301–310 of 321 posts
Earlier quoted context omitted.
Lol thanks for the tip. Does it work even for normal tasks or only the long running one's?
It's not worth bothering with unless the task is very difficult, long-context, long-running, or all of the above. But, when it's worth using, it genuinely increases success rates and appears to amplify model intelligence.
Earlier quoted context omitted.
If you want frontier-level, the economically reasonable option is OpenRouter or a direct sub to frontier-of-your-choice. The reality is that they do not offer configurations that would allow a consumer to run that much VRAM on a single setup to protect datacenter margins. Apple used to, and they stopped, those devices are going for ~$20k+ each on ebay now. You can get very, very capable models on a 3090/4090/5090/600…
I truly think by 2028 we'll have integrated chip systems that'll be able to run opus 4.8 level models at ~500 watts at acceptable performance. Honestly I think now is the worst time to invest in AI hardware. Get your harness ready and processes perfected with hosted models, and wait a few years to buy hardware to transition to running models locally
Earlier quoted context omitted.
If you have solar, it is not, because you have battery and equipment degradation from cycle charging, c’mon man… I would agree with you if you said it was vastly cheaper overall (with the initial equipment investment amortized over time) compared to The Power Company. In many states, even if you are generating electricity and selling it back to the power company, they still gonna charge you normal rates of usage beca…
> if you have solar, it is not, because you have battery and equipment degradation from cycle charging, c’mon man… no, the rate of that is pretty independent of use. unless you live in a place where selling energy back rules are designed to screw the solar owner (California)
Earlier quoted context omitted.
Most of it doesn't require AI. You could generate automation scripts that do that, except of customer support. People became dependent on AI in places where it never was required and now tech bros are doing the squeeze.
Honestly, having spent a huge chunk of my career in customer support, 80%+ of the tickets could be solved with a script and not need an AI. Just about every company has a catalog of macros for answering support tickets and once you have a good set, 80% of people just need you to send them a link to the support article where you actually already answered their question in great detail, if they'd bothered to look for i…
I feel like I must have plateued and don't know what to do next to level up. I'm currently on the $100/month codex plan and it seems fine using 5.5-xhigh all the time. I think of what to do next, have a chat session to determine exactly what to ask for up to the point of being ready to implement, and then codex churns on a commit-sized task whereupon I briefly check it on my local dev server. If necessary I ask for a…
Can I ask what exactly you are building? Your experience tracks for me when building a real product -- something I want other people to use. Most of my time on these projects is spent talking to my users and carefully refining my requirements and design. For personal pet projects I can definitely see how you can blow through your token budget very quickly. If I just point my coding agent to iteratively come up with s…
Earlier quoted context omitted.
One of the best things you can do is start by having it do unit test coverage for existing behavior. A refactor with no tests breaks things pretty much no matter who does it, because they don't know what the right behavior is.
While I could generally agree, in this specific instance if the AI were “thinking” correctly it should have found the mistake. I admit it was a difficult problem though (solving it required creativity). To be more precise, the prompt actually pointed to where there could be issues, and the issue, which was exactly of the kind that was pointed at , was not found.
If you told it to write unit test coverage, you would have covered more of the codebase. That reduces the size of context necessary for the next mistake finding investigation - it'll see it's already covered a lot of the paths. Then you say "Go look for issues" (or whatever you asked it to do) and it'll be able to think more deeply about what's left over.
What specific model were you using, at what effort? How big was your context window?
Earlier quoted context omitted.
Yeah I agree. I’m “vibe engineering” an entire (non-trivial) programming language, toolchain, and standard library, as well as some smaller side projects. I leave OpenCode implementing entire milestones unattended for long periods regularly. I feel like I’d need to not have a job or a life if I wanted to exhaust the OpenAI $100 plan using GPT 5.5 xhigh, and I’ve found it insanely capable. That said, while I don’t rea…
Who is the consumer of the new language?
I'll probably throw it out on the internet someday if it gets far enough, but there are no attention/adoption related goals attached to the project.
It's currently useful for trivial scripting and iterating as and when I have time.
Earlier quoted context omitted.
Who is the consumer of the new language?
Me, to scratch an itch and because LLMs make it possible. I'll probably throw it out on the internet someday if it gets far enough, but there are no attention/adoption related goals attached to the project. It's currently useful for trivial scripting and iterating as and when I have time.
Earlier quoted context omitted.
It could put managers out of a job, without AI too, so they prefer to not use it.
What metric shows performance? Lines of code added, deleted, number of commits? None of these are are good measure of quality and actual contribution.