Given the approach from the article, you can commit the hints to git and run tests for verification. The model would be used during coding.
2,212 karma · joined July 14, 2011
But children do have access to internet and often with some protections.
This is also how I feel about AI, where a full ban is the lazy way out. Similarly like the internet, it is not possible to 100% protect a child every potential harmful AI interaction.
But ETFs do have to follow particular rules defined by their product description. So it is still interesting to benchmark against.
Maybe agentic trading still performs worse than ETFs. But alternatively, if it were meaningfully better then it would be okay to opensource, similarly how ETFs are publishing their portfolios.
An important factor is that fine tuning existing open models is incredible cheap. You can easily change any cultural biases if you want a model to be 'sovereign'. And Mistral could combine that with their custom data sets for their enterprise customer needs. Mistral still trains their own models, but they also seem to offer fine tuning existing models.
With model weights being commoditized, another differentiator could be deploying efficient inference chips, especially if you combine it with a developer ecosystem for vendor lock-in. That is why it is interesting that both Samsung and ASML are investors, since they are companies that could make a difference in this area.
My preference would be ifixit level guides where you can easily replace parts yourself. Then it would be perfect if the same servo is used everywhere so I can have 3 or 4 stored somewhere.
There are also a couple of advantages. They can take money directly from revenue before it leaves Stripes and without any processing costs. They can also invest into startups through credits and financing. And finally, their exposure to bankruptcy risk can drop as well.
And EU regulations are generally more two-sided where lots of innovations can happen by smaller marketplaces as well. Not just Amazon.
But now I use the MCP and that seems to resolve all my search problems. Now I let an agent search. Their MCP can still be improved though
Fine tuning an open model to European values is significantly cheaper than making your own model.
- Fable is more cautious
- Opus 5 gets things done in a more dangerous way
Both models score similar. The only issue is that Fable is more expense/usage limited.
On AWS EKS Fargate, each pod runs in its own dedicated VM. With Oxide each k8s node is a VM, so you still need something like Talos.
On networking it looks like it is getting closer. Where you can have external subnet give pod routed IPs without overlay. But the gap, as marked by the article, is also the load balancing.
It would be nice if Kubernetes were a native feature out-of-the-box. Also integrated within the existing user/access control.
Now with agents, you can get really bad (vibe coded) code bases in a week.
Before, to get this kind of experience, you had to work in a company for at least 2 or 3 years.
It does not cost too much effort to maintain MCP servers. No port forwarding or VPNs required thanks to OpenAI tunnels.
And security wise its quite nice, since you have to activate MCP or give permission sometimes. So each chat is kind of isolated from each-other.
In normal conditions, you use the product while it’s active. But with a server you are not daily checking.
You might have a bug in your changing limit. I think the constant higher temperature could also become an issue.