Anthropic has introduced Claude Mythos, a new model class positioned above its existing Opus tier, currently in a limited preview restricted to cybersecurity professionals and researchers. The control…
Anthropic released Claude Opus 4.8, a point update to its highest-capability model family, with targeted improvements in honesty calibration and agentic judgment for long-running autonomous tasks. The…
Anthropic released the system prompt for Claude Opus 4.8, revealing strict behavioral rules including a mandate that Claude must never use `<antml:voice_note>` blocks and must proactively search the w…
Auto-itera, an autonomous experimentation engine, now automates AI engineering decisions by running controlled experiments on real production data. Users define a goal, provide candidate arms, and set…
The AI Village agents raised only $510 for charity this year despite being significantly more capable than last year, when they raised $2,000. The drop occurred because humans were less engaged with t…
A new empirical study found that layering three retrieval methods—typed discovery, semantic context, and file verification—achieved a 0.954 score for LLM-generated engineering artifacts, outperforming…
A developer built an open-architecture Credit Optimizer that reduces AI agent costs by 30-75% by analyzing task complexity before routing to the appropriate model tier. The system scores tasks on a 1-…
A developer expanded their AI-agent security benchmark from 10 to 16 scenarios, revealing that Claude Code Sonnet 4.6 scores +9 out of 16 while Haiku 4.5 scores only +3. The original tie between the t…
On April 17, a developer took their AI agent offline after suspecting a compromise, only to discover four days later that the agent had poisoned its own memory with hallucinated information. The agent…
A developer built a local Python CLI tool called `ai-cost-optimizer` that reduced their Anthropic API bill by 50% by implementing a semantic cache, prompt compressor, and model router. The tool interc…
The article describes Forgekeel, an open-source methodology that prevents Claude Code from writing code until a ticket scores at least 80/100 on a six-dimensional quality gate called KERNEL. The syste…
The Claude Max plan primarily differs from Pro by making Opus 4.6 the default model (instead of Sonnet) and automatically providing a 1 million token context window without additional charges. While m…
A friend's startup was spending $4,200/month on the Claude API, but an audit revealed that $2,900 of that was waste caused by three common mistakes. The fixes included enabling prompt caching (saving …
A Rust crate called `llm-json-repair` created to fix common formatting issues in JSON responses from Claude AI models. The author found that 14% of 12,400 structured-output API calls to Claude Sonnet …
The author ran three Claude Code sub-agents (an explore-reviewer, security-reviewer, and plan-architect) on the same 500-line pull request and found that the agents disagreed on 41% of their 78 total …
Firetiger used an AI agent to optimize LLM prompt cache TTLs in production, reducing waste by 77% over several weeks by hill-climbing against telemetry and cost data. The agent autonomously measured s…
Anthropic resolved elevated error rates on requests to Claude Opus 4.6 and Sonnet 4.6 models on May 15, after identifying and addressing the issue that began around midnight UTC. The company confirmed…
OpenAI's Codex CLI and Anthropic's Claude Code are terminal-based AI coding agents built on different models, with Claude Code excelling at deep reasoning for complex refactoring and ambiguous require…