\
  The most prestigious law school admissions discussion board in the world.
BackRefresh Options Favorite

Review of IBM's new open weight model by a bigtech bro

I had a shortish exploratory chat with Granite4.1:8b tonight...
obsidian center dragon
  04/30/26
who cares
aqua kitty gay wizard
  04/30/26
I understood like half of that. Explain it like I don't read...
offensive 180 corn cake garrison
  04/30/26
It's designed to be fast and it was trained on high quality ...
obsidian center dragon
  04/30/26
What does "no reasoning" mean?
offensive 180 corn cake garrison
  04/30/26
Everyone thought they needed reasoning models to get the bes...
obsidian center dragon
  04/30/26
What does that mean? Doesn't it need to do reasoning to foll...
offensive 180 corn cake garrison
  04/30/26
The model still has to follow intermediate steps during prom...
obsidian center dragon
  04/30/26
Yeah ofc, I just didn't know what "reasoning" mean...
offensive 180 corn cake garrison
  04/30/26
Like how chat gpt and claude for "hard problems" w...
milky wonderful ratface
  04/30/26
Got it, I thought it might mean that. I totally believe it c...
offensive 180 corn cake garrison
  04/30/26
Would never use something that has "deterministic outpu...
milky wonderful ratface
  04/30/26
I have news for you about women
lime office half-breed
  04/30/26
what tokens/sec are you getting
vengeful mustard hell hairy legs
  04/30/26


Poast new message in this thread



Reply Favorite

Date: April 30th, 2026 10:54 PM
Author: obsidian center dragon

I had a shortish exploratory chat with Granite4.1:8b tonight.

It is a good model. The outputs feel something akin to deterministic which reflects the enterprise deployment IBM is shooting for. Input -> Output. The voice is pleasant and not overly beepboop robot. It hyperfixates on patterns (one message with a list kicks off 5 more) but it responses really well to faux system messages correcting it. The world knowledge is good and nuanced for an 8b model.

If I had a no-human-in-the-loop pipeline for evaluations or content parsing or something I’d 100% reach for Granite 4.1 first. It’s like,,, instruct tuned but only enough to accomplish its intended goal.

——

Oh! And! No reasoning! As an engineered design constraint. Neat!

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2.#49856001)



Reply Favorite

Date: April 30th, 2026 10:56 PM
Author: aqua kitty gay wizard

who cares

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2.#49856010)



Reply Favorite

Date: April 30th, 2026 10:56 PM
Author: offensive 180 corn cake garrison

I understood like half of that. Explain it like I don't read hackernews

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2.#49856011)



Reply Favorite

Date: April 30th, 2026 11:00 PM
Author: obsidian center dragon

It's designed to be fast and it was trained on high quality data. IBM really went their own direction

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2.#49856026)



Reply Favorite

Date: April 30th, 2026 11:02 PM
Author: offensive 180 corn cake garrison

What does "no reasoning" mean?

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2.#49856029)



Reply Favorite

Date: April 30th, 2026 11:09 PM
Author: obsidian center dragon

Everyone thought they needed reasoning models to get the best chat experience, but now with agentic harnesses the reasoning becomes a waste of tokens. I have it disabled in my Hermes Agent because it's too fuckin slow. IBM basically just saved us all from having to manually disable it

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2.#49856064)



Reply Favorite

Date: April 30th, 2026 11:10 PM
Author: offensive 180 corn cake garrison

What does that mean? Doesn't it need to do reasoning to follow instructions?

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2.#49856068)



Reply Favorite

Date: April 30th, 2026 11:28 PM
Author: obsidian center dragon

The model still has to follow intermediate steps during prompt processing, people are just finding more efficient ways to do it. One model (I forget which one) keeps the entire prompt intact at each layer.

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2.#49856095)



Reply Favorite

Date: April 30th, 2026 11:54 PM
Author: offensive 180 corn cake garrison

Yeah ofc, I just didn't know what "reasoning" meant and was too lazy to search

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2.#49856136)



Reply Favorite

Date: April 30th, 2026 11:33 PM
Author: milky wonderful ratface

Like how chat gpt and claude for "hard problems" will go into a "chain of thought" where it "reasons". I turn it off for basic chats and only use it when I'm having it solve something difficult. Also sometimes it makes it stupider believe it or not. Also way faster without it.

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2.#49856103)



Reply Favorite

Date: April 30th, 2026 11:53 PM
Author: offensive 180 corn cake garrison

Got it, I thought it might mean that. I totally believe it could make it stupider in some cases. I'll turn that off on the ones I use and see if the results are better.

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2.#49856134)



Reply Favorite

Date: April 30th, 2026 11:31 PM
Author: milky wonderful ratface

Would never use something that has "deterministic outputs"

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2.#49856098)



Reply Favorite

Date: April 30th, 2026 11:36 PM
Author: lime office half-breed

I have news for you about women

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2.#49856105)



Reply Favorite

Date: April 30th, 2026 11:55 PM
Author: vengeful mustard hell hairy legs

what tokens/sec are you getting

(http://www.autoadmit.com/thread.php?thread_id=5862289&forum_id=2.#49856142)