Viewing profile — keithwhor

The economics of production cost, investment and distribution have created a lopsided industry where only guaranteed hits get funded. Less soul = pandering to more people. With new…

My guess is that intelligence gets commodified to the point where LLMs and diffusion models are sold on chips and we seamlessly integrate them into the HW + SW stack. Then they’re …

A friend and I are working on something like this. It’s more Slack-adjacent; the problem we’re tackling is, “what does a future where agents seamlessly integrate with day to day co…

Employee A: $2,000 / mo inference spend (eg Claude code). Ships 5 features a month. High impact. No bugs. Employee B: $100 / mo inference. Otherwise identical. Does Employee B dese…

One that goes boom.

You’ve just described what Roblox is already doing.

It’s also possible for LLMs to be inevitable, generate massive amounts of wealth and still be mostly fluff in terms of objective human progress. The major change from my perspectiv…

I think it's likely we learn to develop healthier relationships with these technologies. The timeframe? I'm not sure. May take generations. May happen quicker than we think. It's c…

I am building a company in this space, so can hopefully give some insight [0]. The issue right now is that both (1) function calling and (2) codegen just aren't really very good. T…

I think this is a cop out. OpenAI literally published a better integration spec two years ago, stored on `/.well-known/ai-plugin.json`. It just gave a summary of an OpenAPI spec, w…

In the grand scheme of things I think we are still very early. MCP might be the thing which is why I'd rather try and contribute if I can; it does have a grassroots movement I have…

Quick follow up: I anticipate alignment issues as well. Anthropic is building MCP to make the Anthropic experience great. But Anthropic's traffic is fractional compared to ChatGPT …

On MCP's Streamable HTTP launch I posted a issue asking if we should just simplify everything for remote MCP servers to just be HTTP requests. https://github.com/modelcontextprotoc…

I've been programming since I was eight, but truly fell in love with biology in 12th grade chemistry: the first introduction to organic chemistry and biochemistry. It was the first…

I mean you don’t need gRPC. You can just treat all tool calls as SSEs themselves and you have streaming. HTTP is pretty robust.

At least this uses existing standards, which was my biggest gripe with MCP. That said - protocol whiplash. And it might get worse.

If this is a bet, I'll happily take the other side and give you 4:1 on it.

I don’t disagree. I fought this battle for a long time — ran a company where I tried to simplify SDK development by making every endpoint POST and JSON params; sorta like SOAP / ju…

That makes sense. But if that's the case I think we should call a spade a spade and differentiate "Local-first MCP" and "Remote MCP"; because what (many, most?) companies are reall…

Would disagree there — system integration probably accounts for like 90% of development work; just at different layers of abstraction. It’s evergreen work that companies are endles…

This is very cool but definitely has the XKCD standards vibe [0]. If the industry is standardizing on MCP but then we decide it's not good enough, we just end up back where we star…

The good thing to note is that (AFAIK) MCP is intended to be a collaborative and industry-wide effort. Whereas plugins was OpenAI-specific. So, hopefully, we can contribute and hel…

The `stdio` approach for local services makes complete sense to me. Including using JSONRPC. But for remote HTTP MCP servers there should be a dead simple solution. A couple years …

Today MCP added Streamable HTTP [0] which is a huge step forward as it doesn't require an "always-on" connection to remote HTTP servers. However, if you look at the specification i…

Great read. I think connecting with nature while you’re young is great — when you’re older, even better. Would love to read more of these.