The biggest issue I've seen with people burning through tokens is using very long sessions, especially starting with plan mode and then "iterating" over extended periods. I was burnt badly by extra usage so now I run on $20 Pro. I ruthlessly create new sessions/agents, always ask to create markdown files first (no plan mode) and minimise context aggressively - for example I have a lot of skills that use lazy loading and a small local MCP for lookups plus openrouter with a local model for image detection and fulltext search. Basically I use Claude Code in pi.dev style.
This is beautiful. I even had people reach out to me with suspiciously long "long time no chat" instant messages until I realised they were AI written (in one case misspelling the name of their own partner). "If you are requesting human attention, demonstrate human effort" is going to be my new answer to that!
This is exactly the same as the ""If you didn't take the time to write something, I'm not going to the take the time to read it" mantra that was floating about HN a few months ago.
I think in many cases people use LLM outputs without even understanding the contents of it. You're only really able to say something in your own words if you understand it. As a matter of fact, it is a good way of probing if you truly grok something. So it isn't just laziness to write, but also laziness (or inability) to understand.
> Ban the domestic use of fully autonomous weapons.
"Domestic" is an interesting shift here from the earlier _general_ discussions on autonomous weapons. So robot imperialism is good for Dario. But the imperial boomerang is a thing, in which case the proposed regulation itself is smoke and mirrors or just regulatory capture?
> workflow improvements that would have taken days or weeks of engineering
It's a nice article and good point but I feel "design" in the title is misleading - the example given has an extremely reduced visual or spatial scope (something models are still not good at). The post is more about rapid prototyping.
I find it so interesting "Agent legibility is the goal" picks up James C. Scott term (without defining it, so I assume that's what they mean) which is _not a good thing_. Legibility is a governance effort to box in life.
Great post showing the ironic revenge of opinionated architecture in times of cheap code. Exactly what LLMs can’t deliver, they always seem to be bias towards added complexity, not simplification.
Outsourcing usually gives you exactly what you pay for, arguably more transparently than other ways. It’s just that transparency (i.e. the price for quality) is sometimes not passed on from management / procurement taking that decision down to the team eventually having to work in a distributed fashion.
I think that’s also where the assumptions of the original post are off - the difference between DeepSeek and a frontier model is not usually what low quality outsourcing can cover. So you probably end up paying a highly qualified outsourced engineer who may not be significantly cheaper (most outsourcing is not just due to cost but capacity and capability).
I agree the post looks a little AI written but generally this kind of analysis is quite common. Leaving aside human heuristics that are generally too well known to catch real scammers (like time travel or "7 days", which is bad because often weekly patterns are important so at the very least look at 10 days) and actually have low precision, what I find odd it that all results just return a user ID.
So this is really just surfacing cases, but with not enough context to be useful to prioritise. I would expect a score to be included.
Apart from that it misses a lot of signals like refunds, declines, disputes etc [1].
Thanks for clarifying the rule - I wasn't aware of that and follow it next time. But I also don't think it's a marketing link. The post explains why specifically in the cases of transaction fraud other signals are important, with specific SQL examples, and that should translate to any other payment provider.
reply