Hacker News: jensb1

New comment by jensb1 in "GLM Built Its Own Inference Infrastructure"

jensb1 — Thu, 17 Sep 2026 10:20:30 +0000

What is "illegal" about it?

New comment by jensb1 in "Ask HN: Is it just me or is Claude Code getting worse?"

jensb1 — Fri, 01 May 2026 10:50:37 +0000

Not more stupid IMO, but significnatly less token efficient or they have decreased tokens for subscription users, difficult to know.

Claude Code driver using PTY (proof of concept)

jensb1 — Sun, 08 Mar 2026 14:05:26 +0000

Article URL: https://github.com/jensb1/jensagent

Comments URL: https://news.ycombinator.com/item?id=47297416

Points: 1

# Comments: 0

New comment by jensb1 in "Toy Lisp compiler using LLVM done with AI in 8hrs"

jensb1 — Mon, 17 Mar 2025 17:02:09 +0000

Hi, always wanted to create a toy lisp compiler in LLVM for some reason, but never had the time to get it working.

Took a new stab at it with Claude 3.7. Got a working version up in less than 8hrs in total with passing tests! Never wrote a single line of code. I would estimate the number of cursor iterations to about 500.

Process was: 1. Ask Claude to create a boiler plate JIT in LLVM (see below shared chat) 2. Asked Claude on the architecture and what classes should be created (did this in cursor): - lexer - parser - AST - Code gen 3. Implemented each part separately, lexer, parser and AST took 1hr, codegen took ~7hrs.

It can define variables, functions and do some basic stuff: try: (defn factorial [n] (if (= n 0) 1 (* n (factorial (- n 1))))) (factorial 5)

Hope you like it!

Here are some chats if you are interested in the first part of the coding (the rest was done in cursor):

LLVM - https://claude.ai/share/3c5a1f92-389f-4274-8348-dcceaee8f140

Lexer - https://claude.ai/share/fa32b8bd-0b8e-4faa-bc09-fc3dd9bb5ad3

Toy Lisp compiler using LLVM done with AI in 8hrs

jensb1 — Mon, 17 Mar 2025 17:02:09 +0000

Article URL: https://github.com/jensb1/lisp_llvm

Comments URL: https://news.ycombinator.com/item?id=43390521

Points: 1

# Comments: 1

New comment by jensb1 in "Exllamav2: Inference library for running LLMs locally on consumer-class GPUs"

jensb1 — Wed, 13 Sep 2023 09:43:27 +0000

typo

New comment by jensb1 in "Exllamav2: Inference library for running LLMs locally on consumer-class GPUs"

jensb1 — Wed, 13 Sep 2023 09:09:44 +0000

Could someone explain how token generation speed relates to latency for the first token to be outputted?

And if anyone have any metrics on latency on a 4090 for the 70B model, that would be very helpful.