I’m not familiar with the tool you’re using and my big, traditionally written projects have largely been organically grown over the years as unpredictable requirements change – mostly I just try to keep things readable enough that I can jump back in when I need to do so on old projects…

It sounds like you want to incorporate LLMs into brainstorming though. Maybe try using the word “elicitation” in your prompts for early phases? e.g. “ROLE: Requirements Elicitation Specialist” or “ROLE: Architecture Design Elicitation Specialist”. You can also meta-prompt to get a system prompt tailored to your specific needs.

Hmm. I’m not exactly sure how I got there or what would work for other people, but it can be done.

Maybe try thinking of it like pressing the clutch in a manual drive car? The engine might keep spinning, but if you hold down the clutch and ignore it eventually it’ll run out of gas…

Or maybe think of it like tuning out someone annoying chattering nearby. They might keep talking for a bit but if you ignore them, eventually they’ll get bored and shut up / leave. Even if they come back, just ignore them again if you don’t want to engage.

Or, try focusing on sensory details instead of mental chatter. Really notice what you’re seeing/hearing/feeling without actively describing it or planning anything.

I don’t usually stay in that state all that long, but sometimes it’s nice to just be.

I suspect most of them do not have an internal monologue in the same (verbose) sense that humans can have, but the relatively closely related ones (e.g. mammals, probably) likely have similar memory/sensory integration experiences. It’s possible to get your own inner monologue to “shut up” for a bit, and just be and feel and do. You can still remember an experience without talking to yourself about it as well. I suspect that closely related animals’ experience is like that – although differing based on the particular set of senses and drives unique to their species.

The further away you go from that, the less idea I have of what’s going on (besides “state machine” of some sort). I have only the vaguest notion of what it might be like to be a spider, and even less of an idea of what it’s like to be a starfish.

Imagine some future PugJesus type excavating our memes from the archives and reposting this 1000 years from now. 🧐️

That one flue over my head. 😉️

Makes me think of this song: Fox Tale Waltz Part 1

I say it more like nɪʃ personally.

He writes out the entire code, and it works every time.

Well, I’m not sure if they’re entirely human if it actually works the first time every time – but they’re definitely not any of the LLMs I’ve encountered… :-)

I’m thinking obsessive about work (never mutes their phone type) and using AI tools. Politely check (preferably in person) to make sure you’re not waking them up in the middle of the night with off hour requests; there are some people who feel compelled to respond to everything immediately instead of getting back to you the next day.

Going back even older… Mysterious Cities of Gold. That’s never been remade or adapted…

They actually resumed the story directly in a sequel series in 2012: https://en.wikipedia.org/wiki/The_Mysterious_Cities_of_Gold_(2012_TV_series)

Is BotBall still a thing? They had that (waaay) back when I was in high school, at least.

Congrats. I groaned IRL.

Hmm. So… how long do you think before we start seeing news stories about their DRM servers getting hit with DDOS attacks (or other network fuckery) and no one being able to play their PS4/PS5 games? 😛️

Probably hundreds of millions or billions if you include things like washing machines, dish washers, automated gates, garage openers, etc. that automate specific tasks. Just the read/write arms in hard disks alone is probably a staggeringly huge number, if we’re counting things like that…

Based on what I see on my Steam Deck (not sure on Bazzite specifics), it looks like the WINE prefixes are stored in ~/.local/share/Steam/steamapps/compatdata

I think the number in each folder name is the game’s steam ID, which makes it a bit cryptic. You can probably find that ID by running grep -i "name of game" *.acf in the steamapps folder. The files are named like appmanifest_STEAMID.acf, if I understand how this works correctly. You might also just be able to search for the file you’re looking for directly though if you know what the name is inside the prefix and it’s distinct enough.

Might be this? https://www.youtube.com/watch?v=9Vk6hANjLeU

YT thinks I’m a bot and has me blocked for some reason, so can’t confirm.

On the original CD-ROM, it was SOUND/RADIO/STATIONS/Bluegrass/MUSIC/sp.WAV

Probably the best song in the game. Certainly the most memorable!

I think I’d get bored pretty quick just driving around with no goal – although, I did have a fair amount of fun driving around Streets of Sim City as a kid and probably spent more time messing around my own SC2K maps than I did with the actual game missions, so I could be wrong about how bored I’d get of a pure driving simulator…

Regardless of whether I’d enjoy it, I have family members who I’m pretty sure would find it right up their alley – especially the classic car aspect.

If it’s sold as a separate soundtrack, typically no. Usually they’re just MP3, FLAC, or WAV files – sometimes you get a choice, sometimes not.

I wrote some VBA for a job a long time ago. It was pretty good for making quick and dirty UI in Excel – like, click a cell and have it pop up a form you can interact with that will let you do data entry with less clicks/typing than whatever Excel would’ve made you do if you had to do it naively.

I used it for showing a list that could be filtered down by partially typing in text in one project. (A really basic autocomplete sort of thing, essentially.) For another project, I integrated IE and showed some complex data in the embedded browser with buttons (or maybe it was checkboxes? been too many years) in the form to quickly classify it and move on to the next entry without having to flip back and forth between multiple programs and manually open files. (Each entry corresponded to a row and widgets on the form updated values in various columns so I could go through all the data and fill out the full spreadsheet super fast.)

Alternatively, write a script that checks your spreadsheet for errors. e.g. add a reference to a regex library and use it verify that all the entries in a column match the data format you expect (like serial number patterns with hyphens in specific places).

You can also ask your coworkers for something tedious they have to do a lot in Excel and see if you can find a way to make it less tedious.

I tried throwing this image at qwen3.6 locally with the prompt “What is in this image?” and it spat out:

Based on the visual evidence, this is a micrograph (a photograph taken through a microscope) of bacteria.

Here is a breakdown of what you are seeing:

• Organism Type: These are bacteria. You can tell by their small size relative to the scale bar in the bottom right corner (which represents 10 micrometers).
• Stain: They are stained purple/blue, which indicates they are Gram-positive bacteria. In a Gram stain, Gram-positive bacteria retain the crystal violet dye and appear purple.
• Shape: The individual bacterial cells are spherical or round, which classifies them as cocci (singular: coccus).
• Arrangement: The most distinct feature is that the cocci are arranged in chains.

Conclusion: This image shows Gram-positive cocci in chains, which is the characteristic appearance of bacteria from the genus Streptococcus (or possibly Enterococcus). Common examples include Streptococcus pyogenes (which causes strep throat).

So you might be able to get further than you expect. You might try collecting some of your own sample data for things you understand (like particular bacteria you’re interested in) and providing those images along with a prompt that includes labels for your sample imagery. (Like “Image 1 is an example of (…whatever…). Image 2 is an example of (…something else…). Which (if any) of these are in Image 3?”)

I don’t know how well it would work, but worth a try.

The dream, for me, is to get it to understand the protein structure files and DNA sequence files

Even then, much of what I’d want help with looking at proteins is how to write analyses of points in 3D space

I tried throwing this image at qwen3.6 as well, and it spits this out (but takes a REALLY long time to do it on my local hardware):

Based on the visual evidence, this image is a 3D molecular visualization of a protein structure, likely created using software such as PyMOL, UCSF Chimera, or VESTA.

Here is a breakdown of the specific components visible in the image:

1. The Protein (Blue Ribbon):

   • The large, coiling blue structure is the protein backbone.
   • It is rendered as a “ribbon” or “cartoon” diagram, which is a standard way to visualize the secondary structure of proteins.
   • The coiled sections represent alpha-helices, which make up the majority of this protein’s structure. This “helix bundle” fold is characteristic of proteins in the globin family, such as myoglobin or hemoglobin, which are responsible for oxygen transport and storage.

2. The Central Ligand/Co-factor (Middle Right):

   • Nestled within the protein fold is a complex molecule shown in a “stick” and “sphere” representation.
   • The Flat Ring: You can see a flat, ring-like structure with blue sticks (representing nitrogen atoms). This is characteristic of a porphyrin ring.
   • The Red Sphere: There is a large red sphere in the center of the ring. In this context, this almost certainly represents an Iron (Fe) atom.
   • Conclusion: This complex is a heme group (or heme prosthetic group). Heme is the molecule responsible for binding oxygen in hemoglobin and myoglobin, or for electron transfer in cytochromes. The long chains extending from the ring are likely the side chains of the heme molecule (propionate groups) or a bound drug/inhibitor interacting with the iron.

3. The Ion (Bottom Right):

   • There is a small molecule floating near the bottom right of the protein.
   • It has a yellow center with four red arms arranged in a cross/tetrahedral shape.
   • In chemical coloring (CPK coloring), yellow represents Sulfur and red represents Oxygen. This indicates a Sulfate ion ($SO_4^{2-}$). Sulfate ions are common in crystal structures of proteins and are often used to stabilize the structure or mimic phosphate groups.

Summary: You are looking at a structural biology model of a protein (likely a globin like myoglobin) containing a heme cofactor (the molecule with the iron) and a sulfate ion. This type of image is used by scientists to understand how the protein works at the atomic level.

You might be able to it to do something useful with analysis of protein renderings, but I think you’ll need some creativity with the prompts to stop it from overthinking things… It was able to recognize this as myoglobin in the “thinking” stage quickly enough, but then kept second guessing itself about various aspects for a long time. I also tried throwing it at gemma4 but it didn’t really give me much besides recognizing it as some sort of protein structure.

hook it up to some lab robotics and automate experiments

You might find this project and associated HN post interesting – it’s basically someone doing that with electronics analysis instead of biology, IIUC. No idea how well it works, but interesting to look at and think about.

Maybe there’s a coding community on lemmy that’s a decent place to talk shop on how to build these scripts up and what local models are good at what?

There’s [email protected] and probably some communities on lemmy.dbzer0.com as well – they’re not super-active though (at least from what’s made it to my attention browsing by all).

non-text based problems

I don’t know enough about the specifics of what you’re doing to really give detailed suggestions, but I have been surprised by models like qwen3.5/3.6 giving reasonable results to questions about images – like answering questions based on comparing a few images. For example:

• Which of these images were taken from the same place?
• Which of these images were taken in the AM and which in the PM?
• Is the third image more like the first or the second? Answer “1” or “2” only indicating which of the first two images it is most similar to.
• What sort of tags would you attach to these images? Provide a list of tags as JSON as the only response.

Those prompts actually worked for imagery from camera systems I have to deal with for my job – which, frankly, shocked me. The AM/PM one in particular read timestamps in the image (i.e. did OCR automatically) and converted from a 24 hour clock to answer the question. I’ve implemented that in scripts with older computer vision tools (like tesseract) that needed a lot of hand holding; the fact that current models can just do it is sort of mind blowing to me…