1,762 karma · joined April 10, 2019
The real problem with nuclear energy is, and always has been the cost. It always seems to turn into a boondoggle.
The gross thing is seeing the public cheer it on.
The second time you were much more accurate. You wouldn’t have even had to restate it differently if the first time had been accurate.
You changed what you wrote to make it accurate now, but refused to admit that and instead just prepended it with "literally"!
Wonderfully ironic given that we are talking about being accurate in your writing!
Yikes, you are doing it too. Does accuracy in prose not count anymore?
When you have a strong case you shouldn’t have to bend the facts.
"Guidance for Use"
Your preference for bullet lists over headers is odd. This comes down to what works best with the models - they are interpreting it. This is a moving target. If you believe that your suggestion works best you should provide some sort of evidence. The default would be to not even get into that sort of thing.
Non-Hierarchical AGENTS.md
Claude-code, Gemini, and GHCP all support hierarchical context files. Your proposal and this new one from OpenAI and friends do not, and I think that is a shame.
With Claude code and others, if I put a context file (agent.MD or whatever) in a project subfolder, e.g., something explaining my database model in with the related code, it gets added to the root project context when the agent is using that subfolder.
It sounds to me like this formulation doesn’t support that.
The US is making a big mistake giving up on the EV chain. In doing so it is ceding drones and robots, which are key to future wars and economies.
The countries that it is currently waging economic war against should instead be engaged in creating an alternative to the Chinese supply chain. For example, it is currently disassembling the automotive supply chain that included Canada and low-cost Mexico, but it should be doubling down on that.
And what’s worse is that the companies always seem to find a way to reset it to what they want quite frequently. One of their tricks is to reorganize permissions frequently so the ones that allow their spam to get through are always new.
And what’s worse is that the companies always seem to find a way to reset it to what they want quite frequently. One of their tricks is to reorganize permissions frequently so the ones that allow their spam to get through are always new
Dangerous incentives IMO.
In Canada, a third of the dates we see are British, and another third are American, so it’s really confusing. Thankfully y-m-d is now a legal format and seems to be gaining ground.
I guess this also helps them steer OpenAI into their orbit.