We are improving the base Grok 0.5T V8 model (public version 4.3) every few days. The 1.5T V9 has just completed its training (incorrectly called pre-training) and represents a major upgrade. Then, we add Cursor data into a
LLMS
-
User critiques Opus for overconfident responses and cost
By
–
I've stopped using Opus for brainstorming/strategizing, because it keeps wanting to jump to a conclusion and the end of every response. It's too confident it knows the answer every time. It makes it hard to have a back-and-forth. Also, it's too expensive vs Codex 5.5 sub.
-
Study finds memory in LLM agents remains unreliable
By
–
Breaking new study: memory in LLM agents still can’t really be trusted, even after over trillion dollars has gone into the development of the field.
-
Building software on mobile using ChatGPT’s Codex
By
–
you can just build things from your phone, with Codex in the ChatGPT app
-
Using AI memory features to personalize code generation and output
By
–
Memories in both ChatGPT and Codex are godsend! It allows them to contextualise and hyper specialise outputs and generations to you and your “taste” I’m often amazed by how Codex would just know tiny details of which tests to run, what commit dynamics it should follow and how to
-
UX pattern for LLM tool failures and dialog integration
By
–
Yes! There's a lot of nice UX approaches this style opens up.
For instance, if the LLM runs a bit of code that's blocked by the sandbox, we don't just show a `y/n/a(ll)` prompt, but instead stop the tool loop and insert the failed code into the dialog. -
RMS-MoE adds Co-Activation Memory to Mixture-of-Experts
By
–
Why do Mixture-of-Experts models keep re-computing the same expert choices for similar inputs? Researchers from Mashang Consumer Finance, Nanjing University, and Alibaba Group introduce RMS-MoE: they add a Co-Activation Memory that remembers which expert teams worked best for
-
AI tool poisoning exposes major enterprise agent security flaw
By
–
#AI tool poisoning exposes a major flaw in enterprise agent security
by Nik Kale @VentureBeat Learn more: https://
bit.ly/48YvAHT #LLM #GenerativeAI #ArtificialIntelligence #MachineLearning -
Claude Chrome extension token efficiency
By
–
Have you tried the claude chrome extension? It should be significantly more token-efficient
-
Google Gemini 3.2 Flash-lite-live cheaper real-time model
By
–
GOOGLE : Traces of Gemini 3.2 Flash-lite-live have been spotted on Google Cloud Console. Even cheaper real-time model?