AI Tools & Guides

anthropic launches free ai vulnerability scanner for open source maintainers with no human review Open-source maintainers will start getting vulnerability reports from Anthropic that were written by AI, and no person at the company will look at them before they are sent. Anthropic says it expects the reports to be more than 90 percent accurate, but it also admits they may contain errors.

Anthropic launches free AI vulnerability scanner for open-source maintainers, with no human review

anthropic opens up claude code with mods that can reshape the ai coding tool from within The most important detail in Anthropic's launch of Mods for Claude Code is this: they run without a sandbox and with your own permissions. Anthropic warns users about it too, and advises installing Mods only from sources they trust.

Anthropic opens up Claude Code with Mods that can reshape the AI coding tool from within

unity releases official claude code and codex plugins so ai agents stop learning the engine from stale tutorials Unity's grievance with coding agents is a precise one: they pick up the engine from the wrong release. According to the company, general-purpose agents usually lean on forum posts and tutorials aimed at outdated engine versions, so the code they generate may compile yet frequently fails to behave as intended.

Unity releases official Claude Code and Codex plugins so AI agents stop learning the engine from stale tutorials

pangrams new gmail add on tags the ai written mail before you open it Sorting cold emails into piles for two months straight — that is the routine Pangram co-founder and CEO Max Spero describes having lived with before the company opened the feature up to everyone.

Pangram’s New Gmail Add-On Tags the AI-Written Mail Before You Open It

claude code projects returns as a control room for fleets of cloud agents What Anthropic is selling with the rebuilt Projects feature in Claude Code is not a nicer chat window. The pitch is a team of agents that talk to one another.

Claude Code Projects returns as a control room for fleets of cloud agents

hugging faces ml intern turns a chat prompt into a running training job Under $0.50 for six hours of training. That figure appears in Hugging Face's demo video for ML Intern, the assistant it has just plugged into its chatbot, and it is the single detail that reveals what the tool is really meant to do.

Hugging Face’s ML Intern turns a chat prompt into a running training job

vibe coding explained and why plenty of developers want nothing to do with it Seventy-four vulnerabilities. That is the tally researchers at Georgia Tech's School of Cybersecurity and Privacy arrived at after combing through 43,000 security advisories this past April and tracing the defects straight back to AI-generated code. Fourteen of the 74 were rated critical.

Vibe coding, explained — and why plenty of developers want nothing to do with it

claude voice mode explained the settings that stop it cutting you off Right up to this July, anything you said aloud to Claude came back in the voice of Haiku, the weakest model Anthropic ships. That was never really a product call — it was a latency one. Quick model, quick answer.

Claude voice mode, explained: the settings that stop it cutting you off

ai model distillation explained the cheap way to inherit an expensive models brain Building a capable AI model on the cheap comes down to one trick: get somebody else's costly system to do the teaching for you. That single sentence contains the entire dispute.

AI model distillation, explained: the cheap way to inherit an expensive model’s brain

gemini2.5 Google has announced the launch of its upgraded Deep Research feature, now powered by the Gemini 2.5 Pro model.

Google Upgrades Deep Research with Gemini 2.5 Pro for Smarter, Faster Information Analysis