TestingCatalog News ποΈ
It cannot interact with apps yet π
More controls are also available in the settings π€
TestingCatalog News ποΈ
Work with Apps Beta also comes with a VSCode Extension allowing ChatGPT to access editor context more reliably! There it can also see selected parts of the code π
It cannot modify the code directly in the editor yet.
Installation instructions https://help.openai.com/en/articles/10128592-how-to-install-the-work-with-apps-visual-studio-code-extension
Installation instructions https://help.openai.com/en/articles/10128592-how-to-install-the-work-with-apps-visual-studio-code-extension
TestingCatalog News ποΈ
Google AI Studio may get a new UI design soon, making it look closer to the consumer-facing Gemini version.
Chat bubbles will get a new look as well π
Finally got a chance to play with new conversation starters UI on ChatGPT for Android.
Very slick and thoughtful UI π₯
Very slick and thoughtful UI π₯
TestingCatalog News ποΈ
According to the "Limits" page on Le Platforme, Mistral AI is preparing to release 3 new models (supposedly next week?). - mistral-large-2411 - Potentially a multimodal Large 2.1 - pixtral-large-2411 - mistral-moderation-2411 - a mini model for moderation
More than this, Le Chat responses already say that it uses "Pandragon" - a previously discovered model with multimodality.
h/t https://www.tgoop.com/c/1349477688/15007
h/t https://www.tgoop.com/c/1349477688/15007
TestingCatalog News ποΈ
Looks like there is a new round of LLM battles on lmarena this weekend πππ - anonymous-chatbot - some reports suggest that it is an improved 4o with better formatting and instruction use. - secret-chatbot - potentially a bigger size gemini-exp model mentionedβ¦
"chatgpt-4o-latest-20241111" also appears in the models list on lmarena code.
A minor model update from the past week which some users are reporting is live on ChatGPT already.
A minor model update from the past week which some users are reporting is live on ChatGPT already.
TestingCatalog News ποΈ
Looks like there is a new round of LLM battles on lmarena this weekend πππ - anonymous-chatbot - some reports suggest that it is an improved 4o with better formatting and instruction use. - secret-chatbot - potentially a bigger size gemini-exp model mentionedβ¦
Also "mystery-gemini-3" is there π
TestingCatalog News ποΈ
Perplexity is working on the possibility of adding domain names as search sources for a certain Space π It seems to be panned as part of an Enterprise offering because on the UI you can see who added a certain domain to the list.
Besides that, Perplexity is planning to provide a 30-day free trial for enterprise customers saying "Share Perplexity with your colleagues" π€