This feels misguided. MCP is still one of the best ways to execute deterministic sub-flows (i.e., stepwise processes) and secure tooling that an LLM would either lose itself while executing or should never access directly.
Im still struggling with understanding when MCP works better. I move everything to cli after a while. Can you give me more concrete examples? Because I don’t doubt you, I just don’t understand.
Most APIs and CLIs are not setup with clear separation of permissions, and when they have those permissions are mostly designed around human access patterns and risks, not LLM ones. The primary example of course being read-only vs write access.
MCPs have provided any easy way to side-step that baggage.
e.g. in an MCP, you have tools, those tools are usually binned into "read" vs "write". Given that, I can easily configure my tooling to give an LLM (e.g. Claude Code) unlimited read access to some system (by allowing all read-only tools) without likewise giving the LLM write/destructive access.
Obviously you can design APIs/CLIs with this in mind, but up until now that has not been a primary concern so they haven't.
That makes some sense. But one can make the argument given how easy it is to create CLI tools and add new API endpoints, enhancing them is still a better approach than creating and MCP.
I'm not pro or anti-MCP myself. I just haven't had a lot of success using them yet. I've been struggling to find the right balance and every path has lead me to a CLI tool (optionally paired with a skill).
Now I'm not using my cli tools in Claude Chat proper, but I'm not using MCPs either because they just keep failing me. This could very well be a me problem, but I'm still looking for that "ah-ha" moment.
Maybe I'm misunderstanding you, but the way you describe MCP sure sounds like it's just another RPC endpoint. Those are easy to add using traditional methods. Why deal with all the overhead of MCP for those cases?
It's the security layer that I'm most interested with MCPs. Granting full access to the CLI feels super dangerous and maybe there are options to certain commands that I want to restrict from LLM usage.
Many thanks for everything. Without Ghostty I wouldn't have been able to create https://github.com/rcarmo/webterm and have a decent browser-based terminal that works the way I expect it to.
I would concur, although I am using Edge instead of Brave (work requires it, but I also adopted it as a personal alternative to Safari for when I need Chromium).
Claude Opus was able to perfectly replicate an angular/functional part without decimating it, so I would expect the next step to be explicitly instructing AI to clean up meshes.
That's pretty impressive! However this workflow could have trouble dealing with the types of meshes coming out of those 3D generative algorithms. Geometries are arbitrary (not simple geometric shapes) so you'll have to fit with NURBS, and the meshes are noisy so that'll struggle/be somewhat arbitrary (what do you consider feature, what do you consider noise?).
However you highlight what I think is the way forward: using scriptable CAD that can leverage LLMs or, maybe in the future, specialized generative algorithms that output in a sane geometry specification.
I still call voodoo on this. I use an iPhone, iPad, Mac to comment here—all of them autocorrect to em dashes at one point or another. Same goes for ellipsis.
I doubt it explains any reasonable fraction of this, but github moving from early adopter techies to general population "normies" would be a reason for the shift. I would expect it explains at least some increase in the use of em-dashes.
You can remove em dashes from the analysis and the trend is still there: newly created accounts are still 6X more likely to use the remaining LLM indicators (arrows and bullets, p = 0.00027).
reply