.
@xai was cooking with their new Grok-4 fast Model! So freaking cheap and so good at the same time + 2m context window. This is huts! "2M token context window, and a unified architecture that blends reasoning and non-reasoning modes in one model" Input tokens $0.20 / 1M $0.40 /
GENERATIVE AI
-

Grok-4 Fast Model Launch: Cheap, Powerful, 2M Context Window
By
–
-

Federal Judge Orders OpenAI to Preserve ChatGPT Conversation Histories
By
–
BREAKING: Federal judge orders OpenAI to preserve ChatGPT conversation histories in a copyright case! Even if users ask for deletion or privacy laws demand it, OpenAI must keep those chats safe.
Business accounts are off the hook, for now. OpenAI says it’ll -
Grok Adds Beautiful Text-to-Speech Reading Capability
By
–
Grok can now “read aloud” in a beautiful voice https://t.co/qy5MBYzXrw
— Elon Musk (@elonmusk) 20 septembre 2025Grok can now “read aloud” in a beautiful voice
-
sGrok AI Algorithm Assesses Content Quality for Small Accounts
By
–
Yeah. Will make a big difference for small or new accounts who post great content, a sGrok will actually read every post to asses whether others would find it interesting.
-
LMArena Benchmarking Gamed by Sycophantic AI Responses
By
–
It is kind of amazing how many good benchmarking tools have been saturated or gamed (whether by accident or on purpose) in the past few months. LMArena really seemed like a good method, but then it turned out that you could just go full syncophantic and people loved it.
-

Intelligence Index Benchmarks Need Improvement Beyond Saturation
By
–
Not to take away from Grok 4 Fast (which seems like a very good model) or from Artificial Analysis (one of the few organizations doing independent benchmarking), but the Intelligence Index is an average of pretty saturated benchmarks (aside from HLE), we really need better ones.
-
Intelligence Density: Large Models’ Distance from Theoretical Maximum
By
–
Intelligence density per unit of memory & compute is a fundamental metric. My rough guess is that large models are at least one, but maybe two, orders of magnitude away from the Platonic maximum.
-
McConaughey Considers Private LLM, GPU Setup Discussed
By
–
Matthew McConaughey says he wants a private LLM on Joe Rogan Podcast > someone tell him to > Buy a GPU > if he wants help i'll set up the whole thing for him for free if he tells more people to Buy GPUs > alright alright alright
-
Grok 4 Fast Released to All Users on Web and Mobile
By
–
Grok 4 Fast is available now for all users in http://
grok.com, http://
grok.x.com, iOS and Android apps in Fast and Auto modes. All users, including free users, will have access to our latest model without restrictions, marking a significant step toward -
Grok 4 Fast: Feedback Wanted for Model Improvements
By
–
We’d love to hear your feedback on Grok 4 Fast. The team will be incorporating your responses into continuous model upgrades, so please be vocal on X. If you want to push the limits of reasoning efficiency, please join us!