Tobias Lohse
banner
mrloh.io
Tobias Lohse
@mrloh.io
I love your writing. But this is a bit confusing. Since AI doesn’t really have a memory. Just telling it something in a chat won’t alter its behavior beyond that chat (and depending on the provider maybe the next few chats). Some providers allow for global context. But AI cannot remember or learn.
October 13, 2025 at 1:30 PM
Yeah there’s a few blogs using it as the commenting system these days. You could build much more with the AT Protocol, but my current implementation is pretty simple github.com/MrLoh/mrloh....
mrloh.io/app/blog/[slug]/Comments.tsx at main · MrLoh/mrloh.io
Contribute to MrLoh/mrloh.io development by creating an account on GitHub.
github.com
June 13, 2025 at 2:00 AM
Any replies you leave here on Bluesky will show up as comments on the blog post.
May 27, 2025 at 2:43 AM
I think the biggest gap is the lack of a server side middleware for actions. I’m currently rolling my own, but it requires a lot of documentation and is a steeper learning curve for other devs on the team than if react had something built in that would allow injecting context via middleware.
April 26, 2025 at 3:18 AM
Yeah that’s one of the downsides of not having HTTP verbs with standardized idempotency. I’m currently handling this by sending results over the wire and having shared functions which handle appropriate error UX and could do things like retried.
April 26, 2025 at 3:16 AM
I wouldn’t write an API without a framework that helps with handling session/db/etc. context management and I don’t usually call fetch without a client that handles retry logic and standard errors.
April 26, 2025 at 2:20 AM
I think the directives are a great evolution from tRPC and use client feels very intuitive. The only thing I struggle with is the lack of middleware on both the client and server side of the action.
April 26, 2025 at 2:17 AM
I moved on to ai.pydantic.dev now which looks like it’s built by engineers who actually know modern Python well.
PydanticAI
Agent Framework / shim to use Pydantic with LLMs
ai.pydantic.dev
March 26, 2025 at 2:45 AM
Also the whole event thing is build in a way that you have to declare types that you don’t adhere to if you use parallel dispatching of events and collecting them. Tons of different examples in the docs and examples raise type errors. It’s embarrassing.
March 26, 2025 at 2:43 AM
`llm.structured_predict` wraps an OpenAI method that has proper generics and drops them to return `BaseModel` that is way way worse than returning Any since it means now you can’t use this code without doing a cast or type ignore statement.
March 26, 2025 at 2:42 AM