#Claude Code
50 articles with this tag
Most read in #Claude Code, last 30 days
- 01
How to Use Claude AI Free: 14 Methods That Actually Work
- 02
The Two Words Every Security Startup Is Adding to Get Bought: Claude Code Just Made It Obvious
- 03
PayPal's Agent Authorization Model Explained
- 04
Agents beat humans on speedruns, still can't invent
- 05
Web Search APIs for AI Agents: Benchmarks, Pricing and MCP Setup
- 06
Coding Agents Security Failed 70 Times, Same Bugs
IMEC shows when owning AI models beats API bills
IMEC's Steven Latré told AI Engineer when hosting open-weight models beats APIs: GLM-class coding workloads saved 24-25% and Kimi K3 hit 86% but only four concurrent users.
Sonar Wants Your AI Agent to Stop Guessing
Sonar's Vortex injects SonarQube rules into AI coding agents to cut token waste and catch shared temp-file flaws before PR.
Anthropic now merges 30,000 changes a day
Anthropic merges 30,000 changes a day and uses Claude to test like a user before humans review. Verification is the bottleneck.
The AI Engineer Now Builds the Loop, Not the Feature
Aparna Dhinakaran told AI Engineer the AI engineer now builds the loop, not the feature, and demoed Arize Signal's always-on agent for traces.
Your model isn't the bottleneck, Jellyfish finds
Jellyfish data on 50,000 engineers shows model choice explains <1% of PR throughput. Skill use and context matter far more.
Stripe Lets Agents File Your Startup, With Limits
Stripe now lets you start Atlas incorporation from an AI agent or CLI, but signatures and payments stay in the Dashboard.
GEICO spent $1,000 to map legacy claims in a day
GEICO ran a one-day, $1,000-token war room to map legacy claims code and ship agent APIs, using Anthropic's Fleet Kit and code-modernization plugin.
Smarter models didn't kill the harness
Jedidiah Katz says frontier models absorbed coding tricks, but the agent harness still controls trust, cloud runtime and cost.
Two Years of Shipping Landed on Same Median
Hariprasad Sudharshan told AI Engineer two years of AI-assisted building converged on the same median product, leaving distribution as the only moat.
How to Build an AI Shopping Agent That Searches Amazon and Pays With Stripe Link
A step-by-step guide to an AI shopping agent built as a remote MCP server, with SerpApi for Amazon search and Stripe Link for a one-time virtual card.
Web Search APIs for AI Agents: Benchmarks, Pricing and MCP Setup
Eleven web search APIs for autonomous agents compared on latency, cost per 1,000 calls and factual accuracy, with the MCP wiring for Claude Code.
The Two Words Every Security Startup Is Adding to Get Bought: Claude Code Just Made It Obvious
Open Claude Code and the skills marketplace lists 100+ cybersecurity installs. Read the descriptions and they are selling the same control-plane story.
Agents beat humans on speedruns, still can't invent
Prime Intellect pitted Claude Code and Codex against humans on the NanoGPT optimizer speedrun. They won on steps, but produced no new optimizer.
Cursor is better. Cancel Claude Code.
Cursor is better than Claude Code. Cancel it. I use the command line. You can also run cloud agents and close the laptop.
Lightsage $4M funding for Agent-Led Growth
Lightsage raised $4M led by Nexus to build Agent-Led Growth infra that tests if AI agents can actually use your API.
PayPal's Agent Authorization Model Explained
PayPal lays out a three-question test for agentic payments and previews its Approval Token as a step toward FIDO AP2 mandates.
Coding Agents Security Failed 70 Times, Same Bugs
Palo Alto Networks researchers pwned 10 coding agents 70+ times with the same command and file-system bugs, and even OS sandboxes fell to symlink tricks.
Ironclad Rethinks AI Token Spend ROI
Ironclad replaces token leaderboard culture with trusted throughput, measuring merged PRs and review quality to raise ROI on AI token spend.
Agentic Engineering Is Now Writing All the Code
DHH tells Lex Fridman that agents now write 100% of his Omarchy Quatro code, flipping programming from handcraft to steering.
AI Diffusion Requires Owners, Not Vendors
Long Lake's Varun Shenoy says AI diffusion is a 20-year owner-operator problem and lays out a five-rung ladder from co-pilot to co-worker.
Inside the Uber Software Factory Scale Play
Uber runs 70% of pull requests via agents and cut cost per session 52% by capping context, tuning cache TTL and routing subagents to cheaper models.
Dario Amodei, 2% Owner of a $965B Company, Seeks Founder Control
Bloomberg reported on August 18, 2026, that Anthropic plans to give Dario Amodei and co-founders super-voting shares before the company's IPO, despite Amodei holding roughly 2% of the company. Anthropic's annualized revenue ran from $9 billion at end-2025 to $47 billion by May 2026, almost tripling its valuation from $380 billion to $965 billion in three months.
Claude Code Adds AI Design, Cross-Session Chat
Anthropic's Claude Code rolls out AI-driven UI design previews and cross-session chat, enhancing developer workflows.
Claude Code Adds Design Preview, Cross-Session Chat
Anthropic's Claude Code introduces a 'Claude Design' research preview and cross-session messaging, enhancing developer productivity and collaboration.
YC QM Agent Harness: A Collaborative AI Shift
Y Combinator's new open-source QM project introduces a multiplayer agent harness for startups, focusing on collaborative AI with isolated workspaces and flexible model integration.
AI Agents Revolutionize Scientific Software
AI agents are transforming scientific computing, speeding up software development and maintenance, but human oversight and long-term stewardship remain crucial.
Anthropic's Boris Cherny on Building Claude Code
Boris Cherny of Anthropic discusses Opus 5's advancements, prompt injection resistance, and the 'unhobbling' philosophy behind Claude Code's development.
Anthropic, Cognizant Deepen AI Partnership
Cognizant is expanding its use of Anthropic's Claude AI across its internal platforms and client services, training over 30,000 employees.
Anthropic Launches Claude Opus 5
Anthropic releases Claude Opus 5, delivering near-frontier AI intelligence at a reduced cost with state-of-the-art performance in coding and knowledge work.
Sakana Fugu-Ultra v1.1 boosts AI performance
Sakana AI's Fugu-Ultra v1.1 orchestration engine sees performance gains and adds a Claude Code-compatible interface.
Anthropic's Claude Code Creator on AI's Future
Boris Cherny, Head of Claude Code at Anthropic, discusses the evolution of AI models, the future of software engineering, and Anthropic's focus on AI safety.
Claude Code Adds Live Artifacts, Screen Reader Mode
Claude Code's latest update introduces 'artifact features' for live data interaction, alongside screen reader mode and enhanced sharing capabilities.
Anthropic's Cat Wu & Thariq Shihipar on AI in Software Dev
Anthropic's Cat Wu and Thariq Shihipar discuss the evolution of Claude Code and the impact of Claude Tag on software development, emphasizing increased efficiency and collaboration.
Sierra's AI Agents Boost Productivity
Sierra's AI agent, Pinecone, is revolutionizing business productivity by consolidating workflows, maintaining context, and leveraging business-specific data.
Dario Amodei's Bankruptcy Warning Preceded Anthropic's 80x Quarter
Dario Amodei warned in February 2026 that a one-year timing miss in AI demand forecasts could push Anthropic into bankruptcy. By May, the company had grown 80-fold in a single quarter, closed a $65 billion Series H at a $965 billion valuation, and filed a confidential S-1 with the SEC.
Anthropic Claude Sonnet 5 Powers Up Dev Tools
Anthropic's Claude Sonnet 5 becomes the default for paid tiers, bringing a 1M token context window and enhanced coding capabilities, alongside new Claude Code features.
Claude Code’s Mid-Year AI Boost
July 2024 saw Claude Code introduce major updates, including an in-app browser, the Sonnet 5 model, and workflow enhancements.
Alberta Gov Taps Claude for Cyber Defense
Alberta's government uses Anthropic's Claude AI to scan millions of lines of code, finding and fixing cybersecurity vulnerabilities in hours.
Omnigent Policies Get Smarter
Databricks' Omnigent introduces contextual policies, allowing AI agents to govern actions based on session history for enhanced security and cost control.
Claude Opus 4.8: Anthropic's New Default
Anthropic's Claude Opus 4.8 is now the default model for premium plans, bringing enhanced effort levels and new developer tools like dynamic workflows.
Claude Code's Mid-Year Dev Push
June 2026 updates for Claude Code bring enhanced CLI features, real-time artifact sharing, and improved AI model integration.
Anthropic AI Updates Accelerate Development
Anthropic's Claude Code is rapidly evolving with weekly updates, boosting developer productivity and AI capabilities, including the rollout of Opus 4.8.
What Is Claude Code: Features, Agent Swarms and How It Works
Anthropic's Claude Code is rapidly evolving with weekly feature drops, enhancing agent capabilities and developer workflows.
TCS Taps Anthropic's Claude for Regulated Industries
TCS partners with Anthropic to bring Claude AI to regulated industries like finance and healthcare, integrating it into its own operations and client solutions.
FrontierCode: AI Coding Benchmark Goes Beyond Correctness
Cognition's FrontierCode benchmark redefines AI code evaluation, measuring real-world 'mergeability' and finding current models fall short of production standards.
Claude Code Benchmarking: Semantic Search vs. Grep
Turbopuffer's Kuba Rogut benchmarks semantic code retrieval on Claude Code, revealing how semantic search enhances AI agent precision and efficiency compared to grep.
Claude Code's Latest Updates
Claude Code rolls out Opus 4.8 as default, introduces dynamic workflows, security plugins, and performance enhancements for developers.
Claude Code Sets Opus 4.8 as Default Model for Developers
Claude Code updates its default model to Opus 4.8, introduces dynamic workflows, security plugins, and faster, cheaper Opus options.
Reverse Engineering a Viking VOIP Phone with Claude Code
Boris Starkov reverse-engineered a Viking VOIP phone's protocol using AI, bypassing proprietary software via a MITM attack.
Anthropic Debuts Claude Opus 4.8
Anthropic unveils Claude Opus 4.8, boosting AI performance with new features like 'effort control' and 'dynamic workflows' for complex coding.
