netcraft

this is exactly my question. I would expect that luna is analogous to mini before, but is terra equivalent/better than 5.5 and Sol is a step above? or is terra nerfed and 5.5 is analogous to sol?

Location: Memphis, TN

Remote: Yes (Only)

Willing to Relocate: No

https://ryanguill.com

https://www.linkedin.com/in/ryan-guill-92034a1/

CV: https://ryanguill.com/resume/

I am an experienced, driven, motivated engineer who is looking for high-agency, high-impact problems to solve. Bonus points for roles that are a positive impact on society.

Looking for remote roles in majority remote teams. I'm comfortable in startups and large corporations, I just want to ship fast on things that matter.

Postgres/Snowflake/DuckDB, Typescript, Python, AWS, Docker, LLMs and related tech - but I love learning new languages. I ask a lot of questions, and think in terms of processes and systems. I use and build agents and love a good SQL query.

email: ryanguill+hn@gmail.com

huge if true had an episode about this recently https://www.youtube.com/watch?v=0HlLwG2xN_c

I think its understandable that you took that from the click-bait all over youtube and twitter, but I dont believe the research actually supports that at all, and neither does my experience.

You shouldnt put things in AGENTS.md that it could discover on its own, you shouldnt make it any larger than it has to be, but you should use it to tell it things it couldnt discover on its own, including basically a system prompt of instructions you want it to know about and always follow. You don't really have any other way to do those things besides telling it every time manually.

the day ends in y, water is wet. I really hate that github doesn't have any real competition. Yes, I know about gitlab, but it isnt real competition.

unfortunately im not in the same situation. I have a high incidence in my family, my calcium score wasn't clean (especially for someone my age) and my vo2max isnt the best either. Though my many stress tests have always been fine.

I don't think im in terrible shape right now, but looking ahead 10 to 20 years, without medical intervention I probably would be.

yes, changed to a stronger statin.

yes, changed to a stronger statin.

I have high cholesterol, have had for more than a decade. Was on a statin, they didnt help. Doubled them, they didnt help. Changed my diet radically, lost 25 lbs (I was a little overweight, but not bad), ate full medeteranian diet and did everything I could, my numbers didnt budge. Changed to a stronger one and within two weeks my numbers were perfect.

I believe for some of us its purely genetic.

agree completely. I used to be (and still would love to be) a process person, enjoying hand writing bulletproof artisanal code. Switching to startups many years ago gave me a whole new perspective, and its been interesting the struggle between writing code and shipping. Especially when you dont know how long the code you are writing will actually live. LLMs are fantastic in that space.

Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day.

This is true to an extent for sure and they will go much longer than most engineers without getting "tired", but I've def seen both sonnet and opus give up multiple times. They've updated code to skip tests they couldn't get to pass, given up on bugs they couldn't track down, etc. I literally had it ask "could we work on something else and come back to this"

thats a very generous way of putting it. Anthropic's prompt caching is actively hostile and very difficult to implement properly.

I love duckdb, I use it as much as I can. I just wish that the support for node/bun was as good as python. And I wish that they would bundle it differently for node/bun - the way it is now it depends on a dynamic link to a library which means I cant bundle it into a bun executable.

I was also a bit skeptical, but chatgpt gave a pretty good answer I think: https://chatgpt.com/share/69553e26-ea28-8011-bc17-8658fbea4e...

Buildings with higher people/sqft could already take advantage of indoor co2 scrubbers today.

160F, non toxic, this already sounds like something that could feasibly be used in the home. I would already be interested in installing one. And would absolutely love to see what it would do to school performance.

The hard part is capture and disposal.

I think the reason python won was that it was easy to learn and read and was batteries included. vs perl: People need to solve their problems, not fight with syntax

Theres a lot of network effects as well. The more people were using it, the more people will use it.

better link: https://earthquake.usgs.gov/earthquakes/eventpage/us6000rtdt...

couldn't have said it better myself.

Data should be data, queryable, relational. So often I have had to change enums into lookup tables - or worse, duplicate them into lookup tables - because now we need other information attached to the values. Labels, descriptions, colors, etc.

My biggest recommendation though is that if you have a lookup table like this, make the value you would have made an enum not just unique, but _the primary key_. Now all the places that you would be putting an ID have the value just like they would with an enum, and oftentimes you wont need to join. The FK makes sure its valid. The other information is a join away if you need it.

I do wish though that there were more ways to denote certain tables as configuration data vs domain data, besides naming conventions or schemas.

Edit to add: I will say there is one places where I have begrudgingly used enums and thats where we have used something like prisma to get typescript types from the schema. It is useful to have types generated for these values. Of course you can do your own generation of those values based on data, but there is a fundamental difference there between "schema" and "data".

Very nice!

Did you consider making this a view instead? Just curious if there is a reason why you couldn't.

apparently I missed Simon Willison's article, this at least somewhat explains them: https://simonwillison.net/2025/Oct/16/claude-skills/

So if youre building your own agent, this would be a directory of markdown documents with headers that you tell the agent to scan so that its aware of them, and then if it thinks they could be useful it can choose to read all the instructions into its context? Is it any more than that?

I guess I dont understand how this isnt just RAG with an index you make the agent aware of?

I use claude code every day, and havent had a chance to dig super deep into skills, but even though ive read a lot of people describe them and say they're the best thing so far, I still dont get them. Theyre things the agent chooses to call right? They have different permissions? is it a tool call with different permissions and more context? I have yet to see a single post give an actual real-world concrete example of how theyre supposed to be used or a compare and contrast with other approaches.

I dont disagree with anything you said. If I was in their shoes, I would have done exactly the same thing.

Maybe my complaint is that I wish vscode had more features like intellij, or that intellij was the open source baseline a lot of other things could be built on.

Intellij is not without its cruft and problems, dont get me wrong. But its git integration, search, navigation, database tools - I could go on - all of these features are just so much nicer than what vscode offers.

I love cursor, the tab completion and agent mode. But I really dislike vscode after using intellij for so many years. I really wish the underlying editor was better, or I could get cursor features in intellij instead. The editing of the files is mostly fine, but its everything else around it that a full IDE provides thats just so much better. Right now its intellij + claude code for me, and its fine, but I wish I could get the AI power of cursor in a better package.

take this thinner phone, add more battery to get back to the size of the current one, thats what I want. 3+ day battery life please.

I totally agree, hope my comment didnt come off to the contrary. As a layman, I consume most of my information through popsci sources (though I try to go more for the Dr. Beckys than the meatless or sensational stuff), and its generally described as something that we just take for granted - "we just found the oldest galaxy ever observed, only a few hundred million years after the big bang - and its too bright and has way more 'metals' than expected" - but we measured that with redshift, which makes a bunch of assumptions that of course they cant talk about in every video, but we dont talk about anyone questioning them.

I have no doubt that there are great scientist spending their entire careers trying to improve these rulers and measurements, but I also know that there are great scientists spending their entire careers basing everything on the best rulers they have...

I've always thought as a layman that the weakest link in all of this is our cosmic distance ladder, seems like the most likely place that errors would stack up and lead us to some wrong conclusions. So may places for things to go wrong, we make a lot of assumptions about type 1a supernovas actually being a constant brightness, dust obscuring our view of them, plus all of the assumptions we've made about even measuring the distance between the ones we've measured. And its not like cosmologists havent acknowledged this, but I think a lot of the hubble tension might be solved once we figure out how to measure these distances more accurately.

this is very cool! Where can I follow you to see updates?

agreed, which is awesome, the only thing that worries me is that they will drop support for it earlier than they have to when they want to force people to upgrade eventually. I hope to get 10 years out of my M1

Super cool!

We needed to do something similar one time with 5 large touchscreen tvs that were arranged as a table, where each side needed to be a separate touchscreen application with them all playing a synchronized video in the background but users could interact with things flowing from one end to the other and could send objects from their other apps in any direction to other apps, like users sending things they found to the person on the other side of the table.

We ended up with a trashcan mac pro (thats about all we could find in budget that could drive all the screens at the same time) with apps that were synchronized using redis (I wrote that part). It worked really well, though I didnt get to see the finished product before I left that company. But we always really wanted to have separate computers that were synchronized. We just couldnt get that to be reliable enough - it worked for a while but then various things would throw it out of sync, meaning we would have to restart the applications periodically which wouldnt work.

Something I have always wished we had, since the very early days of PCs was the ability to network devices together in such a way that they could share their resources and collaborate more. Imagine being able to take advantage of all of the computers in an office to do a task like a supercomputer. Of course thats a very hard problem, applications and OSs would need to be designed for it and we would need new algorithms (look how long it took us just to take advantage of multiple processors in the same machine on the same board), but there were some projects out there like seti@home and folding@home that did it somewhat, but I always hoped it would be something that the computers themselves would support.

ive always seen the reason MS included solitaire and minesweeper was to teach people how to use a mouse and a gui.

I can remember even in the early 2000s when we started installing PCs instead of green screen terminals at different locations having employees play solitaire as a way to get them used to their new computers and learning how to use a mouse.