---
title: "Aditya Raj (@Astrobot) | Hashnode"
description: "Aditya Raj (@Astrobot) writes on Hashnode. Read their latest articles and follow their work."
url: "https://hashnode.com/@Astrobot"
---

@Astrobot

# Aditya Raj

@Astrobot · Joined February 2024

### [Server Sent Events(SSE): The Backbone of LLM Token Streaming](https://blog.astrobot.tech/server-sent-events-sse-the-backbone-of-llm-token-streaming?utm_source=hashnode&utm_medium=feed)

from scratch to production. Covers Express setup, consuming events, CORS, and how LLMs like Claude and GPT use SSE to stream tokens in real time.

18 min read · [blog.astrobot.tech](https://blog.astrobot.tech/server-sent-events-sse-the-backbone-of-llm-token-streaming?utm_source=hashnode&utm_medium=feed)

[Jun 14](https://hashnode.com/posts/server-sent-events-sse-the-backbone-of-llm-token-streaming/6a2e9787743ce7fdd7c94811)

### [Paper Summary: SWE-BENCH CAN LANGUAGE MODELS RESOLVE REAL-WORLD GITHUB ISSUES?](https://blog.astrobot.tech/paper-summary-swe-bench-can-language-models-resolve-real-world-github-issues?utm_source=hashnode&utm_medium=feed)

Here's a full deep-dive on the SWE-bench paper: PAPER X-RAY ║ Title : SWE-bench: Can Language Models ║ ║ Resolve Real-World GitHub ║

12 min read · [blog.astrobot.tech](https://blog.astrobot.tech/paper-summary-swe-bench-can-language-models-resolve-real-world-github-issues?utm_source=hashnode&utm_medium=feed)

[May 10](https://hashnode.com/posts/paper-summary-swe-bench-can-language-models-resolve-real-world-github-issues/6a00e28ee3eebc2e20c3a3e0)

### [Paper Summary: SWE-agent Agent-Computer Interfaces Enable Automated Software Engineering?](https://blog.astrobot.tech/paper-summary-swe-agent-agent-computer-interfaces-enable-automated-software-engineering?utm_source=hashnode&utm_medium=feed)

This is a Claude-generated summary! PAPER X-RAY ║ Title : SWE-agent: Agent-Computer ║ ║ Interfaces Enable Automated ║ ║

11 min read · [blog.astrobot.tech](https://blog.astrobot.tech/paper-summary-swe-agent-agent-computer-interfaces-enable-automated-software-engineering?utm_source=hashnode&utm_medium=feed)

[May 10](https://hashnode.com/posts/paper-summary-swe-agent-agent-computer-interfaces-enable-automated-software-engineering/6a00e1e1e3eebc2e20c34cb5)

### [Recursive Language Models (RLMs)](https://blog.astrobot.tech/recursive-language-models-rlms?utm_source=hashnode&utm_medium=feed)

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

8 min read · [blog.astrobot.tech](https://blog.astrobot.tech/recursive-language-models-rlms?utm_source=hashnode&utm_medium=feed)

[Mar 30](https://hashnode.com/posts/recursive-language-models-rlms/69cad4299fffa7474079706d)

### [What is HyDE](https://blog.astrobot.tech/what-is-hyde?utm_source=hashnode&utm_medium=feed)

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 docu

3 min read · [blog.astrobot.tech](https://blog.astrobot.tech/what-is-hyde?utm_source=hashnode&utm_medium=feed)

[Mar 24](https://hashnode.com/posts/what-is-hyde/69c21e9730a9b81e3af97de7)
