News for hackers. Stuff that matters.

A comment on Fable 5.2 one-shotted my nephew's dream game. Parent comment

Re:Fable 5.2 one-shotted my nephew's dream game by Conscat on Tuesday November 10, 2026 @01:23AM (#50436767)
These agent swarms with harnesses are certainly more than just an LLM, but the LLM is certainly the integral part that delivers the most value. Without it, there is no AI.
[ Parent | on HN ]
Re:Fable 5.2 one-shotted my nephew's dream game by locknitpicker on Tuesday November 10, 2026 @01:54AM (#50436945)
> Without it, there is no AI.

With a LLM alone, all you have is a stateless chatbot. If you increase the parameters of the LLM by a few orders of magnitude, you still have a stateless chatbot.

If you start with an anaemic LLM and run it with a ReAct loop and tool-calling, you now have something you can use to do agentic coding and RAG-like capabilities.

There's a reason why relatively small open weights models are starting to perform on par and even outperform models that need a huge datacenter to run.

[ Parent | on HN ]
Re:Fable 5.2 one-shotted my nephew's dream game by spider-mario on Tuesday November 10, 2026 @04:41AM (#50438010)
They are?
[ Parent | on HN ]
Re:Fable 5.2 one-shotted my nephew's dream game by locknitpicker on Tuesday November 10, 2026 @06:05AM (#50438611)
> They are?

Yes. Feel free to check recent benchmarks from the likes of OpenRouter

[ Parent | on HN ]
Re:Fable 5.2 one-shotted my nephew's dream game by spider-mario on Tuesday November 10, 2026 @07:44AM (#50439558)
Which ones, and which models? https://openrouter.ai/benchmarks/gpqa-diamond shows Kimi K3.1 (not small) roughly on par with Gemini 3.7 Flash. I see no coding benchmark there that could substantiate your claim, and it doesn’t match my experience either, so I’m curious what you are basing it on, but you’re leaving the onus on me to prove you right.
[ Parent | on HN ]