Maybe I just lack imagination, but I don't really know how jobs are supposed to solidify around the role of giving prompts to agents and then looking at the results. I mean, engineers will be in the breadline because their role was simply to prompt the agents.. only to be superseded by managers or executives who no longer manage engineers but themselves prompt the agents? And, for this previously considered obsolete function which they do presumably by copy/pasting requirements from their email inbox, they will be paid by someone who doesn't know that they could just be talking to their own agents?
Sorry if I misunderstand the point, just trying to understand.
If it's samey regardless of language, isn't that in contradiction to your original theory? " .. the most important feature for agent performance is the popularity of the language .. "
POGOs are criminalized and often operated by illegal immigrant Chinese people, it's not really representative. At least that's my understanding having lived in Manila for a few years.
I mean, we view social networks as having network effects that keep people there. The same force that stops people from switching from Facebook and TikTok prevents people from abandoning social media altogether. Waiting for all the adults to be responsible and forward thinking seems a little far fetched.
I'm not in favor of these social media bans, but I would think the benefit here is that without the ban your child will be in the "real world" while everybody else's is on social media. This would make the "real world" socialization benefits more difficult.
Aren't they related in the sense that they're not tech/SaaS/software related? "I'm looking into being an elevator mechanic; I need the money because my wife is pregnant." and then "I'm writing poetry by hand." Like, their life is going in a non-tech direction?
Who do you imagine the winners and losers will be? To the extent AI is useful and disruptive, it's best utilized by people with capital. Which is to say, the winners are few and the losers are everybody else. In this case, the losers aren't just more vocal, they're louder and more visible because they're much more numerous.
How am I being virulently anti-AI? I've been a Claude Code max subscriber for many months and find it very helpful. It feels a little unfair to conclude that any criticism is just unfounded fear and insecurity..
I could also include the correct implementation for it to copy in the prompt, if you get what I'm trying to say. Some amount of laziness or vagueness in the prompt is an intended use case, it's surely the point of having the subagents do so much churning of tokens to research before writing the plan that I'm about to disregard. But sure, those are helpful tips.
You're right. I think having it spawn lots of subagents, read everything, formulate a big and detailed plan, only for it to be subtly wrong while requiring me to carefully review the result and the intermediate plans that produced it is quite tiring. I suppose things slip through.
Plan mode improves results, but it doesn't solve the underlying problems. Pretty often Claude Opus 4.7 on xhigh will formulate a reasonable enough plan, churn for a while, then come back with a summary that it didn't stick to the plan because it wasn't accurate.
Worse, the disclaimer is buried under a bunch of "did X, did Y on line Z of file a/b/c", as if it's just a minor inconvenience. To the extent the plan was inaccurate, you're left in an undefined state where you might as well undo what it just did..
I wouldn't use any provider: z.ai, Claude, OpenAI, ... if I was concerned about the government obtaining my prompts. If you're doing something where this is a legitimate concern (as opposed to my open source stuff), you should get a local LLM or put a lot of effort into anonymizing yourself and your prompts.
I got their z.ai plan to test alongside my Claude subscription; it feels about on par with something between sonnet 4.0 and sonnet 4.5. It's definitely a few steps below current day Claude, but it's very capable.
I've had the $20/month plan for a few months alongside a max subscription to Claude; the cheap codex plan goes a really long way. I use it a few times a day for debugging, finding bugs, and reviewing my work. I've ran out of usage a couple of times, but only when I lean on it way more than I should.
I only ever use it on the high reasoning mode, for what it's worth. I'm sure it's even less of a problem if you turn it down.
Dafny and similar languages use SMT; their semantics need to be such that you're giving enough information for your proof to verify in sufficient time, otherwise you'll be waiting for a very long time or your proof is basically undecidable.
I'm not sure about benchmarks comparing languages, but Dafny goes through a lot of tweaking to make the process faster.
Is that interesting? Computers accomplish all sorts of tasks which require thinking from humans.. without thinking. Chess engines have been much better than me at chess for a long time, but I can't say there's much thinking involved.
I admit that when reading the description of your relationship (I don't mean to be disrespectful, for what it's worth) I can't help but wonder how it can possibly be consistent with "a relationship between two people can be basically whatever they want it to be." It really reads like the relationship is whatever _she_ wants it to be.
If you had come into the relationship with the understanding that you'd both date/have sex with other people then great; it doesn't matter what other people think. However, when you say that it was hard for you to accept her being with other men, and that you're lucky that "she has never fallen in love and wanted to run away with one of em", damn. My first instinct is that you should take your own advice: find or design a relationship where you don't have to accept this.
I realize that some of my knee jerk reaction might just be instinct/cultural values, I mean no disrespect.
You're proposing a truism: if you don't get a good result, it's either because your query is bad or because the LLM isn't good enough to provide a good result.
Yes, that is how this works. I'm talking about the case where you're providing a good query and getting poor results. Claiming that this can be solved by more LLM conversations and ultrathink is cope.
I've read your questions a few times and I'm a bit perplexed. What kind of answers are you expecting me to give you here? Surely if you use Claude Code or other tools you'd know that the answers are so varying and situation specific it's not really possible for me to give you solid answers.
I have a Claude max subscription. When I think of bad Claude code, I'm not thinking about unused variable definitions. I'm thinking about the times you turn on ultrathink, allow it to access tools and negotiate it's solution, and it still churns out an over complicated yet partially correct solution that breaks. I totally trust Claude to fix linting errors.
I don't really understand your point. It reads like you're saying "I like good code, it doesn't matter if it comes from a person or an LLM. If a person is good at using an LLM, it's fine." Sure, but the problem people have with LLMs is their _propensity_ to create slop in comparison to humans. Dismissing other people's observations as purely an emotional reaction just makes it seem like you haven't carefully thought about other people's experiences.