baalimago

I'm sure there are many more harnesses like Pi. Clai[0] (which I've written) is one of them. We also have hax[1] and aichat [2]. I made some additional comparisons here[3].

At the end of the day, it's quite easy to write together a bespoke agentic harness. So I'm sure there are countless additional ones. You don't really need a lib/open source one at all. Just make it write itself.

[0]: https://github.com/baalimago/clai [1]: https://github.com/OleksandrChekhovskyi/hax [2]: https://github.com/sigoden/aichat [3]: https://www.clai.chat/compare/

Do android dream of goose?

How is this cheaper than (sadly) one of the 1/1,000,000,000 humans who can do the same?

I'm wondering how it benefits Deepseek. Why would they willingly give up their trade secrets?

It's obviously very valuable, as they are running a profitable company. It follows the same trend as when they released their cache optimizations a few months back: why do it? What followed their release of this technology was that Anthropic and OpenAI silently released models which were on-par or similarly intelligent, but "surprisingly" had much cheaper cached tokens. So their inventions were obviously just worked into their competitors, who just got much greater margins + became more profitable.

The same thing goes here: I'm sure there are inventions and optimizations which are unknown to Deepseeks competitors which yet again will be worked in. So once again, they're letting their trade secrets go.

My question is: why? How does Deepseek benefit from this? There must be some gain I'm not seeing as they keep doing this play over and over, and I doubt it's "for the good of open source", as China is practically as isolated as you can get. To believe that this is in the spirit of the open source community is heavily naive.

No, and it's also not a major player in the AI race, backed by the Chinese state

I'm having trouble finding what this actually is

They're entering the search engine scene since they already have "all of the internet" stored due to the expansive LLM crawling -> training?

I don't understand why we http/1 is still around. Even worse: updated to encourage more usage.

Huge security issues involved with it, see: https://portswigger.net/research/can-ai-do-novel-security-re...

> "Can't you read? No problem, now you don't have to!"

Funny how these things work. I built slivingdoc.dev which is practically exactly the same thing.

Glad to see that my idea was on point, even though I ofc failed to make it into a competitive product.

I thought that the bulk of memory is already "technically bought" by the AI hyperscalers in the form of the big (not so) "hidden" debt? As in: the supply should already be known.

Why the need for speculation?

We Swedes also try to ignore the Danes as much as possible

Ah, so there was a solution to hinder the big-bad AI after all..? Simply... Turn them off?

> it's pretty incredible what the OpenAI team is doing

We don't know how much they are bleeding financially, it might just be a front

I never quite understood why agents should be treated as anything but normal software engineering. "Just" build a normal service and add an async call to some agentic framework, then parse the results. There is no need to "flip" this system and have the agent BE the process and invent a whole new ecosystem to manage the complexity that this flip creates.

If an agent is treated like nothing but a call to an external service (...which it is), everything fits in the existing programming paradigms. But I guess that's not very exciting. Only pragmatic.

>pretty shitty sandbox

Well, speak for yourself. My MCP servers are pretty solid.

There's nothing in the protocol making them inherently poor other than perhaps popularity, causing a swarm of people vibe-coding things they don't understand.

"We will not get off the saddle and refuse to buy a car!"

AI for proofreading/spelling correction and reordering works quite well. My words, but perhaps structured in a way which makes more sense, with sentiment replaced by synonyms.

Basically an automatic "second-pass" which I would've caught had I re-read it, but automatically.

In essence: MPC servers are the sandbox

Prompting is an art

> It’s kinda wild to me that this hasn’t been done

https://github.com/awslabs/git-remote-s3

This works seamlessly so you can run `git remote add origin s3://my-git-bucket/my-repo`