221–223 of 223 posts
Claude recently lets you top up with manual credits right in the web interface - it would be interesting if these were allowed to top up and unlock the max plans.
When you run out of quota it presents you with options to stop, upgrade -- or I added a third option in this blog to connect to a local model until your quota resets: https://boxc.net/blog/2026/claude-code-connecting-to-local-m...
Earlier quoted context omitted.
Can you say a bit more about evals and your approach?
High level, the approach is: - I'm pain point driven: - I can't compare what I can't measure. - I can't trust to run this "AI" tool to run on its own - That's automation, which is about intentionality (can I describe what I want?) and risk profile understanding (What's the blast radius/worst that could happen) Then I treat it as if it was an Integration Test/Test Driven Development exercise of sorts. - I don't start…
Your first two points jive with my intuition that an agents primaries should be a code execution sandbox, mounted files and git.
If you have any practical examples to share I’m sure a ton of people would appreciate it.
Earlier quoted context omitted.
High level, the approach is: - I'm pain point driven: - I can't compare what I can't measure. - I can't trust to run this "AI" tool to run on its own - That's automation, which is about intentionality (can I describe what I want?) and risk profile understanding (What's the blast radius/worst that could happen) Then I treat it as if it was an Integration Test/Test Driven Development exercise of sorts. - I don't start…
This is really insightful. Thank you. Your first two points jive with my intuition that an agents primaries should be a code execution sandbox, mounted files and git. If you have any practical examples to share I’m sure a ton of people would appreciate it.
It may or may not address the practical examples you need but I'd been to hear your thoughts and maybe it's possible to come up with a more illustrative one.
I didn't go for bubblewrap or similar containers yet because I didn't want to lose a specific type of baseline newcomer yet (Economists who do some coding) but I will be adding to it with whatever most elegant approaches I can find that don't leak too much complexity for things like sandboxing, system testing, integration mocking (reverse proxying), Observing with Openteleletry or otherwise, presenting benchmarks, etc.