Anuma
What you can do
Chat with AICreate with AIBuild with AIAI Council
AI Model Access
Multiple AI ModelsOpen-Source LLMsClosed-Source LLMs
Nearby
Unified MemoryPrivacyPortable Context
Work & Career
ProfessionalsDevelopersEntrepreneursJob SeekersFreelancersSmall Business OwnersParents
Students & Learning
StudentsResearchersLanguage LearnersTeachers & Educators
Creative & Content
WritersDesignersContent CreatorsMusicians
Finance & Legal
Personal FinanceLegal & ContractsInvestment ClubsReal Estate
Help CenterWhat's NewBlogFAQAI Prompt LibraryHow Memory WorksOpen-Source LLMsClosed-Source LLMsPrivate by Default
Pricing
Get the appTry Anuma
Get the app
Anuma
What you can do
Chat with AICreate with AIBuild with AIAI Council
AI Model Access
Multiple AI ModelsOpen-Source LLMsClosed-Source LLMs
Nearby
Unified MemoryPrivacyPortable Context
Work & Career
ProfessionalsDevelopersEntrepreneursJob SeekersFreelancersSmall Business OwnersParents
Students & Learning
StudentsResearchersLanguage LearnersTeachers & Educators
Creative & Content
WritersDesignersContent CreatorsMusicians
Finance & Legal
Personal FinanceLegal & ContractsInvestment ClubsReal Estate
Help CenterWhat's NewBlogFAQAI Prompt LibraryHow Memory WorksOpen-Source LLMsClosed-Source LLMsPrivate by Default
Pricing
Get the appTry Anuma
Get the app
Back to What's new

Grok 4.3 lands, and cross-tab sync gets leaner

May 4, 2026·1 min readModelsPerformance
Grok 4.3 lands, and cross-tab sync gets leaner

Grok 4.3 joins the lineup

Grok 4.3 is now selectable alongside the rest of xAI's models in Anuma — xAI's latest, drop-in available across the model picker.

Cross-tab sync, lighter on the wire

Behind the scenes, the multi-tab streaming pipeline got a meaningful upgrade. Anuma already keeps conversations in lockstep across browser tabs; this week the cross-tab pipeline switched from full-snapshot updates to delta updates — only the changed bits travel between tabs. Multi-tab chats stay in sync the same way, with less bandwidth and quicker convergence under heavy streaming.

Quality

Synthetic tool-result placeholders no longer leak into the model's view of your conversation history, so answers stay grounded in what you actually said.

← Back to What's new

What you can do

  • Chat
  • Create
  • Build

Core features

  • Unified Memory
  • Multiple AI Models
  • Council Mode
  • Private by Default

Solutions

  • Work & Career
  • Student & learning
  • Creative & Content
  • Finance & Legal

Company

  • About
  • Careers
  • Branding
  • Contact us
  • Affiliate

Resources

  • Help Center
  • Blog
  • FAQ
  • Prompt Library
  • How memory works
  • Open-Source LLM
  • Closed-Source LLM
iOSAndroid
Anuma
Powered by
© 2026 Anuma, Inc. All rights reserved.|Privacy|Terms|Cookie Policy||