Ask HN: Navigating AI Tooling Choices

[atif089]

I'm currently using ChatGPT Plus and developing with GPT-4o-mini (Continue for VS Code), which costs me around $25 a month. However, I'm considering switching to Claude, as I'm aware that AI tools can evolve rapidly, and ChatGPT might improve again in the future.

I'm also frustrated with the cumulative costs of AI tools — $20 for Cursor, $20 for the GPT API, and $20 for ChatGPT.

Are there any recommendations for managing these costs while still accessing high-quality AI tools? Is it worth switching to Claude now, or should I stick with ChatGPT for the time being? Any insights or experiences would be greatly appreciated!

[rubslopes]

I'm having the same questions. Currently, and this might change rapidly, the new GitHub Copilot provides the best cost/benefit solution. For $10, you have access to the best models, and with a Composer feature similar to Cursor, that edits multiple files in your code base.

But if you want to experiment with many open LLMs instead, I suggest you use OpenRouter. It gives you access to any model with a single api key.

[sandwichsphinx]

I'm currently subscribed to both ChatGPT Plus and Claude Pro, but if I had to choose only one, I'd stick with ChatGPT. The message limits are more flexible, especially with unlimited mini-usage, which lets me experiment and iterate freely. With Claude, I frequently hit the message limits, which makes me hesitant to use it at all—like saving items in a game only to never use them, ultimately defeating the purpose.

[inquisitor27552]

im on supermaven $10 and they provide free premium chat to openai and anthropic.

cursor is nice but it messes a lot with my hud / field of vision. it's like driving a bike but you have car handbrakes.

[rubslopes → inquisitor27552]

I believe they give you $5/month to spend with chat, no?

[mansimov]

why are you paying for cursor? use copilot and pass your anthropic / openai key (will charge you per usage) in cursor

[csomar]

copilot will give you access both to o1 and claude 3.5.