I am not seeing corrections. How can I get corrected on Langua?

There are a few different ways you can get corrections whilst chatting with AI on Langua:

• 1) Click the pencil button below your responses. Via the Chat Settings, you can also turn on the option to automatically show these corrections. You'll then see written corrections below your responses.
• 2) In Chat Settings > Advanced Settings, enable the option for the AI to verbally ask you to repeat corrections. When you make mistakes, the AI will provide the corrected version of what it thinks you were trying to say, and ask you to repeat it. After, it'll continue the conversation seamlessly. Note that this option only applies in certain chats, such as the 'chat about anything' and debate categories. This is because in our testing, it did not work well with categories like role plays.
• 3) When you end the chat and have replied at least 6 times, you will see an option to generate a detailed feedback report. This can also be generated by clicking the brain icon in the mobile apps (as of writing, that icon does not show on the web version).

Sometimes, you may see that the AI gives different suggestions depending on the method you use. This is because each method approaches it from a different angle. Also, AI models are not perfect and may make the following errors occasionally:

• a) correct you when they shouldn't (for example, it may correct the capitalisation of a word when it doesn't remember that you're speaking, not writing), or it may suggest a more formal version when yours was fine. When you view corrections via the pencil button, you will note a 'check & explain' link. Click that and the AI will explain why it has made the corrections, as well as check its answer. Sometimes it may spot that it had made an error.
• b) miss a correction (in our testing it does spot the errors around 95% of the time)
• c) make typos e.g. a duplicate word is visible after it crosses something out.

We expect these imperfections to decrease over time as the models continue improving. We're using the world's best available models and constantly testing and optimising.

If you doubt that a correction is right, one option is to actually ask the AI in your next reply. You can say it partly in your native language if needed e.g. 'I was told that I should use X instead of X but I'm not sure that's correct.' Note that if the correction in question was provided in writing below your response (via the pencil button), rather than verbally, then the AI won't know about that correction, so you will have to give it enough information.

Hope this information helps!