Hacker Newsnew | past | comments | ask | show | jobs | submit | michaelbrave's commentslogin

Same, I've sorta ended up converging on make a rough plan, get second and third opinions from various AI's on it, sort of decide and make choices while shaping the plan, which we turn into a detailed specsheet. Then follow the 'how to design programs' method which is mostly writing documentation first, then expected outcomes, then tests, then the functions, then test the flow of the pipeline. This usually looks like starting with Claude to write the documentation, expectations and create the scaffolding, then having Gemini write the tests and the code, then have codex try to run the pipeline and fix anything it finds that is broken along the way. I've found this to work fairly well, it's looser than waterfall, but waterfall-ish, but it's also sort of TDD-ish, and knowing that there will be failures and things to fix, but it also sort of knows the overall strategy and flow of how things will work before we start.

I'm still in the process of having to write letters to lawmakers about the stupid 3D printer law, now I'm going to have to write letters for this stupid thing too. Like how hard is it to take a day to have a conversation with someone that just knows a little bit about these things, a hobbyist even. The minimal amount of question asking, hell they could even ask an LLM and it would still give a better answer.

I keep thinking about something like a search engine integration that would suggest relevant bookmarks at the top of your search results. It might have been even cooler back when we had things like delicio.us and if we could have gotten recommended relevant links from people we followed's bookmarks too. But even knowing how to code like I do I sorta can't think of how to do it, maybe a browser extension that injects over google? I guess I've more thought about how it would interact than how to actually make it.

I use Linkding, and there is https://github.com/Fivefold/linkding-injector which does exactly what you described. I don't use it, though. Usually it brings up irrelevant results, and in the rare case that it would have brought up useful ones, the Firefox search bar history-based autocomplete got me there first.

This is bullshit. It's a clear power grab to re-seize democratized means of production, and added surveillance. Both suck. The proposed bill in Washington is even worse, and blanket bans nearly any kind of machining or manufacturing that doesn't use surveillance. I'm going to have to actually write letters to lawmakers now as if there wasn't enough bullshit happening already.


I don't think it's the fiber.

I did a similar unscientific experiment in the past where I did a juice fast for two weeks and had bloodwork done before and after (similar bodytype, unhealthy, overweight, high blood sugars, high cholesterol etc). Basically the doctor was shocked how all my numbers became the same as someone really healthy during the fast. So I think the lack of junk and calorie restriction is doing more than the fiber.


I sort of already had an experience where it did kinda. I was consulting with it potential fashion choices to upgrade my work uniform, to look professional but still creative, basically to look more like a creative director. It recommended brands, colors, styles etc. Then I was asking about eyeglass frames showed it three pictures, described my facial features and it was like "you have to buy this one now" more enthusiastic than expected. It wasn't ads or anything but there was a bit of salesyness in there.


I kinda figured they were more interested in enterprise customers rather than consumer customers.


I always kinda figured that AGI would need to be sort of similarly modeled like a brain, for which LLMs could at least fit the function for language. Meaning AGI won't be LLM based, but maybe parts of it could be.


Kinda, I mean so our brains shift once we are able to write things down instead of having to memorize completely, similarly when the internet happened we now could find answers quickly and stopped remembering or writing down things that were easy to find. So now thinking will shift again, dumber might be the right word, but it might not be, our thinking would shift away from computation type of knowledge and lean more toward making good judgments or having clearer goals type of knowledge.


that's going to be a confusing name with the connections to 3D printing


I'm not sure how it's confusing. Is it any more confusing than "v8" also being a type of internal combustion engine or blender also being a kitchen appliance?


Yes.

v8 as a drink and as an engine.

blender as a piece of software and as an appliance

filament as a physical building material and as a physical rendering material.

One of these things is not like the other (or rather, one of these things sounds very much like the other).


You can make lithophanes with 3d prints. I don't know about anyone else but that's what I thought this post would be about.


v8 is also a beverage.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: