LogStudio
Few people pride。
LogStudio
Few people pride。
News

ChatAI Smart Chat The price has been reduced

by |Published

One fold!

Ok，The main reason is that the upstream (OpenAI) has cut prices。 OpenAI has released a new chat-specific API，It's called Turbo，The version went up to GPT 3.5. However, surprisingly，While greatly improving the speed of computing and response，Operating costs are also significantly reduced。The direct payout is that the price of this model is one-tenth of Davinci，which is 0.002 Dollar 1000 Token。

I tested the model as soon as it was released，How much accuracy is improved is less clear，Anyway, the API format has changed a lot 😂。And then the first feeling was... Fast! React made a web app before it could hide elements based on state, and it was already shipped! - even Chinese is just as fast。

of course，There are still some differences between this model and GPT-3，For example, it tends to ask for further instructions rather than answer immediately，This is what GPT-3 does not have，The latter will immediately begin to answer。

In short，Because a new model was applied，Now the drop grid wisdom chat is also folded in sync，As you read this，All changes have been implemented，Have a good chat!

You may also also like

Published

Down entry method X should deal with self-signed certificate cracking attack

Downstudio Studios in 3 moon 30 Day gets message - drop input method X subscription cracked，Malicious users can modify Apple's Purchase Receipt content for any length of subscription without actually paying。 Most in-house apps，We responded the first time.。 This crack is primarily for apps that are locally communicating with Apple servers to decrypt receipts (considering that the crackscript has a generic Rewrite for in-house purchases)，Any app that communicates directly with Apple's servers will theoretically be hacked directly)；There are also many apps that also ignore local security，Although they communicate with their own servers,，Does nun verification do not，So it's been cracked, too.。 exist 4 Month，We started to get a lot of user feedback on the user base，We're actually making security improvements.，To protect the rights of paying users。 Now，Pocketed input X […]

ChatAI can now read incoming web links
Published

The web reading function is now implemented for ChatAI

  Now Drop Chat supports the second networking mode，Before，ChatAI supports online search (Google search) on the first question of each session，to make some of the answers more accurate，This greatly reduces the scenario in which the model has hallucinations (fabrications).。 Now，ChatAI can directly read the page you pass into，This allows you to ask questions about the content of the page、analyse、Summarize、translation and so on。Web links are matched and extracted using regular expressions，So when you use this function，It is best to separate the link from the body content with spaces，avoid extraction failures。 Other than that，ChatAI supports multiple links to read，There is no upper limit to the amount that can be extracted here，But for the sake of your points and model maximum processing length，It's better not to commit too much in a session。 Will reading a web page cost extra points? – No，But the content itself certainly costs points。 Is this feature also limited to the first question per topic? – No，This feature is unlimited，But reading many pages on the same topic will quickly fill up history，This leads to higher prices，Please make appropriate use of this function。   of course，This feature also has some limitations，This needs to be clarified，Please be aware when using this function： Due to model handling content length limitations (GPT 3.5) and price issues (GPT 4)，Content reading is roughly limited to 800 non-english word (also English word) approximately 1000 token around，If the content is too long，The content behind will be cropped，It will not use the GPT model to summarise，This is also due to price and efficiency； […]

Published

【Drop Wisdom Chat】From now on，Drop smart chat supports Vision!

  Drop smart chat now supports visual models! Supported models include Claude 3 Haiku，Claude 3 Sonnet， Claude 3 Opus and GPT-4o (GPT-4o also supports setting the image definition level high or low.)。Clients for each platform have been released，Update 0.6.3 version。 Limits Because the model has a limitation on the processing power of images，On every conversation send，The Lag Zhiliao client supports sending up to 5 pictures，Each image must not exceed 3.5MB in size，If the user selects an image that is larger […]

Published

Pocketed input macOS 3 Published

After a full year of development and testing，Pocketed input macOS 3 Officially released。In fact, before this, many users have purchased the falling input method macOS in advance 3 And continued to participate in development and testing，hereon，Thanks to these motivated users，If not you are actively involved in the drop input method macOS 3 development，It wouldn't be so good、A useful input method was born。 Compared to the falling input method macOS 2，The new generation of input methods contains as many as 31 item optimizations and improvements，The same time，In the follow-up 3 Generation input method in the life cycle，I'll keep adding more new features to it，and record it in the relevant page。 Pricing New Generation Input Method Pricing RMB 88 Yuan.，It's a lifetime license that everyone loves – a one-time purchase，Authorization is available for life。Even if released in the future […]