I think friction is a feature. If you can pump out 100k words an hour and keep millions of lines in context at all times there is no driving force to abstract, to simplify, to discover new ways of doing things? I think because my brain context is so tiny I've always been very good at simplifying, finding the structure that makes me not have to remember exceptions and ifs everywhere. If you don't have that problem then there is no force pushing you to discover better ways. I do use LLMs at work and for some personal projects that I want to explore. But the more I work with them, the more I see how important friction is.

Little preview of something I've been working on! You can connect to any provider, or through any harness like Hermes Agent, and the setup is instant with no configuration required, unless you want to. Proactive, self-aware, and will be fully open source

90% of AI Engineer interviews in 2026 are just these 15 concepts repeated: 1/ Transformers & LLM Fundamentals: how LLMs predict the next token, self-attention, multi-head attention, positional encoding, and why transformers replaced RNNs 2/ Tokenization & Embeddings: BPE, how text becomes tokens, and how vectors capture meaning 3/ Prompt Engineering: system prompts, few-shot learning, chain-of-thought, and structured outputs (JSON/schema) 4/ RAG: chunking strategies, retrieval, context injection, context windows, and why RAG beats fine-tuning for fresh data 5/ Vector DBs & Search: vector databases, semantic search, hybrid search , reranking, and HNSW indexes 6/ Function Calling, Tool Calling & MCP: how LLMs trigger APIs, code and databases, and the standard protocol for connecting them 7/ AI Agents & Agentic Workflows: plan, act and observe loops, orchestrated multi-step pipelines, and AI coding agents 8/ Memory & Multi-Agent Systems: short-term and long-term memory, and specialized agents collaborating on a task 9/ Fine-Tuning: full fine-tuning, LoRA, QLoRA, PEFT, and when to fine-tune vs prompt vs RAG 10/ Alignment & Distillation: RLHF, DPO, and knowledge distillation (big model teaches small model) 11/ Quantization & Model Compression: INT8/INT4, pruning, sparsity, and the quality vs speed vs cost tradeoff 12/ Inference & Serving: prefill vs decode, KV cache, speculative decoding, LLM serving, vLLM, batching, and model routing 13/ Multimodal AI & Vision-Language Models: text, image, audio and video in one system, and models that see and reason about images 14/ Evals & Hallucination Detection: LLM evaluation, LLM-as-judge, prompt evaluation, and catching confident but wrong answers 15/ Safety, Observability & Production: guardrails, AI safety, prompt injection, tracing, cost optimization, and production GenAI systems Know these 15 deeply and you can crack most AI engineer interviews

I asked Claude Code to make a new GTA: San Andreas mission where CJ has to vibe code a startup and then raise money from investors in SF

@flohoeller's idea, built the same afternoon. open any task, see the full lineage: root to every descendant, who started whom, status and duration per task. fan-outs collapse, tested at 150. experimental, PR up: github.com/desplega-ai/agent…