News AI
August 8th, 2024

Ask HN: Best AI Code Assistant?

The user tested several AI coding assistants, finding GitHub Copilot the most stable and effective, while seeking recommendations for solutions suitable for large codebases with fine-tuning capabilities.

Ask HN: Best AI Code Assistant?

The user has been testing various AI coding assistants, including JetBrains AI, GitHub Copilot, GitLab Duo, and Tabnine, over the past few months. They found GitHub Copilot to be the most stable and providing the highest quality code completions, although they noted a decline in the quality of completions over time. JetBrains AI offers interesting integrations with IDEs, but the code completion feature often fails to work effectively. GitLab Duo was briefly evaluated, and its code completion quality was significantly lower than that of GitHub Copilot. Tabnine has some interesting features and control options, but its code generation quality does not match that of GitHub Copilot. The user is seeking recommendations for AI coding solutions that are effective for large codebases and offer features like fine-tuning or knowledge base integrations.

- GitHub Copilot is considered the most stable and high-quality AI coding assistant, despite a recent decline in performance.

- JetBrains AI has useful IDE integrations but struggles with code completion reliability.

- GitLab Duo's code completion quality is notably inferior to GitHub Copilot.

- Tabnine offers unique features but lacks the code generation quality of GitHub Copilot.

- The user is looking for AI solutions that can handle large codebases and support fine-tuning or knowledge base integrations.

Related

Self hosting a Copilot replacement: my personal experience

Self hosting a Copilot replacement: my personal experience

The author shares their experience self-hosting a GitHub Copilot replacement using local Large Language Models (LLMs). Results varied, with none matching Copilot's speed and accuracy. Despite challenges, the author plans to continue using Copilot.

Show HN: Local Devin – powered by Sonnet 3.5

Show HN: Local Devin – powered by Sonnet 3.5

CodeCompanion.AI is a free, open-source AI coding assistant with semantic code search, project-specific instructions, and privacy features. It supports various technologies, automates tasks, and aims to boost developer productivity.

Ask HN: Am I using AI wrong for code?

Ask HN: Am I using AI wrong for code?

The author is concerned about underutilizing AI tools for coding, primarily using Claude for brainstorming and small code snippets, while seeking recommendations for tools that enhance coding productivity and collaboration.

Up to 90% of my code is now generated by AI

Up to 90% of my code is now generated by AI

A senior full-stack developer discusses the transformative impact of generative AI on programming, emphasizing the importance of creativity, continuous learning, and responsible integration of AI tools in coding practices.

GitHub Copilot – Lessons

GitHub Copilot – Lessons

Siddharth discusses GitHub Copilot's strengths in pair programming and learning new languages, but notes its limitations with complex tasks, verbosity, and potential impact on problem-solving skills among new programmers.

Link Icon 10 comments
By @yaro-works - 6 months
Try Supermaven. Suggestions are much faster than any copilot, and it has the largest context of your project. A 1 million token context window. Also, you get access to GPT-4o, Claude 3.5 Sonnet, and GPT-4 out of the box
By @mstaoru - 6 months
I tried Supermaven, and while it is certainly fast, it is more distracting to me since I have to read the suggestion, find it wrong, and type by myself (Python). Our FE guys who are doing React find it much more useful, probably because of the sheer amount of repetitive boilerplate React and JS require.
By @alwinaugustin - 6 months
Most of these AI assistants are still works in progress. Sometimes, they provide correct suggestions; other times, they do not. This is understandable, as generative AI still requires significant improvement in understanding context and predicting the most appropriate design, architecture, and solutions. These tools can be more time-consuming than manually editing or refactoring the code. I use these tools when I find it difficult to understand certain logic, as they explain it well. However, we still have to wait to generate production-ready code.
By @nreece - 6 months
Been hearing great things about Cursor, and its been impressive in my few days of use.

https://www.cursor.com

By @bubblebeard - 6 months
I’ve looked at several alternatives over the past year and Copilot is the best I’ve seen so far overall when you factor in ease of use, price to performance etc.

There may be services which generates code better, but at the end of the day you still need to review and touch up anything that is generated.

Copilots chat integration in Jetbrain IDE’s has also been great at helping me discover language features/functions, especially when learning new languages.

By @th3w3bmast3r - 6 months
I tried JetBrains AI and Github Copilot and ended up just removing them altogether.

The autocomplete when it works is wonderful but more often than not, I need to delete and type it again. Most of the time I know what I want to type and not using AI saved me the time it took me delete and try again.

I did like the chat window but it wasn't enough for me to keep it. Maybe you can't teach this old dog new tricks :(

By @jaymee - 6 months
I'm using Codium VScode extension. It's free and it is doing its job.
By @purple-leafy - 6 months
I’ve completely turned copilot off, its suggestions are usually dogwater. The thing I miss most is when it would sometimes correctly write imports
By @nailer - 6 months
I vote against Github copilot. The context window is too small for it to do anything meaningful.