korrents
Rui Carmo

What Rui Carmo thinks about LLMs

@rui-carmo · 18 positions · On ppll ↗

Portuguese engineer and blogger; writes Tao of Mac, a personal site with entries going back to 2003, on Apple hardware, Linux, home labs, programming and AI coding agents. His Bluesky profile lists him as a principal at Microsoft.

Rui Carmo did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

Filter LLMs · Newest first
Topic
All 18LLMs 5AI agents 4Apple 3developer tools 2coding agents 1design 1JavaScript 1management 1MCP 1
3 more topics
Python 1software quality 1the cloud 1
Sort
NewestOldest

Only Rui Carmo on LLMs. See everyone on LLMs

5 dated positions, 2026, in their own words. Our reading of what Rui Carmo has said — not written or endorsed by them.

  1. Our readingAI is unlikely to be much help with managing personal life processes beyond removing toil.

    Their wordsAnd I think AI is not going to be much help with that, other than remove toil (yes, it will sort out your inbox for you and research your travel itinerary).

    ↗Sep 30th 2026 · 2 min readtaoofmac.com 2nd of 3 in this piece

  2. 5 months earlier

  3. Our readingModels do not possess a hidden planner and instead react to the conversation and tool list.

    JavaScript

    Their wordsModels don't plan They look at the conversation, scan the tool list, and grab whatever looks more probable. That's it. There is no hidden planner.

    ↗Apr 29th 2026 · 6 min readtaoofmac.com 1st of 3 in this piece

  5. Our readingSmaller models require explicit breadcrumbs in responses to successfully follow tool chains.

    Their wordsThe big ones will plan a chain from a tool list and a goal; the wee ones won't-they grab the first plausible tool and stop. The fix is stupid simple: every response ends with a breadcrumb dictionary of hints to follow.

    ↗Apr 29th 2026 · 6 min readtaoofmac.com 2nd of 3 in this piece

  6. 7 weeks earlier

  7. Our readingThe gap between local and cloud AI models is significant, and even high-end hardware cannot match frontier cloud capabilities.

    Their wordsNone of these things are really "local" in any meaningful sense-the gap between local and cloud models is huge, and even tens of thousands of dollars in hardware won't get you close to frontier capabilities.

    ↗Mar 8th 2026 · 5 min readtaoofmac.com 1st of 3 in this piece

  9. Our readingThere is an unwarranted hype cycle regarding the capabilities of local AI models.

    Their wordsAnd there is an almost weekly hype cycle around local models that I think is totally unwarranted in practice.

    ↗Mar 8th 2026 · 5 min readtaoofmac.com 2nd of 3 in this piece