In Portugal it is part of the standard curriculum although in my time they were poorly motivativated and besides solving some classes of quadratic equations no other applications were mentioned.
I don't think you're taking my "there's two sides to regulation" comment in good faith.
I gave a pretty clear example of pro-consumer regulation myself.
Saying that the EU is overregulating cannot possibly be that controversial, given that even the European politicians are beginning to admit it.. Draghi, Von der Leyen (even though she passes blame), Merz, Macron.
- the overregulation narrative conflates two different problems
- and that you minimized too much the consumer benefits of EU legislation
I think the overregulation problem olis less that we have 200 EU regulations and we need to hack and slash 100 of them and more that we have 100 national regulations 25 are exact transcriptions of EU directives, 25 are transcriptions with tweaks and the other 50 are national scoped regulations and what we need to do is to make them uniform so that companies don't have to deal with 27x75 problems.
I'm a bit burned by politicians using the overregulation narrative and then not specifying a single example of a meaningfull rule that they would get rid of. Usually what is left in the air is that worker rights and consumer rights should be cut.
This was an half usefull joke. I can still make it with the exterior unit off for an extra 1 or 2 degrees with just the interior unit blowing during the day and the use the AC to cool during the night when it is more efficient.
In any case where I live fans are not a meaningfull stopgap measure.
> A very personal view but many developers/engineers fail to see the overall picture. And yes, I was there and I went through all of the mistakes.
What is failling to see the overall picture? I hate this overall picture mysticism. I bet that if people where given the same role and information as the CEO they would be able to see the overall picture.
I’ve also found that Claude and friends are eerily good at using classic Unix CLI tools so I build mine in the same style, not unlike the `gh` CLI from GitHub, though with an agent-first design shape.
Usually I’m returning TSV as a default format and I add a `help-all` subcommand to list every available command at once when needed. Another thing that helps is adding just-in-time context-sensitive hints, such as: user has just run a list query with at least one result. Add a one-liner to the response explaining the command shape for getting the detail view of the first response.
In terms of skill files, I like to have my CLI generate them dynamically at runtime by walking their own current command tree and then feeding that through a text template.
Yeah the CLI can provide schema for commands via the usual ‘—help’ syntax, so agents are able to discover + explore commands on their own.
As for an example: if our agent wants to book a journal entry to cash accounts for a client, it MUST provide receipt and directly link the transaction from the clients bank feed, if it attempts to do so without the requisite information we deny the tool call and ask the agent to escalate back to the client for proof of receipt.
Often times this results in the agent not doing the work and instead sending a message back to the client asking for proof of the transaction.
For humans on our platform there may be valid situations where we’d want to allow this, but for our agent this is a hard guardrail thus why it’s not just standard validation for any JE posting on our platform.
if our agent wants to book a journal entry to cash accounts for a client, it MUST provide receipt and directly link the transaction from the clients bank feed
It’s actually encoded in an abstraction that we call “gates” which run before any tool call an agent makes, this allows us to prevent the tool call from happening and return a cited code + explanation on why their tool call was not executed
