Skip to content
View kanson1996's full-sized avatar
:octocat:
Focusing
:octocat:
Focusing
32 followers · 268 following

Achievements

Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Arctic Code Vault Contributor

Organizations

@LiveSecBench

Block or report kanson1996

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
kanson1996/README.md

Hi there 👋

  • 🏫 I'm a bachelor of engineering of NEU, majored in CS(2014-2018). After graduation, I engaged in the system development of capital credit-granting, social-network recommendation and voice-activated assistant etc.
  • 🌱 At the Xiaomi AI Team (2020-2023), I worked on backend development for the XiaoAI assistant. My responsibilities were focused on the R&D of systems including the speech evaluation system and the open platform.
  • 🔭 I'm currently a Software Engineer at Intoken Tech Ltd. in the AI safety industry(2023.12-so far), focusing on the evaluation of large language models and full-stack development. I also maintain a strong interest in Site Reliability Engineering (SRE).
  • 😄 I maintain a strong focus on cutting-edge developments within the AI field, including AI-Native Applications, AI Agents, and multimodal fusion models.
  • 💬 Contact me by email.

Github Stats

Github Stats

Pinned Loading

  1. agent-audit-trail agent-audit-trail Public

    🔍 面向 AI Agent 的防篡改审计溯源系统 | Tamper-evident audit trail for AI Agents — generates hash-chained JSONL logs to answer: what did the agent do, how did it decide, and was anything altered? Framework-agno…

    TypeScript 1

  2. LiveSecBench/livesecbench.github.io LiveSecBench/livesecbench.github.io Public

    LiveSecBench（大模型动态安全测评基准）是大模型安全领域的专业、动态、多维度测评基准。我们致力于通过科学、系统、持续演进的测评体系，客观评估与衡量大模型的安全性能，推动大模型技术向更安全、更可靠、更负责任的方向发展，为产业落地和学术研究提供关键的安全标尺。

    2

  3. LiveSecBench LiveSecBench Public

    Forked from ydli-ai/LiveSecBench

    LiveSecBench，面向中文场景的大模型安全评测基准。框架结合动态题库、模型对战与客观评分流程，可在伦理、合法性、事实性、隐私、对抗鲁棒与推理安全等核心维度持续追踪模型表现。

    Python 1

  4. pebble-agent pebble-agent Public

    Python 4

  5. Langchain-Chatchat Langchain-Chatchat Public

    Forked from chatchat-space/Langchain-Chatchat

    Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain

    Python

  6. TencentPretrain TencentPretrain Public

    Forked from Tencent/TencentPretrain

    Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo

    Python 1