ARAditya Rajinblog.astrobot.tech00Paper Summary: SWE-BENCH CAN LANGUAGE MODELS RESOLVE REAL-WORLD GITHUB ISSUES? May 10 · 12 min read · Here's a full deep-dive on the SWE-bench paper: PAPER X-RAY ║ Title : SWE-bench: Can Language Models ║ ║ Resolve Real-World GitHub ║ Join discussion
ARAditya Rajinblog.astrobot.tech00Paper Summary: SWE-agent Agent-Computer Interfaces Enable Automated Software Engineering? May 10 · 11 min read · This is a Claude-generated summary! PAPER X-RAY ║ Title : SWE-agent: Agent-Computer ║ ║ Interfaces Enable Automated ║ ║ Join discussion
ARAditya Rajinblog.astrobot.tech00Recursive Language Models (RLMs)Mar 30 · 8 min read · Paper: Zhang, Kraska & Khattab — MIT CSAIL, January 2026Code: github.com/alexzhang13/rlm TLDR; From first principles — before RLMs, performance degradation over large contexts was a known issue. RLM Join discussion
ARAditya Rajinblog.astrobot.tech00What is HyDEMar 24 · 3 min read · The 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 docuJoin discussion
ARAditya Rajinblog.astrobot.tech00Positional Encoding in TransformersMar 4 · 4 min read · 1. Overview Positional Encoding is a technique used in Transformer architectures to encode the order of tokens in a sequence. Transformers process tokens in parallel, unlike sequential models such as Join discussion
