Sitelet https://github.com/leungll
Skip to content
View leungll's full-sized avatar

Organizations

@NENU-ST2020-TEAM

Block or report leungll

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.

Content in all repositories owned by your account will be closed.
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
leungll/README.md

About Me

  • Software Engineer at TikTok, building distributed backend systems and platform infrastructure for modern AI systems.
  • Earned a Master's degree in Software Engineering from Carnegie Mellon University, where I worked with Prof. Leonardo Sousa in the Distributed Systems Research Group.
  • Interested in distributed systems, cloud-native infrastructure, and runtime infrastructure for long-running, stateful AI workflows.
  • I enjoy building open-source software and sharing what I learn through technical writing.

Links


AI Code Time

I'm a Night 🦉

🌞 Morning                410 commits         ⣿⣿⣿⣿⣿⣿⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀   23.06 % 
🌆 Daytime                198 commits         ⣿⣿⣿⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀   11.14 % 
🌃 Evening                800 commits         ⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀   44.99 % 
🌙 Night                  370 commits         ⣿⣿⣿⣿⣿⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀   20.81 % 

🤖 AI Coding This Week

⏱ AI Coding Time: 8 hrs 58 mins (97.76%)

✍️ 7,306 lines written by AI, 8 lines written by hand (99.89% AI-written)

🔤 3,312,237 Input Tokens, 953,292 Output Tokens

💵 $57.15 Estimated AI Cost This Week

🧠 8 AI Sessions, 178 AI Prompts

Opus                     7,313 lines         ⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿   100.00 % 

🔎 AI Coding Insights:
🤖 AI-Driven — 99.89% of written lines came from AI
📚 Verbose Prompter — average 3,111 characters per prompt
🔁 Iterative Prompter — average 22 prompts per session
🚀 High AI Trust — 0.16% of changed lines were hand-edited

Metrics

Pinned Loading

  1. Emberling Emberling Public

    Agents are becoming a new class of cloud workload. Emberling is the durable execution runtime for them: every decision and action becomes a durable fact, so long-running agents can recover safely a…

    Go 1

  2. FrontierSignal FrontierSignal Public

    An AI engineering radar for frontier research, tools, and systems - filtering, ranking, summarizing, and delivering the updates that matter every day.

    Python 2

  3. NENU-Courses NENU-Courses Public

    Guidance for courses in School of Information Science and Technology, NENU

    HTML 21 9

  4. ByteDance-Letter-Template ByteDance-Letter-Template Public

    Made with LaTex. ByteDance's recommendation letter template. In addition, you can adapt it into a recommendation letter template for other companies, such as Tencent, Alibaba, Pinduoduo, Meituan, etc.

    TeX 20