OpenAI Launches New ChatGPT Interface, Designed for Coding
OpenAI launched a beta of canvas, a new ChatGPT coding and writing tasks space, this week. The AI company described it as going beyond the limitations of the chat interface by offering a side-by-side interface.
“Although the chat interface is easy to use and works well for many tasks, it’s limited when you want to work on projects that require editing and revisions,” the team wrote. “With canvas, ChatGPT can better understand the context of what you’re trying to accomplish. You can highlight specific sections to indicate exactly what you want ChatGPT to focus on. Like a copy editor or code reviewer, it can give inline feedback and suggestions with the entire project in mind.”
Canvas is built with GPT-4o and can be selected via the model picker. It opens automatically when ChatGPT detects a scenario when it could be useful. Alternatively, adding “use canvas” in the prompt will trigger it.
Canvas has already rolled out for ChatGPT Plus and Team users globally, while Enterprise and Edu users will get access next week. Canvas will be available to ChatGPT Free users when it’s out of beta, the company added.
For coding, this means it can help track and understand ChatGPT’s changes.
Image via OpenAI
Coding shortcuts include:
- Review code, where ChatGPT provides inline suggestions to improve your code.
- Add logs, which insert print statements to help debug and understand code.
- Add comments to the code to make it easier to understand.
- Fix bugs by detecting and then rewriting them.
- Port to language, which can translate code into JavaScript, TypeScript, Python, Java, C++, or PHP.
OpenAI also upgraded its Moderation API last week with a new model that is better at detecting harmful text and images. It uses a new multimodal moderation model.
It’s free for all developers to use via the Moderation API, which is free as well.
“Based on GPT-4o, the new model supports both text and image inputs and is more accurate than our previous model, especially in non-English languages,” the OpenAI team wrote on its blog. “Like the previous version, this model uses OpenAI’s GPT-based classifiers to assess whether content should be flagged across categories such as hate, violence, and self-harm while also adding the ability to detect additional harm categories.”
It also provides finer control over moderation decisions. It enables this by calibrating the probability scores to reflect the likelihood of content matching the detected category, the team stated.
“Since we first launched the Moderation API in 2022, the volume and variety of content that automated moderation systems need to handle has increased, especially as more AI apps have reached massive scale in production,” OpenAI wrote. “We hope today’s upgrades help more developers benefit from the latest research and investments in our safety systems.”
Grammarly uses the Moderation API to help ensure its product outputs are safe and fair. AI audio tool ElevenLabs also uses the Moderation API as part of a proprietary solution to scan content generated by their audio AI products.
WaveMaker React Native Studio Targets JavaScript Developers
WaveMaker, a low-code development platform, released its React Native Studio on Tuesday. The tool is designed to make mobile app building easier for web developers who are adept at JavaScript but not React Native.
WaveMaker Studio for React Native can be used to create both iOS and Android apps from a single codebase. It can translate complex CSS and components into React Native code and comes with tools for testing, debugging, installer creation and deployment, the company stated. It also integrates agile methodologies.
“By combining low-code with React Native, we enable teams to build cross-platform, secure, enterprise-grade and experience rich mobile apps at a fraction of the time and cost,” Deepak Anupalli, co-founder and CTO of WaveMaker, said in a press release. “This solution is designed to help companies stay ahead in a fast-moving, mobile-first world.”
React Jam Fall 2024 Starts This Weekend
React Jam launches this weekend with the theme “Retro Minimalism.” It’s a game design challenge, and this year, less is more. Think Minesweeper, Pong and Breakout simple.
The requirements are to make a multiplayer game using React and the Rune SDK, which will handle all net code and servers, as well as embed your game in the app.
Screenshot via ReactJam’s website.
Games will be rated across three categories: Fun, theme and presentation, with prizes of $500 for first place, $300 for second place and $100 for third place. But there are also prizes for the game with the highest play time during Oct. 11-16 across Rune’s community of millions, and those are a bit more robust at $1,000 for first, $500 for second, and $100 for third.
There are also bonus prizes of online tickets to the React Brussels conference. See the React Jam FAQ for more details.
Deno Releases Stable Rusty V8
Deno released Rusty V8 as stable and production-ready this week.
“Deno is a modern, zero-config JavaScript runtime written in Rust,” wrote Ryan Dahl, creator of Deno and Node.js, on the Deno blog. “At its core is Rusty V8, a library that provides high-quality, zero-overhead Rust bindings to V8’s C++ API.”
Rusty V8 allows Rust developers to embed the V8 JavaScript in projects. Embedding the V8 JavaScript engine would allow Rust developers to interact with JavaScript, to leverage the JavaScript ecosystem or to compile Rust code to WebAssembly, for instance.
“Rusty V8 gives Rust developers direct, zero-overhead access to V8’s C++ API,” Dahl explained. “It stands out for its completeness and seamless integration with high-performance environments.”
Dahl outlined some of the use cases Rusty V8 enables for developers:
- Build custom JavaScript runtimes for embedded devices, serverless environments, or plugin systems.
- Run WebAssembly modules.
- Leverage the V8 Inspector to add debugging capabilities to your JavaScript runtime.
- Use the V8 Fast API, which lets developers “call Rust functions from JavaScript with minimal overhead, perfect for high-performance applications.”
- Automatic memory management thanks to V8’s cppgc garbage collector.
