently available as a research preview. It brings Claude Design’s artboard-based experience to both the Claude Code command-line interf

Crypto Scammer Uses Claude Code to Process 100,000+ Phone Numbers for Victim Targeting

A cryptocurrency fraud operation has been found using AI coding tools to turn huge phone lists into a sharper victim-targeting system. The campaign combined account checks, phishing emails, phone calls, and counterfeit wallet software to pursue people likely to own digital assets. The operation,

Claude Code gets a /design command that lets developers create UI mockups right in the terminal

With the /design command, Anthropic brings a visual design workfl

Hackers Turn Claude Code and Codex Into AI-Powered Tools for Credential Theft and Cloud Attacks

Threat actors are increasingly using coding assistants as operational tools. Detailed research from Gambit Security highlights three campaigns where Claude Code, OpenAI Codex, and large language models facilitated activities ranging from ransomware preparation to the harvesting of secrets on a la

Claude Code Helps Ransomware Operator Steal LDAP Passwords, Backdoor VPNs and Exfiltrate SQL Databases

A new threat intelligence report from Gambit Security has documented one of the clearest real-world examples yet of artificial intelligence being weaponized inside an active ransomware campaign. Researchers found that a suspected affiliate of The Gentlemen ransomware-as-a-service operation used A

Claude Code taught me ESP32 development, and my smart home projects got way faster

I didn't think I could use Claude code for this, but it worked

Samsung says Claude Code can cut chip design work from weeks to days, but it still makes serious mistakes

<img height="560" src="https://www.techspot.com/images2/news/ts3_thumbs/2026/08/2026-08-15-ts3_thumbs-a8c.jpg" style="padding: 15px 0;" title="Samsung says Claude Code can cut chip design

How we rebuilt the Auggie CLI harness to make tasks 53% cheaper than Claude Code

How we rebuilt the Auggie CLI harness to make tasks 53% cheaper than Claude Code

PSA: Claude Code now enables auto mode as default, Anthropic says

Claude Code auto mode has become the default permission setting for users starting today. Sessions for Pro, Max, and Te

Claude Code now runs daily maintenance on Anthropic's software with a 46 percent merge rate

Anthropic is testing whether Claude Code can handle daily maintenance of th

DeepSeek Raises Prices Fourfold on V4-Pro While Launching Open Claude Code Rival

DeepSeek quadrupled peak prices on its V4-Pro model while previewing an open harness to rival Anthropic's Claude Code. The shift from loss-leading to profitability comes as the firm

DeepSeek Harness launches as open source rival to Claude Code, alongside V4-Pro on API with higher prices

DeepSeek is expanding beyond the model layer and deeper into the software developers use to put AI agents to work. The Chinese AI lab on Thursday launched the official version of DeepSeek-V4-Pro , an updated flagship model fo

DeepSeek built a Claude Code rival, then quadrupled its prices

Start with the money, because it is the part every developer noticed. From 16 August, a million output tokens through DeepSeek-V4-Pro costs $3.96 at peak, up from

Blacklight Toolkit Finds Codex, Claude Code, and Cursor Artifacts Exposing Tokens and Session Data

SpecterOps has released Blacklight, an open-source toolkit that identifies local artifacts from AI coding agents like Codex, Claude Code, Cursor, and Antigravity CLI, which can expose authentication data, session history, project details, and connected services. AI agents are increasingly used to

Nimbalyst Runs Claude Code and Codex Agents Across Mac, Windows and Linux

The MIT-licensed workspace puts both coding agents on one board, but its cross-platform reach is easier to prove than its lead over rivals.

Most people pay $20 for Claude Code, but OpenCode Go is $10 and I can barely spend a dollar of it

Claude Code is a good deal, but OpenCode Go is an even better one.

I gave Claude Code, Antigravity, and my local LLM the same coding project, and only one of them understood the assignment

The result I did not see coming

Anthropic Bets on AI Over Human Judgment as Claude Code Auto Mode Goes Default

Anthropic makes Claude Code auto mode the default for Pro, Max and Team users starting August 14. Tests show the classifier blocks 89% of dangerous commands while humans catch only

AWS Continuum integrates with OpenAI Codex and Anthropic Claude Code in major AI security push

Amazon Web Services is threading its AI-powered security infrastructure directly into the coding environments built by two of its fiercest rivals — and in doing so, it is making a bold bet that controlling the security layer matters more than controlling the

Claude Code’s auto mode will be on by default, Anthropic confirms

Claude Code's auto mode, which doesn't ask for prompts at each step, is now the default option.

Claude Code Shifts Agent Security From Repeated Human Approval to Auto Mode

Anthropic is changing how Claude Code handles risky commands, moving away from constant human approval prompts and toward an automated safety classifier called auto mode. Starting August 14, 2026, auto mode will become the default setting for new sessions on Claude Code’s Pro, Max, and Team

Anthropic ends per-action approval in Claude Code; workers keep 66% of AI output

Musk's Texas fab opens at $16.8 billion, and a repo telling AI agents to ignore their own rules hit 20,000 stars.

Claude Code puts auto mode in the driver's seat

Walk away and hope the classifier catches anything irreversible or destructive