mattw1810

All the same they choose to highlight basic prose (and internal knowledge, for that matter) in their marketing material.

They’ve achieved a lot to make recent models more reliable as a building block & more capable of things like math, but for LLMs, saturating prose is to a degree equivalent to saturating usefulness.

On the whole GPT-4 to GPT-5 is clearly the smallest increase in lucidity/intelligence. They had pre-training figured out much better than post-training at that point though (“as an AI model” was a problem of their own making).

I imagine the GPT-4 base model might hold up pretty well on output quality if you’d post-train it with today’s data & techniques (without the architectural changes of 4o/5). Context size & price/performance maybe another story though

This is no different from a web app though, there’s no obvious need to reinvent the wheel. We know how to do this very very well: the underlying TCP connection remains active, we multiplex requests, and cookies bridge the gap for multi-request context. Every language has great client & server support for that.

Instead we ended up with a protocol that fights with load balancers and can in most cases not just be chucked into say an existing Express/FastAPI app.

That makes everything harder (& cynically, it creates room for providers like Cloudflare to create black box tooling & advertise it as _the_ way to deploy a remote MCP server)

I think some of the advanced features around sampling from the calling LLM could theoretically benefit from a bidirectional stream.

In practice, nobody uses those parts of the protocol (it was overdesigned and hardly any clients support it). The key thing MCP brings right now is a standardized way to discover & invoke tools. This would’ve worked equally well as a plain HTTP-based protocol (certainly for a v1) and it’d have made it 10x easier to implement.

MCP should just have been stateless HTTP to begin with. There is no good reason for almost any of the servers I have seen to be stateful at the request/session level —- either the server carries the state globally or it works fine with a session identifier of some sort.

Their patchy JSON schema support for tool calls & structured generation is also very annoying… things like unions that you’d think are table stakes (and in fact work fine with both OpenAI and Anthropic) get rejected & you have to go reengineer your entire setup to accommodate it.

Funnily enough I recently noticed that the X app on iOS started doing this for me… on ads. If I place my finger on an ad while scrolling down, without fault it opens the ad overlay sheet. I guess that’s one way to increase CPC revenue

To be fair, in my experience ticket checking in Luxembourg was (at least in the city buses) so incredibly lax already that not a lot of revenue will be lost by this. All the same it's a nice policy though.