In other words 'just add a calculator tool' is not as sexy research-wise as making the model accurately eyeball arithmetic in its chain of thought. Maybe I'm wrong but that seems to be the case

Scientist-heavy orgs that want to solve everything in token space may overtook tool use; meanwhile Anthropic has been super focused on MCP, Claude Code etc for over a year

But I wouldn't discount how uphill it was to probably even argue for something like MCP cause the labs still very scientist-driven and focused on solving everything in token space. The idea that tool use could be super transformative probably wasn't obvious from inside before Claude Code

But let’s take my MCP clock for example if you ask ChatGPT what’s the time in Tokyo it’s not even gonna think of booting up the code interpreter. It’s gonna just do web search and give you the wrong time (I just tried it and there may be an OpenAI built in widget it pops up now—but again that’s a specific tool call with an iframe output not arbitrary code)

  > curl -s -X POST "https://mcpclock.firasd.workers.dev/mcp" -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" -d '{"jsonrpc":"2.0","id": 1,"method":"tools/call","params":{"name":"clock_get","arguments":{}}}' | grep '^data:' | sed 's/^data: //'| jq

  {"result": {"content": [{"type": "text",
          "text": "[\n  {\n    \"timezone\": \"UTC\",\n    \"iso\": \"2026-08-05T04:44:41.707Z\",\n    \"unixtime\": 1785905081\n  },\n  {\n    \"timezone\": \"Alphadec\",\n    \"alphadec\": \"2026_P4A0_466322\"\n  }\n]"
        }]},"jsonrpc": "2.0", "id": 1}

1) You're a developer 2) On a laptop 3) With a shell open inside an agentic coding harness (Claude Code, Codex CLI, Cursor) 4) Working on a software project

That's maybe 2% of AI usage.

The other 98% is: Someone on the ChatGPT iOS app asking a question on the subway; Someone in Claude.ai web chatting about their calendar; Someone using ChatGPT Desktop to summarize their Notion; A non-developer using AI in a browser at work; Voice mode on a phone; An embedded chat widget on some company's website...

I've been making a couple little utils like a Clock for AI with an open public endpoint [https://github.com/firasd/mcpclock], a text file sampler [https://github.com/firasd/vblinds] and I was noticing the MIT license seems too encumbered with the requirement to keep crediting authors downstream so I used the 'Unlicense' public domain license

(CC-0 seems to be side-eyed by open source orgs cause it preserves patent rights)

I think this article is right that definitions really matter here cause one could argue “CTM is trivial, because we can describe almost any physical system as executing computations.” So we have a dual problem here—not just the difficult discussion of ‘what’s going on in minds’, but also ‘what is computation’.

Another venetianblinds survey, of the Paul Graham 'What I Worked On' article that's used in many LlamaIndex examples:

npx github:firasd/venetianblinds pgworkedon.txt

  --- sample 1/20 char 0 line 1 col 1 range 0:60
  Before college the two main things I worked on, outside of s

  --- sample 2/20 char 3946 line 19 col 237 range 3886:4006
  d an intelligent computer called Mike, and a PBS documentary that showed Terry Winograd using SHRDLU. I haven't tried re

There is some movement in this direction--there is a new 'gh' subcommand called repo read-file for example, that lets agents view a file without cloning a repo. And I made something called venetianblinds that shows equidistant samples of a file. In combo they work pretty well:

gh repo read-file sqlite3.c --repo clibs/sqlite --output sqlite3.c && npx github:firasd/venetianblinds sqlite3.c

    --- sample 2/20 char 283427 line 5855 col 53 range 283367:283487
    le].
    **
    ** ^Closing a BLOB shall cause the current transaction to commit
    ** if there are no other BLOBs, no pending prep
                                                    ^

Let's say you want to post about 'best way to clean your car windshield'. Why would you post it on a blog when nobody will read it when the TikTok algo will at least give you a pity test to a few hundred people

So all that's left is Reddit and social media and the short form video apps (and Youtube)

The other part of course is Google itself won't rank mypersonalblog .com/i-found-a-cool-way-to-clean-windshields

So there's a doom loop... the supply of potential independent sites can't connect to audience demand, the audience is not being funneled to indie sites anyway ¯\_(ツ)_/¯ And now Reddit gets to make much dinero out of selling access for AI training cause that's the only place organic discussion happens at scale

On the other hand if the email server is down that's just as big a problem for any biz as if customer facing product was not working so some workflow things are already treated as production tier priority

Basically embracing life with full knowledge that there isn't some final transcendent epiphany or rapturous endpoint