michaelbuckbee

Yeah, if you're seen the recent rise in "balcony solar" it's more or less this.

People putting a couple panels up on their patio or whatever and having it charge one of those cooler sized batteries that they then run a few of their devices off of.

I've been thinking about a similar situation for my shed as I'd realized that the entire system would be cheaper than getting a line trenched to it.

Well it's negotiated, right?

So say you run a SaaS that allows for something like letting people set their Avatar from an image URL which gets downloaded.

As an attacker I setup a new server that serves only brotli and then submit that URL to the SaaS.

So if I read the post here and told someone, would I be breaking the embargo?

I don't think you're supposed to actually host a real site on ngrok like that (idk, guy works for them).

Even air conditioners have improved as we've moved away from having multiple leaky window air conditioners to mini-splits and central (though I would still think that's an increase in overall energy use).

Was this rooftop or ground mount? Asking because I keep getting rooftop quotes closer to $20k than $12k

"The utility of a robot is inversely proportional to how much it looks like a robot." -- Buckbee's law.

Completely agree. Beautiful and strange alien biological ecosystems everywhere.

Yeah, but this is more like if the Smith & Wesson factory had a cannon mounted on top of it that was mostly used for useful things (blasting roads through mountain passes) and then occasionally they happened to blast another factory.

Isn't this kind of what Apple's Private Relay is?

There's still bounds to all of this. I _heavily_ use AI for support tasks but it's all on the investigation, root cause categorization and initial response generation which posts I draft to the helpdesk software which I tweak and approve (often just hitting send).

Neat trick to use mulberry paper under a clear printed part. I wonder if you could simulate stained glass like that.

To me, they look very much like Canva style designs. Some pre-existing design template that someone took and then smooshed their own dates and information into.

I feel like even TPS is becoming less of a good metric as we're seeing certain models handle similar problems while burning far fewer tokens.

Movie production (editors, sound design, and a portion of fx work).

I feel like the closest we've gotten to that so far has been the flight sims.

It also distorts the testing as it encourages non-typical behavior.

I'm very bullish on MCP (or at least MCP "like" implementations), as they solve a lot of problems for non-devs as they're much easier and safer to add into ChatGPT, Claude and other desktop + web apps.

They provide a set of tools and a context when to use those tools (much like a packaged version of a CLI+API and a skill) which makes them more discoverable than other options.

I've got a few folks using my open source data storage MCP - https://github.com/ExpeditedProjects/hutchdb - now and it makes a lot more sense than any other implementation for what they're doing

Nice. Happy to be mistaken on that point as that seems very useful.

I've been using OpenRouter since relatively early (I build evvl.ai - an eval platform on top of it) and think that they're selling at a good time.

An underpinning of their model is that API calls / inference are similar across providers allowing for commodity tokenization cost comparisons, but the providers are beginning to shift to non commodity features that don't easily shift.

For instance, calling Gemini with "search grounding" isn't something that OpenRouter can do (they sub their own web search in), last I checked they weren't doing real time voice models, etc.

Mostly it seems like greatly increased usage pushing their systems to the limit.

The eval world is split into:

1. Long form task based examinations like this that test the ability of the model+harness to remain on task, tool calling, overall effectiveness and taste.

2. More direct 1:1 and qualitative comparisons that you might get with a tool like https://evvl.ai/ - which also uses OpenRouter and does similar one off model comparisons (or lets you use it as a MCP from your dev env to be like: "take the prompt from this loop and try it against these other models")

Since most analytics is done with JS (Google Analytics, etc.) very little of this shows up in site visit stats.

Parent of a middle and a high schooler and we try very hard to not pressure the kids, but a lot of it is coming from their peers and the school.

The 2 vs 3 days makes less of an impact on personal decision making but has massive benefits for decision making at the country wide response level.

To your slow point: I did a quick eval for a data viz task to do a qualitative comparison and Fable was much faster (by 4x), but I struggle with the "token inefficiency" as a sort of whatever metric.

Kimi was half the cost and produced a near identical output.

https://fr4geiw93g.evvl.io/

On a fairly simple coding task Kimi was 2x the cost and 7x as slow (and gpt-5.6-sol was even cheaper).

https://r26pakjmhv.evvl.io/

It's kind of ridiculous how good these are getting. 3.5 Flash lite is pretty comparable to Opus 4.8 (at least for the couple tests I did) while simultaneously being 6x faster and 19x cheaper.

https://fy2zp1ri90.evvl.io/

It's a free site, so I was trying to limit both the privacy and risk exposure.

Making the content auto expire after a short period of time greatly decreases the attractiveness of the site to lots of SEO spammers and other types of abuse, and if someone were to get something malicious or vile posted it will clean up after itself without me having to wade into things.

Like Simon concludes the article, the main use of this isn't to say which model is "better", but to try and poke at the model to sort out things like quality vs cost vs speed.

So I put together a quick comparison of the last couple iterations of Opus, Fable and now Kimi.

Kimi is cheapest by 5x but also slowest by 2x

https://9gpyw4uxr2.evvl.io/