lwansbrough

I suspect if you showed one human a million photos of a bike they might get it right.

Perhaps this isn’t a new observation but the problem with LLMs is very clear with these. It’s a nice microcosm. The LLM will draw a fish companion (unprompted!) with a nice gradient but won’t get the pelican’s feet right.

It’s obviously a problem of fundamental understanding and demonstrates that reasoning is more “directionless rigour”.

Access to your computer

It shouldn’t be, and certainly doesn’t have to be. Logically it should be cheaper to live in an apartment than an entire house - obviously.

Suburbs are subsidized by economic centres. And the state of affairs in North America - Vancouver included - is we’re not building housing to match demand. That’s true purely in terms of individual units but it’s also true for types of units. Like apartments that aren’t luxury units, but that can fit a family. They don’t build those anymore because city council makes it completely unprofitable for developers.

If you think that apartment living is inherently more expensive I’m sorry to tell you that you have it completely backwards.

For OpenAI, research is marketing. I’m sure they’ve got plenty of budget for that.

This is satire right?

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?”

Thanks, I'll give that a try.

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.

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.

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.

- //

- letter spacing

From the pre-slop era: https://www.youtube.com/watch?v=RKT-sKtR970

Didn't they also just post about how SWEBench is broken?

Like SF, you can pick streets in Vancouver and sell whatever story you want about the city. You won't find many film cameras on East Hastings unless it's a documentary.

You don't think there's a difference between passive entertainment and a conversation with a sycophantic enabler?

They actually do mind, which is why they don’t do it. Did you forget the reality of the situation?

They mind because they are completely outnumbered. Policing only works if you can point out a small minority and say “these people are causing harm to the majority of us”. With something like fireworks (or cannabis protests in many places) the police are severely outnumbered and they don’t have enough room in their jails anyway.

If they did this people like me would start setting off fireworks in protest.

A$AP Rocky did it for a music video. Granted, it was only used for the editing process and not the final video, but it still presents some interesting opportunities, though it doesn't really look real so the applications may be limited.

https://radiancefields.com/a-ap-rocky-releases-helicopter-mu...

What does it cost to train a model like 1-bit Bonsai? Anyone know?

Anyone with a billion dollars want to try this and report back?

Not a greed thing. It’s a national security thing.

No idea I don’t work there.

Chinese labs are also still behind, so they’re incentivized to collaborate and have no reason to do it in private.

I suspect their tune will change if they ever take the lead..

I feel like going with Space + Latin is LLM-level creativity.

Edit: yeah. https://claude.ai/share/06fefe02-4299-44da-8c5a-42607f54ca77

Just buy an AC unit.