News
Anthropic: Claude Writes Over 80% of Its Own Code — and Calls for a Pause Button
Anthropic discloses the numbers: Claude writes >80% of its production code. At the same time, the company argues for the option to pause frontier development.
KI-Konzepte
Grundbegriffe und Mechanik moderner Sprachmodelle und KI-Workflows.
News
Anthropic Threat Report: AI-Using Hackers Rise From 33 to 56 Percent
Anthropic's first major threat report: the share of high-risk actors using AI nearly doubled. Plus one largely autonomous agent attack.
News
The Ralph Loop Goes Mainstream in 2026 — and Brings a Token-Burn Problem
Autonomous coding agents in an endless loop: what Ralph Loop and Loop Engineering really are — and why the bill explodes without hard stops.
News
Token Tsunamis: why agentic AI systems blow up your costs
2026 industry data: agentic AI burns 5–30x more tokens than a chat. What that means for multi-agent budgets.
News
A2A Protocol After One Year: 150+ Organizations, In Every Major Cloud, First Stable Spec
At its one-year mark the A2A protocol counts 150+ organizations, ships in every major cloud, and reaches its first stable 1.0 spec for agent interop.
News
Agent Orchestration 2026: LangGraph Becomes the Default, Microsoft Consolidates Onto One Framework
LangGraph overtakes CrewAI in stars, Microsoft Agent Framework 1.0 is GA. The framework market is reordering — what that means for your choice.
Blog
AI Workflows by Keyword: How We Make Recurring Routines Enforceable
A typed keyword triggers a fixed AI routine — and every single step must be committed before the next one appears. Why that's the actual trick.
Blog
Multi-AI Orchestration Without API Costs: Why Your Existing Subscription Is Enough
Headless agents on your own machine, fed by the subscription you already pay for instead of an API bill — how boostN orchestrates many models.
Blog
Why AI Models Find Different Code Problems
Three frontier models, the same 1000-line script, three different finding lists — and why that very spread makes multi-orchestration strong.
Blog
The AI does whatever it wants — and no CLAUDE.md, no memory, no rule on earth will stop it
You write rules, curate memories, build guidelines — and a week later you're going in circles again. Why that is, and what actually helps.
Blog
Effort level and deep thinking: two independent axes for AI tasks
Effort scales breadth, deep thinking scales depth. When each setting makes sense — with three clear examples and one rule of thumb.
Function Calling / Tool Use LLM Hallucinations — Causes and Remedies Measuring LLM Quality — Evals, Benchmarks, Judges Working with the LLM API — Streaming, Caching, Rate Limits RAG Tuning and Balancing — Embeddings, Weights, Decay and MCP for Advanced Setups Tokens and Tokenization in LLMs Explained Embeddings Simply Explained Fine-Tuning Explained — When, How, With What Building AI Agents — From Tool Use to Multi-Agent Systems The Context Window of LLMs — What Fits and What Doesn't Running LLMs locally — hardware, tools, models Prompt Security — Injection, Leaking, Guardrails Understanding RAG — From Idea to Production System Prompting Techniques — An Overview Temperature, Top-p and Sampling in LLMs
Ensemble / Multi-Model Orchestration Attention Mechanism Reasoning Effort Recall Sampling (LLM) Thinking Budget Automatic Speech Recognition (ASR) $/MTok (Cost per Million Tokens) Input Token Output Token Path Dependency (LLM Output) Whisper Agentic RAG AI Agent Audio normalization AutoGPT Batch API Benchmark (AI) Browser Use Chain-of-Thought Chunking Computer Use Constitutional AI Context Engineering Context Precision Context Recall Context window Contextual Retrieval Cosine Similarity dBFS, Headroom & Clipping DPO (Direct Preference Optimization) Embedding Evals Faithfulness Few-Shot Prompting Fine-Tuning Function Calling GGUF GraphRAG Guardrails Hallucination Hybrid Search HyDE Indirect Prompt Injection Inference Jailbreak Keyword Glossary (STT) KV Cache LLM LLM-as-a-Judge LoRA MCP Meta-Prompting PEFT (Parameter-Efficient Fine-Tuning) Prompt Caching Prompt engineering Prompt Injection Prompt Leaking Prompt Template QLoRA Quantization Query Expansion RAG RAGAS Rate Limit (AI) ReAct (Prompting) Reranking RLHF Role Prompting Self-Consistency Self-Refine Semantic Search SFT (Supervised Fine-Tuning) Spotlighting Stop Sequences Structured Output / JSON Mode Synthetic Data System Prompt Temperature Tier Pricing Token Tokenizer Tool Call Top-p / Top-k TPM/RPM Tree of Thoughts Vector Database VRAM Whisper initial_prompt XML tags in the prompt Adapter (PEFT) Batch Inference Catastrophic Forgetting Continued Pretraining Instruction Tuning Knowledge Distillation Model Card ORPO (Odds Ratio Preference Optimization) Prefix Tuning Safetensors Streaming (LLM) Zero-Shot