Chengchang Yu

Posts tagged "learning"

Published on
January 23, 2026
📝 Prompt Repetition Improves Non-Reasoning LLMs
LLM Paper learning
I recently came across a surprisingly effective prompt technique and the results are wild.
Published on
January 5, 2026
📝 Recursive Language Models：Breaking Free from Context Window Constraints
LLM Paper learning
The Beauty of Simple Recursion
Published on
December 21, 2025
System design for a Global Distributed Cache
AWS Cache System-Design Architecture learning
Design a cache. We had to clarify all requirements surrounding this . It’s a global cache for a distributed database with 100 billion records and each cache holds key value records so based on that do the sizing , distribution , latencies , read heavy, etc. Discuss all issues like replication, crashing of cache servers, cache warm up , TTL etc proactively.
Published on
December 16, 2025
📝 AI Search Paradigm：When Search Engines Learn to Think
LLM Paper learning
The world's information is scattered, but our search tools remain **single-threaded and passive**.
Published on
December 10, 2025
📝 Deep Analysis：The Internal Logic of LLM Safety Mechanisms
LLM Paper learning
How do LLM safety alignment and jailbreak attacks actually work? Why can aligned models still be jailbroken to bypass safety guardrails? What's really happening inside these black-box models?
Published on
December 3, 2025
📝 DeepSeek-V3.2：The Open-Source AI That Rivals GPT-5
LLM Paper learning
How a Chinese lab built frontier AI capabilities at a fraction of the cosy.

Posts tagged "learning"

📝 Prompt Repetition Improves Non-Reasoning LLMs

📝 Recursive Language Models：Breaking Free from Context Window Constraints

System design for a Global Distributed Cache

📝 AI Search Paradigm：When Search Engines Learn to Think

📝 Deep Analysis：The Internal Logic of LLM Safety Mechanisms

📝 DeepSeek-V3.2：The Open-Source AI That Rivals GPT-5