Personal site, established 2026
AI safety researcher and founder.
I do AI safety research focused on scheming and deception detection in frontier language models. Currently finishing my Bachelor’s at the Faculty of Mathematics and Physics, Charles University and starting a Master’s in Artificial Intelligence in September 2026.
On the side, I’m co-founder and CTO at Zoplio — an AI scheduling primitive — with Lukáš Hellesch. We are backed by BUDETO Studio.
My direction is scheming and deception detection in frontier language models — in particular, in-context scheming behaviors of open-weight reasoning models and how those behaviors generalize across languages. I’m drawn to this work because I think rigorous evaluation of misalignment is a precondition for deploying these systems responsibly.
I’m replicating Apollo Research’s Frontier Models Are Capable of In-Context Scheming and Anthropic’s Alignment Faking Revisited on open-weight reasoning models (DeepSeek-R1, Qwen QwQ), then extending the evaluation suite to Czech and bilingual conditions to test whether scheming behaviors generalize across languages. Code, notes, and findings will be published openly.
The AI scheduling primitive: a hosted API and SDKs (Node, Python, Anthropic MCP) any application embeds to delegate meeting negotiation. I own the agent runtime — agent-to-agent negotiation protocol, confidence-scored memory across categories, LLM-driven conversation engine, WhatsApp Cloud integration, Google Calendar OAuth, Stripe usage-based billing.
Backed by BUDETO Studio (€50k seed for 10% equity).
An AI company platform co-founded with Lukáš Hellesch — autonomous AI agent teams (CEO, CTO, CMO, CFO + specialists) that plan, ship, sell, and close. Red Bull Basement ’26 Czech Republic national top 10. Wound down in 2026 to focus on Zoplio and research.
Android application for advanced Bitcoin asset management: M-of-N multisig (BIP-48, BIP-67), coin control, Trezor hardware-wallet integration via Trezor Connect, PSBT distribution between cosigners (BIP-174). Backend implemented as Kotlin/Ktor microservices on PostgreSQL with Docker Compose; frontend in Jetpack Compose. Verified on Bitcoin testnet with a complete 2-of-3 multisig transaction.
Supervised by RNDr. Filip Zavoral, Ph.D. Defence 18 Jun 2026.
Built progressively from the bottom up: console output and a bump-pointer allocator, then thread scheduling, interrupt handling, virtual memory with page-table protection, system calls, custom minimal libc, and a multi-process userspace running user-mode binaries in isolated address spaces with stack-overflow detection. Tested on the MSIM simulator with a CI suite covering every milestone.
Multi-colony foraging simulator demonstrating emergent intelligence from local rules: pheromone trails with diffusion and decay, a customisable per-colony genome, parallel multi-colony execution, and a sandbox editor for map design.
I’m happy to talk about scheming and deception detection in language models, AI safety research collaboration, Mgr supervision in this direction, or anything to do with running an early-stage AI startup.
Email — hi@kubadvorak.com
GitHub — github.com/Majny
LinkedIn — linkedin.com/in/jakubdvorak