tmjdev

I couldn't get it working with lmstudio. I have bonsai-8B running with llama-cpp and am attempting to build a harness for it. Looking good so far, I just got it started but Forge made tool calling work pretty quickly!

Very impressive. Unsure what is going on with the tool icons, they're a bit strangely named. "Bessel", "pour corner" (twice), "From the cross section".

Looks like some work needs to be done to get this into familiar CAD terms with the English translation.

Difficult to use right now, it just switched into the Chinese translation when trying to make a cube and there doesn't appear to be an easy way to change that.

I always see articles about the decreasing cost of solar, but where are these costs collected from? Is it just not available at a consumer level? Maybe I missed the sources in the article somewhat...

I think this just illustrates why hidden state is so difficult for the user. It's hard to replicate old calculators because it was poor UI that was making do with what was yet available.

I've read this many times over the years, sort of enamored by how such a strange phenomenon popped out of a factory setting.

In the most 2016 update the relative says it's common to see weird effects from the spools. If it's so common it should be reproducible I would think, yet I've never seen it done.

I like to preface negativity with a positive note. Maybe I am influenced in my word choice but my intent was to point out that this is a very, very impressive feat and I don't want to undermine it.

While it is impressive and I like to follow the advancements in this field, it is incredibly frustrating to listen to. I can't put my finger on why exactly. It's definitely closer to human-sounding, but the uncanny valley is so deep here that I find myself thinking "I just want the point, not the fake personality that is coming with it". I can't make it through a 30s demo.

Guardrails seems to be a common argument. It feels heavy handed though to use an entire library/ecosystem to ensure you don't have typos, your tests should catch them anyhow.

And migrations are a separate feature that a number of ORMs have, you can have clean migrations with pure SQL using a tool like gomigrate.

I think the real utility is that the ORM is doing the marshalling for you.

It looks like as an ORM gets more expressive it looks more like regular SQL. What is a reasonable argument for using an ORM over writing SQL?

I always feel like I'm missing something because it looks like you have to learn a specific library instead of a general purpose language.

Agreed. I think the earlier days of Angular put a bad taste in many people's mouths. Many people who complain about Angular being verbose seem to only have experience working on smaller apps.

I thought this was a joke at first. He says he "feels great" but I can't help but be skeptical about that claim. Maybe I'm soft because I think a 40 is reasonable and prudent.

To say it another way, you should not expect more code to be merged in the same amount of time as less code. 250 lines is 5x more code, so what is the purpose of a statistic showing 1/5 of the code gets merged faster? That's not a good or a bad thing.

Unless the metric is actually 40% faster per LOC but that's not specified.

"Your current suffering is small because somebody else suffered more."

Or, more commonly, "You think you have it hard? I know a guy who went through XYZ."

Sometimes people need perspective when they feel times are tough, other times they just need sympathy.

I am curious if there has been any research on temporal attention in humans. I'm not sure how you'd quantify it. But in myself I know that I'm constantly predicting where something will be or what it will look like based on how it did a second ago. It's probably the root of reflexes.

This looks like the video equivalent of Dall-E 1. Hard to believe how far we've come so quickly.

The paper talks about "pseudo 3D attention layers" that are used in place of temporal attention layers for each dimension due to memory consumption. It seems like AI research is vastly outpacing GPU development.

I feel it's the typical HN reaction to be negative about generated content. I enjoyed it. I think it could have used another pass on editing but I felt the idea was interesting and I wanted to hear it through.

This is something I have noticed with a lot of models. I'm not sure what the technical term for it is, but when there is a repeated sequence of human input with model generation following (like a chatbot) it seems to be unable to focus. When you prod it to regain focus and come back to the topic being discussed it starts making up lies.

If you use GPT3 for a large amount of content generation the issue of focus doesn't seem to be so prevalent, but it has zero guarantee of truth.

If it was the ratio being studied, could you instead increase your n3 fat consumption?

This is my major gripe with the college courses I took. They start at the molecular level and build to the planetary scale. This works for some people, but for me I had the hardest time finding a personal interest until I got to the application. It was the application I wanted to build, and to do actual work you don't manipulate the molecules directly.

Build an application, then as you need to learn more to get things done you naturally pick up a deeper knowledge of the tech you're using.

Of course this is different for everyone.

I know, it's not a good trend.

There are a lot of jobs listed there with zero benefits listed in the actual job listing. You have to scroll >1/2 down the page to find out what the benefits are and those are fairly vague. Why isn't there at least compensation listed?

Ben Stokes is an inspiration to me. I get excited reading any of the TinyProjects posts. It's so refreshing to see a solo dev building and shipping so much. Hoping I'm tracking for that kind of ability as a full stack dev.

I really like them as well. I enjoy them as a digital art form.

From what I understand, Scott Turner (Here Dragons Abound) got his inspiration from Martin O'Leary[0]. Lots of interesting reading on his site.

Another one in current development but as far as I know doesn't have a devlog quite like Scott Turner's is Azgaar's Fantasy Map Generator[1]. He did keep a devlog until 2018 sometime though[2].

Watabou's Medieval Fantasy Map Generator[3] is really good.

I'm sure I've seen more over the years but these are the ones I can remember.

[0] http://mewo2.com/notes/terrain/

[1] https://github.com/Azgaar/Fantasy-Map-Generator

[2] https://azgaar.wordpress.com/

[3] https://watabou.itch.io/medieval-fantasy-city-generator/devl...

We are in a very similar situation. We've given up so many niceties of modern housing to be able to build. Currently we live in a trailer that was in disrepair years ago. It's a stepping stone to our eventual home.

I feel you on the losing the mind over matter aspect. I simply cannot let that happen to myself though, since for some reason it's deeply ingrained in me.

Often I do exercises to try and extend my ability to overcome the internal desire for creature comforts. Things like swimming through the ice in frozen lakes, staying in the sauna beyond my pain threshold, fasting, picking a particularly difficult physical exercise and pushing my limit (common in weightlifting, pushing past the burn), things like that.

I try to make sure I'm not finding pleasure in the pain, however, since that is in the realm of masochism and I feel that is the path to self-destruction.

Does anybody else do this? What else do you do?

It was that 'carrying the family flag of engineering' thing. This notion that engineering was a safe bet and I should do it if I could. Very little to do with my actual interests. Not to say I don't enjoy electrical engineering. I just don't enjoy the work.

After creating many tools for the companies I worked for it became clear to myself that I should have done that in first place. My advice to you would be to take more CS classes to see if that's really what you want to do. A small price to pay now and will give you a better idea of what you want to do.

That being said, my experience (electric utility manufacturing, military truck electrical systems) was very valuable to my broader understanding of how software is consumed.

I should mention that coding had been an early interest of mine. In middle school I put custom firmware on my PSP so that I could use a homebrewed version of YouTube to watch a series of "Learning C++ From Scratch" videos at night. Had somebody noticed that interest I could have been encouraged early on that that interest could actually be a profitable job and not just a hobby.

This resonated with me. I actually took that road construction job as a flagger. I stood there turning that stop sign back and forth, directing traffic, for a whole summer. I felt, and still feel it was the lowest point of my career. My brain was starved in the truest sense of the word and it gave me new fire to complete my college degree.

Which was Electrical Engineering. I didn't learn that I really should have gone for computer science, computer engineering, or something along those lines until after 5 years of work in the industry. I was just carrying the family flag of engineering.

I contracted with a friend's company after telling them that I needed a change of work and was interested in software. After telling them I had zero professional experience writing code (two CS classes in college), they assured me they would get me up and running.

Now here I am as a full stack engineer just over a year later. I really don't know how I got here. But I do know that this type of work is incredibly gratifying and I should have pursued it early on.

Somehow as I grew up I got the idea in my head that work should be your personal crucible and that loving work was really a sign of workaholism. So I always took those jobs that were miserable just to get a paycheck. I hope I can help my kids find work best suited for them.