ARAditya Rajinblog.astrobot.techĀ·Jun 14 Ā· 18 min readServer Sent Events(SSE): The Backbone of LLM Token Streamingš” If you are here just to read about LLM streaming, jump to section 12 From first principles to production-grade architecture.Covers: protocol internals, Express server setup, multi-client forward00
ARAditya Rajinblog.astrobot.techĀ·May 10 Ā· 12 min readPaper Summary: SWE-BENCH CAN LANGUAGE MODELS RESOLVE REAL-WORLD GITHUB ISSUES? Here's a full deep-dive on the SWE-bench paper: PAPER X-RAY ā Title : SWE-bench: Can Language Models ā ā Resolve Real-World GitHub ā 00
ARAditya Rajinblog.astrobot.techĀ·May 10 Ā· 11 min readPaper Summary: SWE-agent Agent-Computer Interfaces Enable Automated Software Engineering? This is a Claude-generated summary! PAPER X-RAY ā Title : SWE-agent: Agent-Computer ā ā Interfaces Enable Automated ā ā 00
ARAditya Rajinblog.astrobot.techĀ·Mar 30 Ā· 8 min readRecursive Language Models (RLMs)Paper: Zhang, Kraska & Khattab ā MIT CSAIL, January 2026Code: github.com/alexzhang13/rlm TLDR; From first principles ā before RLMs, performance degradation over large contexts was a known issue. RLM 00
ARAditya Rajinblog.astrobot.techĀ·Mar 24 Ā· 3 min readWhat is HyDEThe core question is: what makes zero-shot retrieval fail, and what would fix it? Let me build up the intuition step by step.The root problem: A user query like "how do I fix a leaky pipe?" and a docu00
