That's great news!
Luna is absolutely good in Explorbot
The only reason not to use it was its price. No reasons now!
Luna is insabely smart for tasks like browser discovery, browser interaction, and exploratory testing. Just give it propre harness:
Prince of Persia on day, developer at night. Author of @CodeceptJS and @Codeception testing frameworks. Currently working on @testomatio to make tests visible!
- Everyone is talking about gpt-5.6-sol but I must say gpt-5.6-luna from @OpenAI is awesome for agentic web testing! For testing web you don't need smartest model, just the smart one. Paired with gpt-5.4-nano for actual execution they do great job testing apps! See them running
- I found that @AnthropicAI has unclosed gap in tgeir API platform There is no cheap, 20-30b model in their stack costing up to 0.5$M tokens. The smallest Haiku is too slow and expensive and can't be used for simple parsing and analysis tasks There is gpt nano, gemma lite...
- No. no. no Voice mode for AI agents is not for me If I will use it I will just scream FUCK FUCKING FUCK WHAT YOU FUCK DO to Fable+Opus ignoring my intructions on refactoring I prefer to do this silently typing on keyboard. Passing all emotions into caps lock
- Explorbot runs unscripted, continuosly testing your web application No test automation code No prepared test plans No source code reading It just looks into UI, finds paths, writes test cases and tries to pass them


