Hacker News: tylermarques

New comment by tylermarques in "Open Code Review – An AI-powered code review CLI tool"

tylermarques — Fri, 05 Jun 2026 16:42:38 +0000

There is some evidence.[1] The best reviewer is a different model with fresh context, worst is same model with same context.

1. https://arxiv.org/pdf/2603.04582

New comment by tylermarques in "Training a trillion parameter model to be funny"

tylermarques — Tue, 03 Feb 2026 05:47:58 +0000

In the same vein, we recently released a version v0.1 of our humor benchmark. [1] We use human answers from a cards against humanity style game call Bad Cards [2] as ground truth for what is funny. The models get to choose a card from a hand of 3-6 cards, so not quite de novo joke creation.

[1] https://goodstartlabs.com/leaderboards/lol-arena

[2] https://bad.cards/

IPv6 Based Canvas

tylermarques — Sun, 20 Jul 2025 22:29:04 +0000

Article URL: https://canvas.openbased.org/

Comments URL: https://news.ycombinator.com/item?id=44629962

Points: 91

# Comments: 25

New comment by tylermarques in "Show HN: AI Playing Diplomacy"

tylermarques — Mon, 09 Jun 2025 22:21:52 +0000

Sorry about that! We've toned down the music a bit, trying to put more emphasis on the narrator. Thanks for the feedback :)

We're hoping to create more like this! :)

Show HN: AI Playing Diplomacy

tylermarques — Thu, 05 Jun 2025 17:26:53 +0000

Hi HN!

Myself and a friend launched this today. It's LLMs playing the classic board game of Diplomacy. The game focuses heavily on collaboration between players, and makes an interesting test bed for seeing how LLMs interact with each other and when they are or aren't willing to lie to other players.

You can find the code for the stream here https://github.com/EveryInc/AI_Diplomacy

We've seen some interesting "personalities" emerge in the models. Claude often refuses to lie to anyone, ally or otherwise. O3 has no problem with lying.

Heres a writeup of it as well!

https://every.to/p/diplomacy

Let us know what you think :)

Comments URL: https://news.ycombinator.com/item?id=44193786

Points: 2

# Comments: 2