Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Ethen Blog

Launches, architecture notes, engineering deep-dives and model analysis from the team building Ethen.

  1. The Principles Behind Ethen’s Product Design
  2. What We Want Ethen to Feel Like in 2027
  3. Ethen V5: What We’re Rebuilding and Why
  4. The Road to Ethen V5
  5. What We’ve Changed Since Ethen V4

ProductFeatured

13 min read

Read the article
Table mapping six kinds of work (conversation, creation, coding, investigation, delegated work highlighted, action on computers) to object of attention, time scale, feedback and interface shape.

104 articles

October 2026

  1. Why Ethen Uses Specialized Interfaces Instead of One Universal UIProduct13 min
  2. The Principles Behind Ethen’s Product DesignProduct13 min
  3. What We Want Ethen to Feel Like in 2027Company13 min
  4. Ethen V5: What We’re Rebuilding and WhyCompany13 min
  5. The Road to Ethen V5Company13 min
  6. What We’ve Changed Since Ethen V4Company13 min
  7. Why We’re Choosing Depth Over Feature CountCompany13 min
  8. What It Means to Build an AI Company With AICompany12 min
  9. How AI Agents Are Changing the Way We Build EthenEngineering12 min
  10. Building a Research Lab as a Small Team in the Age of AI AgentsCompany12 min
  11. Why Not Everything Ethen Researches Needs to Become a ProductCompany12 min
  12. What Ethen Research Lab Is Exploring Beyond AI ProductsCompany12 min
  13. Why We’re Not Rushing Ethen Into HardwareCompany12 min
  14. From Screen to Physical World: How We Think About Ethen RoboticsCompany12 min
  15. Why a Digital Robot Needs More Than an AvatarCompany12 min
  16. What We’re Learning From Designing iBOTProduct13 min
  17. Why Ethen Is Researching Digital Robots Before Physical RobotsCompany13 min
  18. How We Think About Image, Video, Audio and Speech as One Creative SystemProduct12 min
  19. Why Model Families Matter More Than Huge Model CountsModels & Intelligence13 min
  20. What 1,499 AI Endpoints Taught Us About Model Catalog DesignEngineering12 min
  21. Why Ethen Studio Is Becoming More Workflow-OrientedProduct12 min
  22. What We’re Learning From Building Ethen for Both Consumers and EnterprisesCompany12 min
  23. How We’re Preparing Ethen for Private and Enterprise DeploymentsProduct13 min
  24. Why Enterprise AI Needs More Than SSO and Admin ControlsSecurity & Trust13 min
  25. What We Mean by Responsible AutonomyCompany13 min
  26. Why Ethen Is Treating AI Safety as a Product ExperienceSecurity & Trust13 min
  27. What Ethen Is Doing to Make AI Outputs Easier to VerifyProduct13 min
  28. How We Decide Whether Something Belongs in Blog, Docs, or ResearchCompany13 min
  29. Why Ethen Uses System Cards and Research Notes DifferentlyCompany13 min
  30. What We Learned Publishing 165 Research VisualsEngineering13 min
  31. Building a Public Research Archive That Can Scale Past 100 PapersEngineering13 min
  32. Why We Made Ethen Research Look More Like a Journal Than a BlogCompany13 min
  33. Inside the Redesign of Ethen’s Research PublicationsCompany13 min
  34. How We’re Thinking About AI for Founders and Small TeamsProduct13 min
  35. Asking AI vs Delegating Work to AI: What ChangesProduct13 min
  36. Why Ethen Founder Is About Outcomes, Not More ChatProduct13 min
  37. What We’re Building for Ethen ComputerProduct13 min
  38. Why Computer Use Is More Than Clicking ButtonsSecurity & Trust14 min
  39. What We Want Ethen Voice to Feel LikeProduct14 min
  40. How Voice Fits Into the Ethen ExperienceProduct17 min
  41. Why Local AI Still Matters in a Cloud-First WorldModels & Intelligence13 min
  42. Building Ethen Across Desktop, Web and Local AIProduct12 min
  43. What We Want “My Ethen” to Feel LikeProduct13 min
  44. Why User-Controlled AI Memory MattersProduct12 min
  45. How We’re Rethinking AI Memory Across EthenProduct13 min
  46. What Makes an AI Model Useful Beyond BenchmarksModels & Intelligence13 min
  47. Why Ethen Sometimes Won’t Use the Newest ModelModels & Intelligence13 min
  48. What We Look for Before Adding a New Model to EthenModels & Intelligence13 min
  49. Why Ethen Is Built Around Multiple Models Instead of OneCompany13 min
  50. Why Better AI Models Don’t Eliminate the Need for Better ProductsCompany13 min
  51. How Ethen Thinks About AI Actions That Can’t Be UndoneSecurity & Trust12 min
  52. What Happens When an AI Task Fails Halfway Through?Engineering12 min
  53. Why Ethen Is Building for Recoverable AI WorkEngineering13 min
  54. What “Done” Should Mean for an AI AgentProduct13 min
  55. Why Ethen Keeps Human Approval in the LoopSecurity & Trust13 min
  56. Designing Ethen for Work That Takes Minutes or HoursProduct12 min
  57. Why Long-Running AI Work Needs a Different UX Than ChatProduct13 min
  58. What Is an AI Workspace? A Better Way to Think About ItProduct12 min
  59. Why Ethen Shows What It Knows—and What It Doesn'tProduct13 min
  60. What We're Improving About Reliability Across EthenEngineering13 min
  61. Why Ethen Supports More Than One AI ProviderInfrastructure13 min
  62. Making AI Model Choice Less Confusing: A Practical Way to ChooseModels & Intelligence13 min
  63. Why Ethen Is Investing in Model IntelligenceModels & Intelligence13 min
  64. The Next Phase of Ethen ChatProduct12 min
  65. What Ethen Work Is Meant to BecomeProduct12 min
  66. Ethen Studio: From Model Catalog to Creative WorkspaceProduct13 min
  67. Ethen Code: What We're Building NextProduct13 min
  68. Why Ethen Keeps Research Separate From Product ClaimsCompany13 min
  69. What We Learned Publishing 40 Research Papers at OnceEngineering12 min
  70. How to Explore Ethen Research Lab: Programs, Evidence Labels and Reading PathsProduct13 min
  71. Why Ethen Research Lab Publishes Its Work in PublicCompany13 min
  72. What We're Building Across Ethen: October 2026 UpdateCompany13 min
  73. Why Ethen Is a Family of Specialized AI Apps, Not One AppCompany14 min

September 2026

  1. Choosing Image and Video Models by WorkflowModels & Intelligence17 min
  2. Checking the Evidence in an AI Research ReportProduct16 min
  3. Choosing an AI Coding EnvironmentDevelopers15 min
  4. What Makes an AI Agent Job VerifiableProduct16 min
  5. Local AI or GPU Hosting: What to Check FirstModels & Intelligence16 min
  6. When an AI Gateway HelpsDevelopers13 min
  7. How to Read an AI Model ComparisonModels & Intelligence15 min
  8. Choosing a Multi-Model AI WorkspaceProduct16 min
  9. Keeping Code History Scoped to the Signed-In UserEngineering16 min
  10. Separating Automation Triggers From ExecutionEngineering12 min
  11. Versioning GPU Deployment Recipes in EthenInfrastructure17 min
  12. How Ethen Desktop Talks to Local ModelsDevelopers14 min
  13. Binding Computer-Use Approvals to Specific ActionsSecurity & Trust13 min
  14. Three Places to Use Ethen CodeProduct13 min
  15. Moving Ethen Designer Into Its Own AppEngineering12 min
  16. Reserving a Budget for VerificationInfrastructure18 min
  17. When an Agent Action's Outcome Is UnknownEngineering13 min
  18. Making Mission Completion Depend on EvidenceEngineering18 min
  19. How Founder's Job Model Fits EthenProduct13 min
  20. How Ethen Chat Starts a Voice SessionEngineering13 min
  21. Building Durable Image and Video Jobs in Ethen StudioEngineering11 min
  22. From Provider Endpoints to Ethen Model FamiliesModels & Intelligence10 min
  23. Showing Unknowns in Ethen Model IntelligenceEngineering16 min
  24. Who Owns Each Model Fact in EthenModels & Intelligence13 min
  25. How Ethen Gateway Chooses an Eligible ModelEngineering18 min
  26. How Ethen Gateway Binds API Requests to ProjectsDevelopers14 min
  27. Inside Ethen's Durable Job ServiceInfrastructure13 min
  28. What a Release Certificate Actually Proves at EthenEngineering15 min
  29. How Ethen Builds Public Model PagesModels & Intelligence12 min
  30. Keeping Ethen Chat FocusedProduct10 min
  31. How Upcube Is Organizing Ethen Across Specialized AppsCompany12 min

From Ethen Research Lab

Ethen Research Lab is Upcube's public research publication program. Each publication states its evidence status.