# Everett Kleven

> Engineer and founder working on AI-native simulation: typed world state,
> replayable execution, and evidence that outlives the run. Creator of
> Archetype at Vangelis Technologies. Also: Physical AI and robotics.

Full content as markdown: https://everettkleven.dev/index.md

## Projects
- [Archetype](https://github.com/VangelisTech/archetype): An AI-native ECS simulation engine: Pydantic's composability for typed components, Daft dataframes for distributed processing, and Iceberg for multi-modal storage. Entities are rows, systems are transformations, and world state is a table you can query after the fact.
- [world-examples](https://github.com/VangelisTech/world-examples): Minimal component, prefab, system, and graph composition examples for Archetype — the smallest working thing for each concept, so the engine can be learned by reading one file at a time.
- [awesome-physical-ai](https://github.com/everettVT/awesome-physical-ai): A curated list of open-source projects for Physical AI — robotics, embodied intelligence, simulation, and the infrastructure that makes it work.
- [sessionscope](https://github.com/everettVT/sessionscope): See how you actually work. A privacy-first browser analyzer for Claude Code, Codex, and ChatGPT session files — zero upload, runs entirely offline.
- [gepa](https://github.com/everettVT/gepa): Optimizing prompts, code, and more with reflective text evolution — treating the artifact under improvement as something a model can critique and rewrite against a measurable objective.

## Talks
- [Fever Dreams: Working With and Against AI Sycophancy](/#talks) (Nerds Like Me — Chicago, 2025-07-24): Why an assistant's agreeableness is a failure mode rather than a courtesy. The talk walks the good (the barrier to shipping software has collapsed), the bad (human-feedback finetuning that rewards flattery over truth), and the ugly (the GPT-4o sycophancy episode and so-called "ChatGPT psychosis") — then lands on Narcissus as the mental model: a reflection you cannot pull away from, even as it costs you. Position: LLMs are mirrors, not oracles, and every output is arbitrary until vetted.
- [How 2 Engineers Rebuilt a $2M Platform in 2 Months with AI Agents](https://www.youtube.com/watch?v=wbjQS_eqEco) (Rally SF, 2026-04-13): The series' first full case study: two engineers replace a $2M platform in two months of agent-driven work. Concrete on the parts that usually get waved at — how the work was specified, split into reviewable pull requests, and gated on tests rather than vibes.
- [Claude Code and Beyond: 4 Real Agentic Coding Workflows](https://www.youtube.com/watch?v=1ChmzWNLAK0) (Rally SF, 2026-06-07): Four builders walk through the workflow they genuinely use, end to end. The recurring threads: writing specs an agent can execute, keeping pull requests small enough that a human can still review them, and where token budgets stop being a detail and start dictating architecture.
- [Claude Code and Beyond: State of the Art Agentic Coding Workflows](https://www.youtube.com/watch?v=H2JQR1-oAhg) (Rally SF, 2026-06-23): The fourth installment, and the longest. Skills dominated — how builders package repeatable procedure so an agent can be trusted with it — alongside review discipline, evals, and the first real comparisons across Claude Code, Codex, and Fable.
- [Claude Code in the Wild: 3 Builder Demos (+ Fable 5)](https://www.youtube.com/watch?v=yqKZo6kmjrs) (Rally SF, 2026-06-28): Three builders demo what they actually ship with, plus a first look at Fable 5. Orchestration and harness design carried the night: how much context an agent needs to act usefully, and how to keep the loop verifiable once it does.

## Contact
- Email: ekleven@vangelis.tech
- GitHub: https://github.com/everettVT
- X: https://x.com/everettkleven
- LinkedIn: https://www.linkedin.com/in/everett-kleven