Preferences

Sammi
Joined 2,057 karma

  1. Honestly the index seems as much a liability as a boon. Keeping the context clean and focused is one of the most important things for getting the best out of lmms. For now I prefer just adding my md files to the context whenever I deem them relevant.

    Skills are much simpler than mcps, which are hopelessly overengineered, but even skills seem unnecessarily overengineered. You could fix the skill index taking up place in the context, by just making it a tool available to the agent (but not an mcp!).

  2. Yes exactly. Skills are just sub agents.md files + an index. The index tells the agent about the content of the .md files and when to use them. Just a short paragraph per file, so it's token efficient and doesn't take much of your context.

    Poor man's "skills" is just manually managing and adding different .md files to the context.

    Importantly every time you instruct the agent to do something correctly that it did incorrectly before, you ask it to revise a relevant .md file/"skill", so it has that correction from now on. This is how you slowly build up relevant skills. Things start out as sections in your agents.md file, and then graduate to a separate file when they get large enough.

  3. Even that isn't generic and broad enough. I've noticed so many people mean SaaS when they say cloud. That isn't even a hardware or server or infrastructure meaning. It's referring to a whole cohesive IT product that you subscribe to.

    Actually I'd say "cloud" says more about the business model than it says about the actual product.

  4. Cloud must be the most uselessly overloaded term ever. I have no way of knowing what you are actually talking about when you use it.
  5. A country building out its export industry means more people get jobs and out of poverty. Chinese leaders didn't do it for the benefit of their people. They only do anything in order to stay in power inside of the party so they can be rich. That's how the Chinese political system works. Please stop it with the Chinese leaders are benevolent narrative. It's clearly bunk.
  6. I don't remember Black Mirror writing this episode. But I didn't watch the latest season either.
  7. It's like saying in the 1970s that people would become dumber because of calculators. It's a tool. You can use it lazily and not learn much, or you use it actively as something that propels you further along in your learning.
  8. You probably need to add some visual indicator that the generation is ongoing. A progress bar is ideal, but those can be hard to feed with real data.
  9. There's an easier fix. Have the candidates state if they have a vision disability first and then send them down a different pathway for validation. There aren't that many, so it's not going to be costly or anything.
  10. Sure. In theory people could be doing that. But for the third time: what is happening in practice?

    What people _could_ be doing vs what they _are_ doing was explicitly my point, so please stop pretending it wasn't, less we have to repeat this merry go round.

  11. You are mixing theory with practice. In theory felines can be both cats and tigers. In practice the felines walking around your neighborhood are all cats.
  12. In practice today JSDoc 100% completely and utterly always is Typescript.

    It might not have been so originally. It might still be possible to do differently. But in practice today you are getting Typescript in your JSDoc with the out of the box tooling that is everywhere.

  13. I'm kinda confused about why this even is something that we need an extra feature for when it's basically already built in to the agentic development feature. I just keep a folder of md files and I add whatever one is relevant when it's relevant. It's kinda straight forward to do...

    Just like you I don't edit much in these files on my own. Mostly just ask the model to update an md file whenever I think we've figured out something new, so the learning sticks. I have files for test writing, backend route writing, db migration writing, frontend component writing etc. Whenever a section gets too big to live in agents.md it gets it's own file.

  14. * sorry, I accidentally a word
  15. I don't have a degree in low voltage electrical engineering, but haven worked close to people who are this does all look like grunt work in that field. So maybe get a bachelor in low voltage electrical engineering? It's all as much digital/computational as it is actually physical these days. Lots of educated electrical engineers end up as software devs, often doing the low level coding. Bootloaders, firmware, and drivers are stuff you have to figure out if you want to get modern electrical hardware to do anything.
  16. > Naturally workers will begin to prefer the motions of the work they find satisfying more than the result it has for the business's bottom line, from which they're alienated.

    Wow. I've read a lot of hacker news this past decade, but I've never seen this articulated so well before. You really lifted the veil for me here. I see this everywhere, people thinking the work is the point, but I haven't been able to crystallize my thoughts about it like you did just now.

  17. > Software estimates are not futile or make believe. They are useful even if they are not always precise. That’s why the industry continues to use them.

    The industry continues to fail when trying to use them. They have negative usefulness.

  18. There's is no fair comparison to be made here with how + and * work is most languages, precisely because + and * work the same in most languages, while whatever perl is doing here is just idiosyncratic.

    Even C gets it's fair share of flack for how it overloads * to mean three different things! (multiplication, pointer declaration, and dereference)

  19. This seems like a synonym for botnet.

This user hasn’t submitted anything.