redman25

Artificial analysis's "intelligence vs cost per task" chart shows the provider's price. I had deepseek scale the prices against openrouter's prices and re-draw the chart and pareto line.

Some models saw big improvement. Deepseek 4.1 flash in particular joined the pareto when openrouter's real prices were taken into account.

Id love to learn what prompts you’re using to do that. Explanations one at a time. Thats something I’ve thought would be helpful before but didn’t know how to achieve it.

Maybe they’re gunning for speedy non-interactive pricing? Or its a limit of the technology or a business decision?

More like acting without a sense of civic duty is stupid. Or acting without a basis in evidence is stupid.

Deepseek is one of the worst in terms of hallucination rate according to artificial analysis' benchmark: https://artificialanalysis.ai/?omniscience=omniscience-hallu...

A large portion of the tests are closed source unfortunately which would make it tough to create a port.

I've been preferring Mimo recently. Same price as deekseek, more reliable tool calling (subjectively), and has some nice qualities in terms of prose, etc.

I've heard others say that Deepseek tends to be smarter on specific problems but that Mimo tends to more well-rounded.

Exactly, intelligence is limited by cost and physical constraints just as much as anything. That's the thing that seems to always be missing from the run-away singularity discussions, it's treated like a perpetual motion machine.

IDK this model release is a bit disappointing considering the community has been chomping at the bit for the 124ba4b model. There was some leaked info about it but people suspect it was not released because it was too close to gemini flash in performance.

I too prefer my misinformation delivered with maximum confidence and no accountability.

What prompt had you given it?

I'm not OP but I work outside and use light mode. Macs are generally fairly bright as long as you aren't in direct sunlight. Solarized light mode for the win though.

It’s a heck of a lot faster too.

Doesn’t ham radio not allow transmissions to be encrypted by law? That rules out most of the internet.

A strix halo machine or MAC will run at less than 20watts idle. You could leave it running.

Is 10 days enough to make walking difficult?

Not to be confused with nanocoder, the agentic coding harness.

https://github.com/Nano-Collective/nanocoder

Exactly, compare MoE with MoE and dense with dense otherwise it's apples and oranges.

200a10b please, 200a3b is too little active to have good intelligence IMO and 10b is still reasonably fast.

It's why you always have a rollback plan. Every `up` needs to a `down`.

So someone is debugging something with git bisect and stumbles on the old commit and gets pwned. Maybe that's why they force killed it? To avoid people going back in history and stumbling on it.

CPU/network throttling needs to be set for the product manager and management - that's the only way you might see real change.

We have some egregious slowness in our app that only shows up for our largest customers in production but none of our organizations in development have that much data. I created a load testing organization and keep considering adding management to it so they implicitly get the idea that fixing the slowness is important.

It’s mainly the benchmarks that have encouraged that. The more tokens they crank out the more likely the answer is to be somewhere in the output.

I feel like the right response for those situations is to start asking questions of the user. It’s what a human would do if they did not understand.

It depends on the harness and/or inference engine whether they keep the reasoning of past messages.

Not to get all philosophical but maybe justification is post-hoc even for humans.

How about a human coworker who screws up 1% of the time? Doesn’t sound so bad in that light. It’s the nature of being human.

Good code review is the solution but if it’s faster to do it yourself, that’s fine too.

First things first, we have to colonize the rest of the solar system before we can terrorize Earth.

For consumers, there's little reason to run unquanted, especially for large models which take less of a hit from quantization. I'm running a 200b model at Q3 with very little degradation. A 1000b model would see even less change.

Yeah, good software takes time. These are all popping up way to fast.

So it's ok for a privately held company to have this data but not the police without a warrant?