Hacker Newsnew | past | comments | ask | show | jobs | submit | lwansbrough's commentslogin

Why stop there though? My harness writes WAT directly and compiles with wasmtime.

It’s very fast and very difficult to read.


In theory. But in practice, in my experience, sub-agents increase cost.

Sub-agent tasks often have overlapping context after the point of dispatch. Example: you tell agent 1 to explore folder A and agent 2 to explore folder B, if they have the same structure a single agent might be able to discover what it's looking for faster in serial mode vs. parallel. And if not faster, likely with fewer tokens.

And as the orchestrator context grows, it also loses out on capturing the nuance from some of the sub-agent context. In theory they pass some of that back, but realistically things get missed, and you can't apply learnings to parallel runs like you can in series.

The latest frontier models are very good at taking the knowledge they've acquired during a session and applying it forward. Sub-agents make more sense in cases where the agent is dumb to begin with and can't make use of the context it learns from serial execution.


This is how I started web dev 20 years ago :) Building a Windows XP “clone” portal for my PSP.

Going to call it user error if you find Opus 4.5 better than 5, sorry.

[loads up most intelligent AI ever created]

“Rabbit sex, how?”


The question may sound ridiculous.

But isn't it more ridiculous that some company decided that the correct answer to such innocent and curious question is basically "That knowledge is too dangerous, you shouldn't ask that."?


I mean, yes. Why?

Why would nature encode such a ridiculously disproportionate / inefficient behavior when it leads to catastrophe so frequently?

I've tried to ask these machines dumber questions like, why castles? And... well I'm working on a few projects (mostly by hand) that they've helped with! :)

I like to ask dumb questions. It's fun. I encourage it.


Lots of species are r-selected, I don't see why that would be considered inefficient. In fact I think there are probably more r-strategists than K-strategists.

Just as stating the wrong thing would be the quickest way to elicit a response in the past, so too can 'dumb' questions prime the context for more complex queries.

I am all for this strategy, and revisiting my list is equal parts fun and conducive to long-term recall.


Answer: Because rabbits are tasty. If they didn't hit the ground hopping and bopping, the species would have died out long ago.

Rabbits are a good input calorie to output meat ratio, and their excrement makes good cold compost. They breed and litter relatively easily. Theyre also easy to house.

Plugged 3.5 Flash Lite into an existing agent harness that was previously using 3.1 Flash Lite and this shit just does not work. It's not following instructions and is not producing the correct tool calls.

Maybe this is relevant? Just in case

> For autonomous subagents with tool calls, code execution, or multi-step reasoning: set thinking_level to "medium" or "high" to prevent premature tool termination.

I just happened to see that in the docs: https://ai.google.dev/gemini-api/docs/latest-model


Thanks, I'll give that a try.

Can anyone explain how you “win” the market of super intelligence? Particularly with open weights models now rivaling the frontier, it seems like a race to the bottom even if the prices don’t yet reflect that.

"race to the bottom" is the negative framing of "competitive market prices".

So a company or union might say "this is a race to the bottom" when someone new enters their market, but to people buying their services this might be seen as welcome competition.

Do you actually see a negative impact from competition in this area? Or do you just mean competition will further reduce prices?


"race to the bottom" is also a response to a "market for lemons". It's not necessarily a good thing because while pricing drops to the floor so also does value to the customer in general. Usually it happens when price is very visible but the details of what the buyer actually receives are not.

You can only outlaw stuff in your own countrys..

And if cheaper access is an advantage, other countries will surpass you


Regulatory capture. You get them to outlaw the part of the competion (safety!) that is unwilling to pricefix and participate in your margin and market division agreements.

Don’t think of this as super intelligence. Think of it as vendor lock-in.

We have a good compare, which is cloud in the early 2000s.

Everyone (at the time) thought cloud compute costs would go to zero.

What most corporations didn’t realize is how entrenched your workflows and processes get when you adopt cloud and you become heavily locked in that ecosystem.

That same ecosystem lock-in is what the frontier labs are hoping for with AI.


Competitors run out of money and shut down, perhaps. Although I don't see how that happens for anyone but Google.

Do we all shift over to Chinese models.

Yes.

You patent and protect (as best you can) the missing ingredients needed to get to AGI. Only half joking and also scary to contemplate. Qualcomm’s CDMA patent is on example. ARM and Texas Instruments two other examples.

You hit the nail on the head. It's a race to the bottom.

Everyone is raising the bottom. Kimi got 60% more expensive during the 2.x cycle despite staying the exact same size.

Now K3 is almost 6x the cost of the original K2 checkpoint, and while the parameter count finally jumped, it's still an extremely sparse MoE and definitely does not cost 6x what the original K2 checkpoint did to host at scale.

Race to the bottom only takes real effect when there's a cap to the capabilities, otherwise everyone races to the bottom of a rising target (how economically valuable the tokens are)


But Kimi (at least say) will release their weights. So surely, if their prices are too high, somebody else will host it cheaper?

a) Why and b) With what compute?

"Why" as in, why take lower margins when Moonshot currently can't service all the demand for the model anyways. Based on past models no one is going to massively undercut Moonshot: few have the chops to serve it as efficiently as Moonshot and of those few, most of them don't go for being the cheapest, they go for being fast + reliable (think Together, Fireworks).

You get what you pay for applies very much with how many axes there are to serving these increasingly large models.

-

And for "with what compute": as the value of a token goes up, what people are willing to pay for compute is going up.

Every once in a while I'll see a story about falling rental rates, but with even slightly more established clouds I've been seeing availability get worse and worse over time.

I'm pretty sure the only reason the highly informal indexes don't reflect this is because every neocloud trying to cash in on an NVIDIA Inception discount kicks off by selling unrealistically cheap compute for a bit.


It's unlikely that a clear single winner will emerge in this competitive market.

Whats the bottom here tho? Its obvious what winning is.

only way you could win the market would be to own all the gpus

AGI will be insanely priced. LLMs are retarded childrin compared to proper intelligence. So this is just the entry level intelligence like thing. But I doubt there will be an AGI accessible by anyone.

If AGI comes to exist it won't be "priced" at all, since the lab that creates it will either quickly be seized by the gov't for national security, or they will become the most powerful organization in the world and have no need to sell services to other corporations. they will become the only corporation.

Good sci fi premise, but not at all how AGI will happen.

It’s not going to be a singularity at one moment of time. It’s not going to be instant runaway self-improvement, no matter what doomers and fetishists say.

It’s going to be gradual. We’ll see glimmers of AGI, and the “G” part will be about gradual broadening of domains and deepening of capabilities.

All of the coding harnesses are already using their own tools to self-improve, and the HITL component is getting less frequent and at higher levels of abstraction.

That’s how AGI gets here: very gradually, no hard takeoff, and nobody will be able to pinpoint when exactly it happened.

So: also no single lab with a massive advantage, no government takeovers. It’ll be a lot less dramatic than the extremes believe. IMO, of course.


The problem is... the moment someone gets it and it really solves hard problems and solves scifi level shenanigans, the given country that owns it, could gain such unfathomable lead above anyone else that it will almost surely lead to an all out war. I don't even know whether it is possible to conceal that you have such capability....

Imagine all the fear- and warmongering kingmakers and powerful individuals when they realize they have no power over anything or anyone.....so game over for them. They won't like it at all, at all.

Another problem, that in order to make it understand real life, it needs robots or humans wired into it (brain interfaces) in order to test certain things in the real world. And that is another level we know almost nothing about, at least on the surface.

PS: do these self improving harnesses even work?


Someone could have a small private breakthrough tomorrow that gives sample learning efficiency of the brain, online learning, and consolidated memories.

So, extend what they said to cover a 50 year timespan? "Instantaneous" wasn't mentioned or implied.

If it’s 50 years and gradual, there will be many places very close. The only “winner takes all” scenario is a sudden breakthrough when nobody else is close.

Because it’s a gradient, not a binary.


If gradually one of these labs ends up with the top model that makes all the others uncompetitive, what's the difference? Why do you see time as important if the end result is the same? Winner still takes all, no?

LLMs may be retarded but at least they know how to write "children"

That's all you could point out?

This is like, a post-hoc rationalization.

Most jobs, not all, can take place inside a city. If you build your cities densely, people can live and work within the city and have all their needs met without the need for a car (see: the great cities of the world)

If you design economic hubs properly, businesses can be located within reach of homes without the need for cars.

If you instead prioritize the need for, I don’t know, a monoculture lawn and separation from lower class people, then you’re choosing to build suburbs. Once a city has built enough suburbs, businesses become out of reach without the use of a car.


What if I want my own garden and not monoculture lawn? What if I want my children to be able to walk in nature near their home? Neither is possible in a densely built city where there are only apartments.

Then there are all the social problems, bad neighbours that become more common in densely built areas. I don't want to deal with that. Suburbs are popular because they provide a superior quality of life for many people.

Of course in an ideal world everyone would be allowed to do fully remote work if possible, and people like me could move to countryside.


[flagged]


They could have everything they want here in my neighborhood of Chicago: easy access to nature, room for a garden. Suburban Americans love to pretend that "cul de sac" and "Manhattan" are the only two types of place


Since I've moved to my current home, I've had jobs in about 6 different towns and cities. I think for all of them I had colleagues that cycled to work and colleagues that drove for an hour or more.

All these jobs had homes and shops within walking distance. But they are not within walking distance of each other.


> Most jobs, not all, can take place inside a city. If you build your cities densely, people can live and work within the city and have all their needs met without the need for a car (see: the great cities of the world)

Most people do not want to live in dense cities in high rises.

The number of jobs which cannot be moved into dense city high rises is much higher than you’re thinking. It might seem that way if your world is office jobs and email jobs, but there’s much more to the world of work than that.

Dense cities also have very high turnover as people grow up and want families.

It’s not about having lawns and staying away from “lower class people”. This feels like a poor attempt to cast moral shade on people who choose not to live in a high rise.


Most people who live in dense cities don’t live in high rises…

It is very clear you have never lived in a well functioning city before, and just have no idea what you are talking about. Take the L and admit you just don’t have experience with it. North Americans often don’t because North American cities are extremely bad in this regard.


I'm sure there are plenty of people, who, regardless of how well functioning a city is, don't want to live in one. Myself included.


Absolutely. It’s just the very anti city people never ever seem to use excuses that are actually valid.

Like if “the things that brings me most joy in life require owning lots of land” or “I don’t like people and every day I have to be near them drains me”, those are really valid reasons and there are many more.

What that tells me is either they have a caricature of cities in their head, or (more likely) being anti city is an identity and not based on anything actually about cities per-say.


- //

- letter spacing



Consider applying for YC's Fall 2026 batch! Applications are open till July 27.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: