PyTorch's `nn.Linear` module transposes its weight tensor before performing matrix multiplication and addition, as revealed by profiler traces showing an `aten::t` operation that only modifies tensor …
A new survey of open-source GitHub projects has identified over 40 tools for browser stealth and fingerprint evasion, spanning source-level patches, JavaScript injection plugins, and protocol-level by…
Port of Context eliminated production agent failures by implementing Code Mode, a sandboxed execution path within the open-source agent harness goose, achieving 100% task delivery versus 56% without i…
Microsoft has introduced Spec-Driven Development (SDD), a spec-first approach to AI-native engineering that uses structured specifications as a shared source of truth for humans and AI. The approach a…
Tessera, a consent-gated remote access broker, allows users to share local ports (e.g., databases, dev servers) with temporary, audited access via an 8-character code and terminal approval. The tool, …
GitHub has released a new experimental `/security-review` slash command for Copilot CLI, now available in public preview, that analyzes local code changes for security vulnerabilities such as injectio…
Anthropic launched Claude Fable 5 and Claude Mythos 5, raising security and compliance concerns. A supply chain attack via compromised Microsoft GitHub infrastructure targeted AI coding agent users, b…
AI labs Anthropic and OpenAI are shifting from flat-rate subscriptions to usage-based billing, with Anthropic's Claude Fable 5 launching at $10 per million input tokens and $50 per million output. Git…
MiniMax released M3, the first open-weights model combining frontier-level coding ability, a 1M-token context window, and native multimodality, which a developer tested on real tasks including a code …
Lindy, an AI agent startup, switched its underlying model from Anthropic to DeepSeek and reports saving millions of dollars in inference costs. The company made the change to address the rising expens…
GitHub has introduced custom agents for GitHub Copilot CLI, allowing developers to define reusable, reviewable workflows that encode team-specific stack and standards directly into the terminal. By us…
In May 2026, two supply-chain attacks targeted AI coding tools including Claude Code and Cursor, with one malicious VS Code extension stealing npm, AWS, GitHub, and SSH credentials from 6,000 develope…
A new variant of the Miasma worm has been discovered exploiting npm's binding.gyp build file to execute malicious code during package installation, bypassing traditional package.json script audits. Th…
A developer describes automating their coding workflow using Claude Code on an EC2 instance with cron daemons that process GitHub issues, but fell into a self-doubt spiral after overshooting the compl…
Google announced at I/O 2025 the stable release of Android CLI v1.0 with new features like programmatic version lookup and direct integration with Android Studio. The company also expanded its reposit…
An unnamed company accidentally spent $500 million on Claude AI tokens in a single month due to unregulated usage limits, prompting firms to reconsider AI productivity gains. Meanwhile, token-burning …
The Miasma software supply chain attack toolkit has been released as open source across multiple GitHub repositories, likely through compromised developer accounts. The toolkit enables attackers to ex…
A new study from MIT and Wharton researchers Mert Demirer, Leon Musolff, and Liyuan Yang reveals that AI coding tools dramatically boost task-level velocity but produce far smaller gains in actual shi…
Anthropic's Fable 5 model has been suspended for all users following a U.S. government directive, but early tests show it excels at autonomous coding tasks with vague prompts, though it is expensive a…
The third AI Shoulder Surf meeting on May 28, 2026, featured participants using Tailscale to securely access private home labs. Olaf built a triathlon training plan with Claude and hosted it on his Ta…