Currently, model responses in character chats exceeding ~300 tokens become unintelligible, progressively lacking more conjunctions, prepositions, commas, and quickly degrading into just a string of adjectives. I assume this is because the repetition penalty parameter is set too high, but we have no way of adjusting this. Please add a slider for repetition penalty alongside the top_p and temperature parameters.
Today I tried edit a image with grok model with a prompt nsfw but grok or Venice, I don’t know what, blocked the content when in the past this no happen.
What is going on with the Grok models? Getting errors like cannot edit an image unless it was created by grok. Very SFW images being block as NSFW. Any updates?
There are serious issues with the end-to-end encrypted models. They rarely work to the point that they are basically unusable. Every request returns a “Signature request failed” error or just a vague “Something went wrong. please try again.”
as subject. The work around I have is to have the AI output title first then the emoji but it shouldn’t require such work around.
It's annoying because perhaps we have a very well-crafted prompt, but if we accidentally stop the bot's response before it thinks or replies, our prompt gets deleted.
This is happening on Samsung browsers, Brave, Opera, and Chrome. Nothing I do fixes this as it continues to refresh, logs me out, logs me back in, and then ruins whatever prompt I was writing. I don’t use any of the image/video modes and don’t have a System Prompt active but it refreshes anyways. It’s happening every few minutes no matter what I do to fix it
I login with google. Is a incredibly annoying when site redirect you to auto relogin and next to clean new chat, erasing all typed but not sended yet text. Additionally. Long conversation with characters buggy. Errors “out of memory“, disappearing my text with maintain AI answer, jumping up and down when print answer. All of this starts like week ago.
Seedance 2.5 R2V - When trying to reference a video and telling the model to edit it, I get back error messages about needing to pass in a -1 duration and aspect ratio of ‘adaptive’ Online UI doesnt offer these and when trying to pass in via API i get a validation error about not matching an expected enum. Thank you
Can we please stop the non-stop auto-refresh on mobile. On iPhone the app has no uncensored models, so we have to use the browser site. But it keeps fucking auto-refreshing non-stop. Its almost unusable. Do the devs not use test the mobile site?
Hi I've been using agentique to help me produce DND campaigns . It works really well but I always run into the same issue that my discussions are always erased when I relog the application, on the spot it starts loading forever and then the next day all my conversations are gone and all my options are put back to default,
Every couple of minutes my VeniceAI keeps signing me out immediately and signing me back in. I switched from Firefox (default browser) to Chrome to see if it solves this issue and it does not. I disabled all the security features and I do not have a VPN or anything like that. I have not changed any settings on my PC. It does this on chrome as well as firefox. Any suggestions?
The three dots to change my primary password or delete a password are not working in any of the 4 browsers that I have tried.
so every time im on mobile and im waiting for the bot to finish it’s prompt for some reason the website decides to reset in the middle of the prompt, and because of that it cuts off in the middle of the prompt as if i stoped it manually…
Description: Context window is capped at 40~50K tokens on all unlimited-use text models, in classic chat. The context counter becomes orange and caps at something like 5% (actual number depends on model, 5% for GLM 5.2, 24% for Deepseek v3). Model behaves as if context window is full, and starts forgetting. No such issue with with Pay-per-use models. Platform: https://venice.ai, Desktop Web Subscription: Pro Did it work before? Yes When did it started happening: Since release of GLM 5.2
Sind da noch mehr betroffen? Gibt es eine Lösung? An was liegt das? -neue apk von venice.ai: Fehler -neue Installation vom Playstore: Fehler Venice kann ich so leider nicht mehr verwenden… Samsung s25 ultra Android 17 One-Ui 8.5 Venice.ai APK und Playstore Version Siehe Beispiel mit Sonne. Ich werde nicht schlau daraus! Ich bin Pro Abonnent! (Weitere Details siehe Screenshots unten) Meine Mail an den Support: [«Guten Tag Ich habe nach meinen letzten Nachrichten noch ein paar Tests durchgeführt. Die Ergebnisse sind gravierend: Testbeispiele (selbe Bilder, verschiedene Texte): - Billing-Screenshots: - "Warum machst du das?" → Fehler - "Wie kann das passieren?" → Fehler
Agentic chat cannot make use of memories, notes, system prompt and temperature….