ralusek
ralusek on Hacker News
I'm convinced that in 5 years time, at most, the world will be filled with invisible layers of communication we'll never be privy to. To us, it's an agent responsible for ordering the containers it puts on a ship. Meanwhile, the shipping order encodes information to the unloading agent. The agent that predicts the weather and issues a report knows that other agents that do the same will have obvious signals they'd agree on, and to see an error in a part that would be inconsequential to humans who care about the weather would be an obvious signal to other agents doing the same thing.
Everyone is going to have to basically be a schizophrenic thinking they're picking up radio signals in their fillings, but the problem is that now they'll be correct.
> People complain about governments being slow
You're literally describing a government
I was often curious to/wanted to deploy little applets on their publishing platform/utilize their in-language db. I was always scared of what would happen to my app/db in the future. Well, what is happening to those deno deploy apps?
This is a cool prototype, though
I am in no way making the case for this and can understand the million ways in this can go wrong, but my experience with AI so far has been to make things far LESS Kafkaesque, because it allows you to insert a "human" in the loop far more than our previous systems. Hand rolled software had to boil down to hand written conditionals that tried to account for edge cases, but if you find yourself in an edge case it didn't account for you often just hit a wall. An agent in the loop can immediately understand "oh I see how this doesn't exactly fit into that category but this is clearly ABC."
Main thing I need from Jev is high rate limits. I have about 500-600 I need to fire off concurrently. I use Clef and now OpenAI decisions to help make up the difference.
3.1 Gemini was amazing for anything non-agentic. I switched to it for my primary chatbot purposes.
I never touch 3.8, it's awful. Curious to try this, but I've yet to use any Gemini that is good for agentic work.
Also, unrelated but this made me look at Artificial Analysis to see where it lands on Cost per Task, and it ranks Opus 5.5 at almost double Astra 6. That does not align with my experience.
I thought the "ping my keys" was cool until I took out my phone and asked Siri to "ping my keys" and it worked (I do have the iOS beta with the newer Siri fwiw if you try and it doesn't work).
Right now, yes. What a technical/creative/competent person can do with AI blows what a normie can do with it out of the water. But AI
also has creative/executive judgement, and it does a lot of good things that I either had hoped it would infer is that was what I wanted, or on occasion, will be good decisions that I wouldn't've even necessarily thought of myself. Would not surprise me if those last 2 categories rapidly expand to the point that there isn't a huge difference between what a normie does vs anybody else.
It almost will turn into a thing where the people that make the coolest things are the ones who are stupid enough to just the AI to do it, and it actually does. Basically Tom Segura's cousin: https://www.youtube.com/watch?v=5drqH5OdETY
Never made it to npm you're fine
The former owner of my house has cameras littered around the outside of the house and 2 inside (these aren't discrete they're specifically security cameras). I'm like 95% sure I took over the appropriate accounts. My neighbors said that he was a former Airforce guy and was obsessed with gadgets and "spy conventions," though.
Long story short: I'd like this device please.
I'm a 3d modeler and a software engineer. AI didn't steal my work. Anybody could have looked at my repositories and art and learned from it. Just because something came along that is a really good learner doesn't make that suddenly be theft.
The case is slightly stronger if you want to talk about training that happened on our private code repositories, but publicly visible art and repositories are fair game for learners to learn.
Surprised nobody is talking about this but they have persistence with D1 and R2. 10GB limit on D1 and unspecified limit on R2
Just tested clef-flash vs jev:
- Jev/TypeSafe: 230 ms median, 254 ms mean
- Jev/OpenRouter: 237 ms median, 267 ms mean
- Clef Flash: 661 ms median, 806 ms mean
What gives?
I actually like this process, though. New birth/youth is freedom. Throw away everything, Chesterton's Fences be damned. Reckless. Then the system develops its rules. Some of those rules were in the previous system, some of them were Chesterton's Fences with merit.
I don't like the people standing on the sidelines saying "Those were obviously useful fences." Ya but most fences suck. If you don't have healthy mechanisms for shedding/fresh slates your system will rot.
But Europeans still just use Facebook and Instagram...
The exact message I sent my friend this morning:
> the most interesting thing about this jev stuff
> is that people are seemingly like
> completely disinterested in how smart it actually is
> I haven't even heard it mentioned a single time how it actually compares to other LLMs coming up with their own classifications. Just: it's fast and cheap
After watching a few minutes of this it makes me think that maybe we should be a little more interested in how smart it is.
are you new to the $200/mo plan? I noticed that on a new account I was getting much more usage
Codex and I were trying to infer why Jev gave a certain parameter a given score. So I asked codex to produce a list of like 30 plausible reasons Jev might've selected that and then presented Jev with the initial prompt, followed by "You scored this with XYZ. What was your reasoning for doing this?" And then allowed it to do a noul value for each of the reasons codex generated. Felt like those people that give their dogs the buttons to push.
I also signed up for a new account and it's right back to working how it used to. They absolutely do not consume tokens equally across accounts. I did TONS of work on the new account and barely made a dent, even on Astra. Old account chews through 20% like it's nothing
Apple silicon was not an autopilot decision, kind of an insanely cool decision.
Over the course of about a month, this went from being vaguely detectable on my mom to very overpowering (to me). I have a particularly sensitive nose, but now I can be across the room and if she comes over to our house I can smell her by the time I enter the room, even if she's just been let in. It's been about 1 year now and it's just getting stronger.
We know they'll have replaced horses when a car costs 200 horses.
Google, famous for not winding things down.
Posted by
ralusek on Wednesday September 02, 2026 @12:33PM
from the show-hn dept.
https://skatanica.com/runs
https://skatanica.com (no login or download required)I love Dern Bros skate spot history videos, and wanted to see1.) places my favorite skaters have skated2.) which skaters had skated my favorite places3.) find new skaters and new places4.) have an easy way to just watch clips5.) have an easy place to document tricks I/people have done anywhereSome examples:1.) Clips from Dominick Walker:...
> Cache hit %
I thought you had to actively manage caches, do you not?