Zed is a new code editor built for speed and optimized for working with large codebases and AI-powered tools. It boasts significantly faster performance than VS Code, especially when handling massive files and complex language servers. Built on a custom, from-scratch foundation, Zed uses Rust for the backend and a novel tree-sitter based approach for syntax highlighting, enabling near-instantaneous loading and interaction. The editor also prioritizes collaborative editing with built-in real-time co-editing capabilities and aims to integrate tightly with AI coding assistants in the future.
ProxyAsLocalModel lets you use third-party Large Language Models (LLMs) like Bard, Claude, or Llama 2 within JetBrains AI Assistant as if they were local models. It acts as a proxy, intercepting requests from the IDE and forwarding them to the chosen external LLM's API. This effectively expands the AI Assistant's capabilities beyond its default model, allowing developers to leverage alternative LLMs directly within their coding environment.
Hacker News users discussed the practicality and licensing implications of using third-party LLMs within JetBrains AI Assistant via a proxy. Several commenters questioned the value proposition given the existing plugins for various LLMs and the potential complexities introduced by the proxy setup. Concerns were raised about rate limiting and cost, especially with OpenAI's APIs. The licensing of models accessed through the proxy was a key point of contention, with some arguing that using a personal API key for commercial purposes might violate the terms of service of some LLM providers. Some commenters suggested that local models offer a more straightforward and potentially less problematic approach. The legality of circumventing API limitations through proxies was also debated. Overall, the reception was cautious, with many questioning the long-term viability and ethical implications of the project.
Senior developers can leverage AI coding tools effectively by focusing on high-level design, architecture, and problem-solving. Rather than being replaced, their experience becomes crucial for tasks like defining clear requirements, breaking down complex problems into smaller, AI-manageable chunks, evaluating AI-generated code for quality and security, and integrating it into larger systems. Essentially, senior developers evolve into "AI architects" who guide and refine the work of AI coding agents, ensuring alignment with project goals and best practices. This allows them to multiply their productivity and tackle more ambitious projects.
HN commenters largely discuss their experiences and opinions on using AI coding tools as senior developers. Several note the value in using these tools for boilerplate, refactoring, and exploring unfamiliar languages/libraries. Some express concern about over-reliance on AI and the potential for decreased code comprehension, particularly for junior developers who might miss crucial learning opportunities. Others emphasize the importance of prompt engineering and understanding the underlying code generated by the AI. A few comments mention the need for adaptation and new skill development in this changing landscape, highlighting code review, testing, and architectural design as increasingly important skills. There's also discussion around the potential for AI to assist with complex tasks like debugging and performance optimization, allowing developers to focus on higher-level problem-solving. Finally, some commenters debate the long-term impact of AI on the developer job market and the future of software engineering.
Continue is a new tool (YC S23) that lets developers create custom AI code assistants tailored to their specific projects and workflows. These assistants can answer questions based on the project’s codebase, write different kinds of code, execute commands, and perform other automated tasks. Users define the assistant's abilities by connecting it to tools like language models (e.g., GPT-4) and APIs, configuring it with prompts and example interactions, and giving it access to relevant files. This enables developers to automate repetitive tasks, enhance code understanding, and boost overall productivity.
HN commenters generally expressed excitement about Continue, particularly its potential for code generation, debugging, and integration with existing tools. Several praised the slick UI/UX and the speed of the tool. Some raised concerns about vendor lock-in and the proprietary nature of the platform, preferring open-source alternatives. There was also discussion around its capabilities compared to GitHub Copilot, with some suggesting Continue offered a more tailored and interactive experience, while others highlighted Copilot's larger training data and established ecosystem. A few commenters requested features like support for more languages and integrations with specific IDEs. Several people inquired about pricing and self-hosting options, indicating strong interest in using Continue for personal projects.
Summary of Comments ( 132 )
https://news.ycombinator.com/item?id=43912844
Hacker News users discussed Zed's performance claims, with some expressing skepticism about its "fastest" claim, especially regarding scrolling and syntax highlighting compared to established editors like Sublime Text and VS Code. Others pointed out the lack of clear metrics backing up the speed claims, emphasizing the importance of quantifiable data for such comparisons. Several commenters showed interest in the editor's potential, especially its use of Rust and its novel approach to collaborative editing. However, some found the comparison to VS Code unfair, given VS Code's extensibility and vast plugin ecosystem, which contributes to its performance overhead. The closed-source nature of Zed also drew concern, with users preferring open-source alternatives for customization and community involvement. Finally, some questioned the focus on AI features, suggesting they might be premature or unnecessary for core editing tasks.
The Hacker News post titled "Zed: High-performance AI Code Editor" (https://news.ycombinator.com/item?id=43912844) has generated a moderate number of comments, many of which express cautious optimism or skepticism about Zed's performance claims and overall value proposition.
Several commenters focus on the claim of Zed being the "fastest" AI code editor. Some question the methodology behind this claim, requesting benchmarks or comparisons against other editors like VS Code. Others point out that "fastest" can be subjective and depend on specific use cases and hardware. One commenter suggests that raw speed might not be the most crucial factor for an AI code editor, arguing that the quality of code suggestions and overall user experience are more important.
Another recurring theme in the comments is Zed's closed-source nature. Many users express concern about relying on a proprietary tool for critical tasks like coding, emphasizing the benefits of open-source alternatives. Some speculate about potential vendor lock-in and the possibility of Zed introducing paid features in the future. There is a discussion about the trade-offs between closed-source development potentially allowing for faster iteration and innovation versus the transparency and community involvement fostered by open-source projects.
Several commenters discuss Zed's features, particularly the AI assistance capabilities. Some express interest in trying these features, while others remain skeptical of their practical usefulness. There's a discussion about the potential for AI to truly enhance the coding experience, with some suggesting that current AI coding tools are more gimmicky than genuinely helpful. One commenter expresses a desire for more concrete examples and demonstrations of Zed's AI features in action.
A few comments touch upon Zed's choice of using Rust and its potential impact on performance. One commenter questions the necessity of using Rust for the entire application, suggesting that a hybrid approach might be more efficient.
Finally, several commenters mention existing alternatives, such as VS Code with extensions, and question whether Zed offers enough differentiation to justify switching. There's a general sentiment that Zed needs to demonstrate a significant advantage over established players to gain widespread adoption.