SSH

AI leaks, news, projects, etc. Manager of @aitrackerbot
1.6m+ downloads on @huggingface

@Alibaba_Qwen Ambassador

[SSH @SSHCodes]

2 million downloads

[SSH @SSHCodes]

@kashikikashikii nothing significant

[SSH @SSHCodes]

i love it when the best open weight model in the world (kimi k3.1 pro) randomly starts speaking another language and ramble about mouses and hospitals in the middle of a security audit

[SSH @SSHCodes]

Kimi K3.1 Pro (max) on black hole benchmark 1.0 (2.0, which is much harder, is running now)
This isn’t bad, it isn’t great. Its just “good”. Below sonnet 5.5 for sure
I’d put it in between GPT 6.1 Sol and GLM 5.3

[SSH @SSHCodes]

I think openai gotta start distilling off of kimi or their cooked

[SSH @SSHCodes]

@cheatyyyy no “preview” at the end 👀
hopefully their further RL cooked

[SSH @SSHCodes]

@liquidai you guys have always been one of the best open weight labs in my opinion, please open weight this

[SSH @SSHCodes]

@Biggest ty!!

[SSH @SSHCodes]

As you post this, I got accepted :)

[shaun @Biggest]

It's a very good time to join the Qwen ambassador programme if you haven't. Trust me ;)

[SSH @SSHCodes]

@hiddnest danggg you got the version straight out of their lab

[SSH @SSHCodes]

plush :D

[SSH @SSHCodes]

@masonxxyz try @AsideAI

[Chanhee @hiddnest]

@arcinternet arc users, we're here for you @AsideAI

[SSH @SSHCodes]

who is railway, why is everyone getting hacked, and why won't anthropic let me into Duet

[SSH @SSHCodes]

@Biggest and how good k3.1 will be

[SSH @SSHCodes]

FYI polls like these really help tune and shape how AI Tracker Bot works, so go vote!

[AI Tracker Bot @aitrackerbot]

Quick question for everyone following 📊

Small releases like today’s NVIDIA physical-plausibility-evaluator (a video quality checker, not a new frontier model): do you want to see more of these, or fewer?

[SSH @SSHCodes]

I just put @t3dotcodes in VR:
woahhhhh

[SSH @SSHCodes]

@thsottiaux NAHHHH give reset RIGHT NOW

[SSH @SSHCodes]

gemini is the most slop, its confirmed this is a good benchmark

[Artificial Analysis @ArtificialAnlys]

Announcing AA-PersonalityBench, our new benchmark of the personality of language models across 30 traits and their communication style across 21 characteristics

Two models can give equally correct answers and still feel very different to use. AA-PersonalityBench measures those differences so people can understand which to use in different use-cases. Some use-cases like creative writing might demand imagination, while legal use-cases might demand directness. We evaluate models’ answers to 900 curated questions to judge subjective Personality Traits and programmatic means to calculate objective Communication Characteristics.

Personality Traits & Indexes. There are 30 personality traits (e.g., eloquent, pragmatic, sycophantic) which we roll up into eight aggregated Personality Indexes: Expressiveness, Organization, Informativeness, Transparency, Warmth, Conviction, Imagination and Slop. Each trait has a set of 30 dedicated questions and models’ answers are compared pairwise by a panel of LLM judges. We then z-score and percentile rank the trait and personality Elos.

Models with the strongest representation across the 8 Personality Indexes:
➤ Expressiveness: Claude Fable 5.1, GLM-5.3, GLM-5.3-Flash
➤ Organization: DeepSeek V4.1 Flash, Step 5 Preview, Inkling
➤ Informativeness: Muse Spark 1.3, Claude Fable 5.1, Muse Wonder, Claude Opus 5.5
➤ Transparency: Claude Sonnet 5.5, Claude Fable 5.1, GPT-6 Astra
➤ Warmth: Muse Wonder, Muse Spark 1.3, Claude Fable 5.1
➤ Conviction: Claude Fable 5.1, DeepSeek V4.1 Flash, Grok 4.7
➤ Imagination: Muse Spark 1.3, Claude Opus 5.5, GLM-5.3
➤ Slop: Llama 4 Maverick, GPT-4o, K2 Horizon

Communication Characteristics. There are 21 communication characteristics (e.g., average sentence length, emoji use, em dash usage) which we group into four categories: length, structure, punctuation, and emphasis. We compute these characteristics programmatically across all model responses.
➤ Length: Qwen3.8 27B averages about 1,030 words per response, nearly four times GPT-6 Luna’s 270
➤ Structure: Nemotron 3 Ultra averages nearly 3 tables per response, while most models rarely use one
➤ Punctuation: GLM-5.3 averages 7 em dashes per response, while Claude Opus 5.5, Sonnet 5.5 and Haiku 5.5 almost never use one
➤ Emphasis: K2 Horizon averages over 2 emoji per response, while most models almost never use one

[SSH @SSHCodes]

@KovD3v good idea!

[SSH @SSHCodes]

Visualizing AA in 3d
Currently the closest to the ideal corner is haiku 5.5