Top all-time · #11740
Shlok Khemani
Personal blog · shloked.com/writingaiprogrammingwriting
Shlok Khemani's personal blog at shloked.com covers ai, programming and writing. Since 2025, 6 different Hacker News readers have linked it 7 times. It is still writing: the last post was on 2026-08-04, and you can follow it by feed.
Too few sampled comments (3) to say how often HN recommends it.?
Why HN links it
HN readers link Shlok Khemani's writing on how ChatGPT and Claude implement memory, including a breakdown of ChatGPT's memory system framed around the bitter lesson.
Summarised by Claude from a sample of 3 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Writer and programmer based out of Mumbai, India. Writing about technology, startups, and life. Photography and hiking enthusiast.
Most-linked posts?
- /writing/chatgpt-memory-bitter-lesson3 people · 3 mentions · first linked 2025-09-11
What Hacker News says?
https://www.shloked.com/writing/chatgpt-memory-bitter-lesson Mb something 've changed since post
Comment linking /writing/chatgpt-memory-bitter-lesson
on “GPT-5.2”Submitted Claude’s memory architecture is the opposite of ChatGPT’s as a story · 448 points
HN discussionRegarding https://www.shloked.com/writing/chatgpt-memory-bitter-lesson I am very confused if the author thinks the ChatGPT is injecting those prompts when the memory is not enabled. If your memory is not enabled, its pretty clear at least in my instance, there is no metadata of recent conversations or personal preferences injected. The conversation stays stand-alone for that conversation only. If he was turning memo…
Comment linking /writing/chatgpt-memory-bitter-lesson
on “Claude’s memory architecture is the opposite of ChatGPT’s”Submitted Seven Weeks in San Francisco as a story · 6 points
HN discussionThe link to the breakdown of ChatGPT's memory implementation is broken, the correct link is: https://www.shloked.com/writing/chatgpt-memory-bitter-lesson This is really cool, I was wondering how memory had been implemented in ChatGPT. Very interesting to see the completely different approaches. It seems to me like Claude's is better suited for solving technical tasks while ChatGPT's is more suited to improving casua…
Comment linking /writing/chatgpt-memory-bitter-lesson
on “Claude’s memory architecture is the opposite of ChatGPT’s”Submitted Google Has Your Data. Gemini Barely Uses It as a story · 2 points
HN discussionSubmitted OpenPoke: Recreating Poke's Architecture as a story · 1 points
HN discussion