Somewhere in a parallel universe:

🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶

There’s only like 7 blacks in all of Japan and look at what they did

🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶

Investigating my past to figure out if i actually sowed any of the bad things happening to me

🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶

After a trial in Budapest resulted in a German Antifa Ost member being sent to prison for eight years for a series of beatings, Antifa in the UK have announced a direct action to target the Hungarian embassy Hungary_in_UK in London on Feb. 14. They’re telling comrades to mask up.

“Anti-fascism” is not banned in Hungary but the terrorist group Antifa Ost is. The U.S. has also designated them a Foreign Terrorist Organization for their attempted m—rders in Europe.

🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶

While I agree the $20k/mo in API requests from AlexFinn is aggressive, these numbers from ImSh4yy are way off. A lot of mistakes here.

Hopefully this clears things up about using M3 Ultra Mac Studios for AI somewhat. I’ll also be releasing open benchmarks and evals for 1,000+ local AI setups soon.

- Mistake 1: $/tok calculated based on single request TPS, not throughput. LLM inference can be batched, and you can move along a pareto frontier of throughput / single request tps. The point you choose on the pareto frontier depends on your SLOs and workload, but it likely isn’t min throughput. You’re off anywhere from 2x-20x (bringing monthly savings to $156-$1560/mo assuming the OP’s $1.50/million or $312-$3120/mo if we use $3/million from official API) depending on which point we choose on that pareto frontier.

- Mistake 2: Assuming device is obsolete in 12 months. This just isn’t true for Mac Studios. Macs are useful for more than AI. Apple’s hardware retains its value extremely well. I’ve talked to resellers who have decades of data on this. The resell value depreciates ~15% per year.

- Mistake 3: Cherry-picked a provider on OpenRouter that has 98.4% uptime. That means it’s down 23 mins per day, or 11.5 hours per month. The official Kimi K2.5 API is $3/M output tokens, 2x the price you used. That’s more of a fair comparison.

- Mistake 4: Ignored input tokens completely. The official Kimi K2.5 API also charges $0.60 per million input tokens ($0.10 if it’s a cache hit). The cache hit part here is the kicker. Whereas you can keep your entire context hot on your own device 24/7, that costs money for model providers and unlike the model weights each user’s context is unique so it doesn’t scale - they need to charge for it. I’m loading entire codebases into context, which often is 200K tokens. That’s $0.12 every time you load in that codebase and $0.02 every time you query it (even for one token) when it’s cached. That adds up quickly, especially when e.g. each tool call using claude code or opencode is an additional request.

- Mistake 5: There are other reasons to run local beyond cost (imo more important). Privacy, compliance, sovereignty (not your weights, not your brain), uptime guarantees, air gapping, no internet access. There’s also latency but usually that’s best going to the cloud, unless you pair it with one of the other reasons e.g. air gapping.

🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶

NEW: WWE wrestler Logan Paul says he is not excited for the Bad Bunny Super Bowl halftime show.

Reporter: Logan, are you excited for the halftime show?

Paul: No.

🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶

For the people who struggle to find out if a coin is bundled or not. Don't buy when you see this kind of things

🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶

He retired his family with a single dollar

🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶

Guy threatens cops with a knife.

First: warning shot in the air

Second: shot in the leg

Third: kicks

Good police work?

🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶

This is scary.. GeoSpy AI can track your exact location using social media photos in 2 secs and show it in 3D.

upload photo -> get coordinates.

🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶

>America leaves the World Health Organisation

>Rest of the world literally cures every form of cancer within a month

🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶

Are you not thrilled that your country is importing these rocket scientists by the millions?

🄳🄾🄾🄼🄿🤖🅂🅃🄸🄽🄶