Hacker News: animan

New comment by animan in "Does the Sumerian King List Align with Paleoclimate Events?"

animan — Sat, 29 Aug 2026 01:12:20 +0000

This was fun to read! I wish there was a no tech version of hackers news for this type of content only

New comment by animan in "Show HN: Are You in the Weights?"

animan — Fri, 19 Jun 2026 00:54:10 +0000

Hi Satoshi

New comment by animan in "Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed"

animan — Thu, 12 Feb 2026 14:19:54 +0000

What was the point of Claude code or Gemini banning the OP? Why would they care about how IDEs use the underlying API?

New comment by animan in "Life of an inference request (vLLM V1): How LLMs are served efficiently at scale"

animan — Sun, 29 Jun 2025 00:11:50 +0000

That snippet is trying to say that you can calculate KV for all the input tokens at once, and you don't need to loop over them since you have them all available.

Instead for decode, you need to sequentially generate each token.

New comment by animan in "Life of an inference request (vLLM V1): How LLMs are served efficiently at scale"

animan — Sun, 29 Jun 2025 00:10:29 +0000

Prefill is part of Inference. It's the first major step where you calculate all the keys and values for the input tokens.

Decode is the next major step where you start generating output tokens one at a time.

Both run on GPUs but have slightly different workloads

1. Prefill has very little I/o from VRAM to HBM and more compute 2. Decode is light on compute but have to I/o the keys and values computed in the prefill stage for every output token

New comment by animan in "CrowdStrike Bug likely caused by unsafe NULL Pointer"

animan — Sat, 20 Jul 2024 00:49:59 +0000

One of us, one of us...