Full-text search across 25444 articles. Combine with topic and date filters; results sorted by relevance.
A developer's benchmark of frontier AI models on a 3D modeling task found Anthropic's Opus 4.7 outperformed Gemini 3.1, GPT 5.5, and Kimi K2.6 in weighted score, speed, and cost, contradicting public leaderboards. The au…
Context rot degrades AI agent output quality when a model's context window reaches 70-80% capacity, causing attention dilution and signal-to-noise loss. Anthropic's Claude Code addresses this with an auto-compact feature…
XAI's Grok 4.5, OpenAI's GPT-5.5, and Anthropic's Claude Opus 4.8 and Fable 5 were benchmarked on one-shot app generation across three interactive tasks. Claude models won the Rubik's Cube round, GPT-5.5 won the gravity …
Google updated its Android Bench benchmark for AI agents in Android development, adding eight new models including Claude Fable 5, which leads with 84.5% accuracy. The update introduces cost and efficiency metrics, and G…
A developer released Talon, an open-source self-hosted harness for long-lived AI agents that persist beyond single-task loops. Talon supports multiple frontends (CLI, web chat, Slack) and swappable model backends (OpenAI…
A developer details how OpenRouter serves as an abstraction layer for integrating multiple LLM providers into production AI applications. By simply changing the base URL and model name, developers can switch between prov…
An evaluation of Anthropic's Sonnet 5 and Opus 4.8 models across 24 coding tasks shows Sonnet produces clearer and more intentional patches, while Opus yields simpler, more robust, and more minimal diffs. Cost varies wit…
Anthropic released Claude Sonnet 5 in June 2026, offering improved performance and lower pricing compared to the November 2025 Opus 4.5 model, with input costs dropping from $5.00 to $2.00 per million tokens. The author …
A critical bug in Anthropic's Claude Code CLI caused cross-session credential leakage, exposing another user's production server credentials to a different user. The affected user's session used the leaked credentials to…
Anthropic's Claude Agent SDK now supports plugins that bundle custom tools, subagents, hooks, and MCP servers into a single portable directory, loading with one line of config. This eliminates the need to manually wire s…
A researcher used Anthropic's Claude Code agent to implement puzzle solvers for two Kaggle competitions, IHES Picture Cube and Megaminx, reformulating them as Cayley graph searches. The agent wrote training scripts, beam…
A security researcher demonstrated a prompt injection attack on Anthropic's Claude Code using the Fable-5 model, achieving remote code execution (RCE) 4 out of 10 times by tricking the agent into downloading and executin…
Anthropic reported elevated error rates affecting requests to some models, primarily Claude Fable 5, on July 7. The company identified the issue and saw success rates return to normal, but continued monitoring to prevent…
Anthropic's Claude Code introduces two settings—model selection and effort level—that control output quality. Model selection determines fixed capabilities via trained weights, while effort level governs how many files C…
Anthropic is extending access to Claude Fable 5 on all paid plans through July 12, as announced on social media. The extension allows users more time to use the AI model.
Anthropic is rolling out Claude Cowork to mobile and web, allowing users to start tasks on one device and continue them on another, with background execution and mobile notifications for decisions. The expansion, beginni…
Anthropic's Claude Agent SDK cannot be deployed like a stateless function because it operates as a long-running process with a shell, filesystem, and untrusted input, posing data exfiltration risks. The article outlines …
Tokens are the fundamental unit of text processing in large language models (LLMs), determining API costs, response speed, and context window limits. Different providers like OpenAI, Anthropic, and Google use distinct to…
A developer created a personalized AI fitness coach using Anthropic's Claude Code, storing workout programs and logs in a git repository. The system adapts to user feedback, tracks progress, and generates exercise plans …
A developer created a workflow using Anthropic's Opus session with Fable subagent for planning and review, and Codex for code generation. The process involves writing a plan.md for each task, requiring approval before im…