keithnz

一昨日議論

I find this kind of thing too limited and you can't do much with it. I like to take problems from our domain. We work with all kinds of measurement data for agriculture / mining / utilities, I'll usually work through the problem of coming up with an alarm/alert system given a timeseries. It has relatively straight forward programming problems like simple on off threshold alerting and more complex issues like making predictors to decide when to irrigate for example. Depending on the level of the person we can do different things, talk about our domain and some of the problems in that domain. So we can go through specifying things, making design decisions, implementing an interesting aspect (usually not too complex with limited scope), next steps to build the system out, how to validate, logging, etc, feeling out how they'd approach making it production ready basically.

keithnz

3 日前議論

just get ai to generate mermaid, it's super competent at doing it, you don't really need any other tools.

keithnz

4 日前議論

thanks! Now having seen the video, certainly not as cool as it sounds.

keithnz

4 日前議論

I built some scripts to do something similar but all local. It also live updates the document so you can see changes come through. Super useful

keithnz

4 日前議論

seems odd to me also. I thought tech people would adapt and embrace (and many do!) but I'm surprised by a lot of responses on HN in the last year or so in relation to AI. Lots of quite negative takes. There is of course downsides, but this seems it is more just being cynical to be cynical.

keithnz

5 日前議論

I feel like for photos you are better off getting them done via a print service anyways, they are pretty cheap and have much better hardware

keithnz

5 日前議論

Personally I love people being excited about tech, and people who were really limited in what they could do being able to do really cool things with AI and doing all kinds of weird things with it. I find the attitude in the article really unappealing, they want to poo poo on peoples excitement over what they can do now. Try and make out its all "boring" etc, but its the cusp of quite a big change in how we interact with computers and the thing we need the most right now is people who are imagining what we can do with it. Feel free to go back to your smoking or whatever, find other grumpy cynics to complain about everything and anything while pretending you are somehow having a better conversation.

keithnz

5 日前議論

yeah, I have a cheap brother laser printer, I don't print that much, but it's been solid for several years. I did have an HP, but it was incredibly problematic, would jam rather easily. Works fine under linux as well.

keithnz

5 日前議論

not sure what it offers? potentially you might not of heard of whichkey? Also, given how little is in the repo, not quite sure why you think this is worth showing on HN?

keithnz

8 日前議論

this isn't an appropriate response on HN, please read the guidelines on how to conduct yourself https://news.ycombinator.com/newsguidelines.html

keithnz

16 日前議論

Looking for slavery, it comes up with Leviticus 25:46-49 but misses the context that starts at verse 44.

keithnz

16 日前議論

This just reaffirms my view is that big companies will lose headcount because of AI, but small and medium companies will (or at least have the potential to) leverage AI to do bigger and better things. This is because big companies could always spend big money on getting what they want made while small companies always have to tradeoff what they can realistically do with the resources they have.

keithnz

19 日前議論

was about to comment similar things! PID is relatively straightforward to tune. Also a lot of the time you just need a PI controller. D can be problematic depending on what noise you have.

keithnz

26 日前議論

what? no? people generally loved, especially with the likes of frog in a blender...

for the younguns https://archive.org/details/joe-cartoon-frog-blender#

keithnz

26 日前議論

a lot of the compatibility stuff on Linux runs windows software, so that's usually not a huge blocker. Having recently switched to Linux as my main (used to run it in a VM) the real issues are all these things that don't quite work out of the box (different distros might get different results). For instance my audio when playing dota2 would randomly cut out and not return when using discord. It took a bunch of fiddling around to get both to work. Then there's weird compatibility things depending on choices you make, for instance, I used RustDesk a lot in windows. But it doesn't really work well in linux with wayland. So while my overall experience is Linux is pretty good... I'm now in a world where I can end up with all kinds of random issues, all likely solvable, but all likely semi unique to my setup.

keithnz

27 日前議論

no, and this shows you haven't really used it, prompts are useless, access to context is what matters. It's because I have access to things that others don't that make the difference, prompts are useless unless you are accessing public information. What you and others are missing is the results are highly valuable to the recipient, assuming AI responses are garbage is just silly these days, people need to get over their obsession with "AI slop", because it isn't.

keithnz

29 日前議論

from what I can tell, you dont have to wear it?

keithnz

29 日前議論

? you missed the point, ironically showing the problem with human responses :) humans are super bad at providing information, they concentrate on singular things, especially if they think they have a point / suspect they know what the problem is, but if they are wrong their response doesn't have enough to go on, so you have back and forth.

keithnz

29 日前議論

depending on actual conditions you are in, it could potentially double (or more) the time before you die of thirst if it was your only source of water.

keithnz

29 日前議論

More and more I'm generating AI emails, often to people outside the company and often to do with technical issues / integrations we have / APIs. So far I don't think the people I'm emailing are really using AI as human responses are, well, lacking. What would be great is new email conventions for different communication pathways.

  Human -> Human (think we have this sorted)
  AI -> Human
  AI -> AI

If you are doing AI -> Human, then you need to be curating the response and understanding what it is saying, also, make sure its not leaking internal details or committing you to have phone calls/video chats (it does that). This works really well for the most, and humans respond with requested content. Quite often my AI debugs problems with their systems which I know little about. But humans do odd things like send screen shots of logs rather than text (they also leak internal details of their systems they potentially shouldn't). I used to tell people the content is partly AI, but now I just send the curated email without mentioning AI.

For AI -> AI you kind of want a hand over document as an attachment to an email. Only thing here is making sure there's no injection of security risks. But quite often instead of getting a human response to my AI generated emails, it would actually be nicer to hear from their AI which could give a better context/details. It would be really nice to be able to go, can you have your AI talk to my AI :) (security is a major issue here)

投稿

Curator – Private "End of the World" Library

Trump administration will pay $1B in taxpayer funds to not build wind farms

Kiwis travelling to US could soon face new social media screening

コメント