Skip to content
View Le0nX's full-sized avatar
⚠️
Open to R&D roles and collaboration in AI agent safety & evaluation
⚠️
Open to R&D roles and collaboration in AI agent safety & evaluation
53 followers · 1 following

Achievements

Achievement: Pair Extraordinairex3Achievement: Starstruckx3Achievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair Extraordinairex3Achievement: Starstruckx3Achievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Highlights

Block or report Le0nX

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Le0nX/README.md

Reliability, Verification & Safety of AI Agents

After ~9 years building safety-critical systems - triple-modular-redundancy UAV avionics, regulated medical-device SDKs, secure banking - I now apply that reliability discipline to AI agents, at the point where a model's output becomes a consequential action (send, pay, modify, disclose, tool call.

Background: 10+ yrs senior software engineer (systems, backend, iOS).

nefedov.d.d@gmail.com · LinkedIn · Telegram @nfdvd

Author of ModernRoboticsCpp — 500+ ★.

Pinned Loading

  1. inspect_evals inspect_evals Public

    Forked from UKGovernmentBEIS/inspect_evals

    Collection of evals for Inspect AI

    Python

  2. ModernRoboticsCpp ModernRoboticsCpp Public

    Modern Robotics: Mechanics, Planning, and Control C++ Library --- The primary purpose of the provided software is to be easy to read and educational, reinforcing the concepts in the book. The code …

    C++ 544 164