Can you catch an AI lying by reading its private thoughts?

I'm a backend and fintech engineer with six years building reliability-critical systems — payment rails, cross-border settlement, agentic trading. Alongside that, I do independent research on AI safety: how large language models deceive, how well deception can be detected, and whether a model's private reasoning can be monitored to catch it. I released this as DeceptionBench, a live cross-play benchmark over six frontier models. Currently an MSc student in Applied IT at Ural Federal University.

Featured research
DeceptionBench — “Among LLMs”

A monitor reading only a model's private reasoning catches the liar — across six frontier models, in a live cross-play benchmark.

ρ = 0.89deception ↔ detection
AUROC 1.00monitor accuracy
96%intent leaks in reasoning

Recent


  • 2026Released DeceptionBench, a cross-play benchmark for LLM deception & monitorability, as a preprint on Zenodo.
  • 2026Joined Figo as founding engineer — core backend for a cross-border neobank.
  • 2025Began MSc in Applied IT at Ural Federal University.

Publications


  1. [1]
  2. [2]
    Discrete Event Simulation of a Municipal Meat Production System: Bottleneck Analysis and Optimization
    Evans Eburu, Daniel M. Balungu
    Sustainable Innovative Development: Design & Management · 2026 · RSCI (eLIBRARY.ru)

Writing


Selected projects


  • Multicash — multi-currency wallet on tbDEX
    nuxtweb5tbdex
    2024
  • Deg X — cross-chain non-custodial DeFi wallet
    web3pythonmulti-chain
    2023

Experience


  • Founding Engineer — Figo
    cross-border neobank · stablecoin rails, card issuing
    2026 — now
  • Founder / Lead Engineer — Jevan Studio
    product & engineering
    2026 — now
  • Founding Engineer — Autospend
    stablecoin infra · agentic trading system
    2025 — now
  • Senior Backend Engineer — Bento
    Nigeria's leading payroll platform
    2020 — 2024