Overview
News
Salaries
Products
People
Growth
Offices
Financials

Overview

Hi, I am Sankalp. I go by dejavucoder on X. I am into AI engineering and applied LLM research.

News

Blog 1 month ago
songs with immaculate vibes only
svg viewBox="0 0 24 24" width="22" height="22" fill="none" stroke="currentColor" stroke-width="1.7" stroke-linecap="round" ...
Read more
Report
Blog 2 months ago
kpop videos that go insanely hard
.vibe-header { text-align: center; padding: 20px 0 8px; } .vibe-header h2 { font-size: 1.4em; font-weight: 300; letter-spacing: 3px; text-transform: lowercase; color: #444; margin: 0 0 4px; } .vibe-header .song-count { font-size: 12px; color: #777; letter
Read more
Report
Blog 3 months ago
Auto-research with codex: How I achieved a 232x Faster Kernel over baseline with Codex in GPU Mode's qr_v2 problem
Table of Contents Intro Contest in short Problem intro Why this problem is auto-research-able Learning Enough to Ask Better Questions (Optional) ...
Read more
Report
Blog 4 months ago
one must imagine sisyphus full of ideas: on exercising the idea muscle
Lore It was mid-May. I was a couple of weeks into catching up on post-training literature and learning reinforcement learning for LLMs in a more bottom-up way. Having done some basic experiments, I was unable to come up with an idea that had the allure to
Read more
Report
Blog 4 months ago
To-loop or not loop: figuring out the context behind agent usage and automation patterns
There was a lot of discourse around Peter's recent tweet. I think the main driver behind this was most people not taking the time to think about Peter's context before comparing it with their own. In this post, I will talk about this "context". Here's you
Read more
Report
Blog 4 months ago
From SGD to Muon: An Incremental Tutorial (Fable-5 vs Opus 4.8)
Fable-5 High You can find Opus 4.8 output after this. From SGD to Muon: An Incremental Tutorial This tutorial builds up to the Muon optimizer one idea at a time. Each section adds exactly one concept on top of the previous one, so by the time we reach Muo
Read more
Report
Blog 9 months ago
Ideas to grow on X the everything app (formerly Twitter)
Practical ideas on growing on Twitter from 4+ years of regular posting and observing the timeline.
Read more
Report
Blog 10 months ago
A Guide to Claude Code 2.0 and getting better at using coding agents
A deep dive into Claude Code 2.0 features, Opus 4.5 workflows, and context engineering. Learn sub-agents, MCP servers, hooks, skills, and practical tips to boost your AI-assisted coding productivity.
Read more
Report
News sankalp's blog 10 months ago
How prompt caching works - Paged Attention and Automatic Prefix Caching plus practical tips
A deep dive into prompt caching - practical tips to improve cache hits and how vLLM's paged attention enables KV-cache reuse across requests via automatic prefix-caching
Read more
Report
News sankalp's blog 1 year ago
Can LLMs dream of Electric Sheep?
I forgot to cancel my Midjourney v7 subscription last month. I love Midjourney, amazing model and great product. I have been short on ideas and, honestly, co...
Read more
Report
Show more news