little_cad

2 か月前議論

Personalization vs privacy is always a trade-off 1) if you want AI chat more like your friends, it means the system(AI) need to know more about you, you have to expose more personal information and less privacy 2) Incognito is safer, but it will look like a cold start and less personalized.

little_cad

2 か月前議論

I only see closed-source models on your leaderboard so far: https://cadbench.ai/leaderboard

It would be interesting to see how open-source models perform on CAD tasks.

little_cad

2 か月前議論

yes, this is the common recipe. Cursor failed on the text-to-cad copilot first and then pivot to coding copilot and got succeeded there.

little_cad

2 か月前議論

If Anthropic starts entering the engineering space, OpenAI and others may follow.

The key question is: why would your tool or harness perform better than the frontier model providers’ own native tools, such as Claude for Creative Work, if your product is only a thin layer on top of their model or their agentic system?

Similarly, why would your tool work better than a CAD company’s own agentic tool? For example, it would not be very difficult for PTC to add an Onshape co-pilot that calls the Claude Agent SDK, while PTC can also build more powerful internal tools/MCP servers for their own use without exposing them to external API users.

コメント