baalimago

Example: claude desktop + projects gives free compute for compilation without any cap (that I've found). So that + opus 5.5 which practically never runs out, it's possible to get thousands of euros worth per month. On Pi/similar, the tokens + compute are metered and it quickly stacks up to something substantially more expensive.

Now this is clearly unsustainable, tip is to milk the cow for as long as it's possible

Besides, do we really want memory of user A's agents to co-exist with memory of user B? Not really. So the argument for collaboration and sharing is quite slim, at least for coding agents. The repository specific context can be encoded into a docs/ or architecture/ directory, just like it's been done pre-agent times as well.

For monitoring deployed agents: maybe. For this I built (yet another) memory management tool slivingdoc.dev, with this it's possible to pull down the durable context of all agents. But here the problem is a distributed system one, not format of the memories.

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/

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.

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

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

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

Why the need for speculation?

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

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.

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.

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

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

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

An agentic system which scans a whole countries political decisions. Wrote a blogpost about it here: https://lorentz.app/blog-item.html?id=scanning-sweden

Reusable on any country's political system as long as they have legal mandates to keep political documents public (most of EU). Still a long way to go, but pretty in a pretty decent shape already. Wrote it for the Swedish election, but didn't get far enough for it to have an impact.

Will continue with for Finnish elections 2027 (on new domain).