> We need to see what it's doing, accessing, working with, underlying data, etc... It's an explicit business requirement for us.
this is my biggest gripe with dot. it doesn't integrate very well with my "agent ecosystem". It doesn't see my boxen. It doesn't load any agents.md. It like... is on an island and the only way it talks to the world is.... opaque magic.
"After all that, the mode share of biking has actually gone down in Seattle over the last decade, to under 3%" <-- your article is from 2018 and that is like 8 years old, an eternity ago.
There is significantly more bike infrastructure now then in 2018. Plus the lime scooters and bikes have radically shifted the balance of bikes vs cars to the point where I'd say that bikes now rule the street in most of the dense parts of Seattle.
I would imagine there are at least 10x more people using those lanes than there was before affordable e-bikes and "bike shares" showed up. You've got people who would never, ever ride in a million years be caught dead on a bike using those bike lanes to run errands, go to visit people, commute to work, etc. Just sit down anywhere in the dense parts of the city and you'l see them go by constantly!
I doubt the people who put those bike lanes in back in 2018 and before ever could have imagined how popular they are now thanks to lime bikes, electric scooters and such. Its honestly pretty remarkable and thank god somebody had the thought to build up that stuff back then!
> It sure isn't simply reviewing, or designing, so where is it ?
If I can shit out some vibe-coded thing over a weekend that does it means anybody else with the same tool can do the same thing. There is no value in the actual code itself -- the faster these models run, the more true that statement will become. In the not too distant future these things will run directly on silicone and operate at thousands of tokens a second. That means they'll iterate and explore something far faster than they do now -- mistakes they make will be fixed in seconds or perhaps milliseconds.
That being said my is likely only "60%" of what makes an actual product somebody would buy. It's finding the other 40% that is something I don't think that LLM's can solve. That requires human judgement and then knowledge of how to communicate that vision to your agents.
In short, I believe the challenge is knowing what to build that others would find useful. It's easy to crank out for yourself. Making something others can use is not. And that is, possibly, the bottleneck. But once these are fast and dirt cheap, (and that is a when not an if) the cost to iterate to something workable goes way down. Of course mumble mumble "no silver bullet" / "mythical man" month mumble mumble and all that soo......
I dunno... doesn't directly answer your question but it is what came to my mind anyway.
I mean, the parent poster is not wrong though. It’s crazy the level of stuff you can offload to your agents. People who haven’t used these tools in the last short while are operating on old, outdated frames of reference.
I’m just about to tell opus or sol to go make a custom watch holder that fits kiddo’s bed frame. I’ll give it the measurements of the bed frame. It already knows the dimensions of my printer. I’m prepared for it to absolutely fail at the task, but honestly I wouldn’t be surprised if it came up with something I can send to my printer and just work. Part of me wonders if I could instruct it to simply generate the raw gcode and skip the entire stl -> slicer pipeline. Probably would blow its context window though.
If you haven’t used these tools, you really don’t understand their capabilities. It’s pretty crazy stuff.
Create a “token guy” that others can consult with to figure out the best model to dispatch something to. Token guys role can be defined as an expert in the current LLM landscape. Not sure whose role this is analogue to in medical (somebody here said insurance agent… that is probably getting close).
Token guy’s role gets even better when you let them recommend entirely different hospitals for a given step in patient care (OpenAI models, random shit on openrouter, etc).
I have a “token guy” in my workflow and the dude has looked at underlying tool call patterns, cache use, etc and made all kinds of recommendations to the clients calling it all on their own and completely unprompted—just following a simple role.
I’d experiment with expanding their role into prompt engineer or some kind of specialist on that domain.
We have a small version of this, but as rules rather than an agent. A token guy role that looks at tool-call patterns and cache use could catch a lot of the wastage that we're missing.
I mean Claude code sessions are all jsonl files that it can interrogate on its own. Get a new agent to capture how it was made and what the prompts were. No need for tedious /resume’ing and prompting.
My vote would be 24v or 48v. You cannot power substantial LED with 3.3v. You’d spend a fortune rolling out ultra-thick gauge wire to avoid pissing away non-trivial amounts of power into heat. Many, many LED strips come as 24v. It’s the perfect balance of wire gauge for the amount of power you’ll be drawing.
You laugh now but in 5 years when these LLM’s operate at thousands or tens of thousands of tokens per second on dedicated hardware in your phone… “might as well” won’t even be a joke.
this is my biggest gripe with dot. it doesn't integrate very well with my "agent ecosystem". It doesn't see my boxen. It doesn't load any agents.md. It like... is on an island and the only way it talks to the world is.... opaque magic.
reply