Frits Karl

@pmarca It’s fine

The hysterical reaction to retardmaxxing confirms the point of retardmaxxing.

@ivanfioravanti github.com/jundot/omlx/bl…

@FritsKarl What’s that? 👀

@FakePsyho Can you also block evey post with a video in it that has a tiktok logo?

I got tired of engagement-farming AI reply bots, and a few hours later I had a firefox extension that correctly tags (and hides/collapses if enabled) about 90% of them. Turns out you can detect most of these accounts just by analyzing their posting patterns. Take their last 200 tweets and find the maximum number of reply tweets within any 5-minute window. If it's 4 or higher, it's an automated reply account. I manually tagged 100 suspicious accounts and 50 terminally online accounts. This single if matched 86/100 of sus accounts and none of the terminally online ones. I've been running this for a few days now and I'm still surprised by the accuracy. I'm pretty sure you can detect almost all of this AI slop without even looking at the content of tweets. I manually checked "false positives" I got and all of them were either: (a) accounts spamming gifs/single words/emoji replies, which is more or less the same behavior just without AI (b) accounts that used AI replies in the past. tl;dr: fixing majority of the current slop apocalypse requires a 0.1x engineer and a minimal effort

@ivanfioravanti What is your opinion on oMLX?

This is super! 🔥 2 pi coding agents + oMLX with Nemotron-Cascade-2-30B-A3B-6bit running in parallel on M5 Max. Great and fast model!

@ivanfioravanti @hornsby_andrew Yes please!

@hornsby_andrew Gonna try!

MLX 4bit vs MLX ParoQuant 4bit using Qwen3.5-9B 📣 As you can see below there is no match. I will try to do same with 8bit in next days to do a comparison. ParoQuant is my new go to quantization below 8bit! I have limited max-tokens in some cases, but the important thing is that same limits have been applied to both quantizations.

@cybrtrkguy This is the way.

Wait a damn minute... If MacOS runs on the A18 Pro (last year's iPhone chip), what's stopping Apple from creating a dock to make your iPhone into your Desktop? Samsung and HP tried this a decade ago, and it never caught on.

@elonmusk @gork, is this true?

Gork returns today

@patramanchan Needs VR. And a bucket.

A brain-melting FPS that takes place inside a giant sphere🤯 Game: Orbifold #SteamNextFest #indiegame

@ivanfioravanti I'll take less beautiful graphics and play now over looksmaxxing and waiting anytime.

@FritsKarl This is so true! When I want to play I want to do it on the fly!

Windows PC with 3090 started after several months, updating everything for the next few hours. 😢

@forestmanjohn 26.99, yw

3 months ago, I quit my job to chase a dream: to build an affordable, convenient, plastic-free coffee maker. Grateful for everyone who has reserved ❤️ puresteelco.com

@digitalix Def

should?

@beffjezos Give the agents avatars in VR, much more interesting.

Apple Vision would sell like hot cakes if you could have multiple virtual computer monitors Would be an insane setup to manage a ton of agentic windows

@levelsio Can I haz moar Firefly plz?

Imagine the future We'll get entire new seasons of shows that ended decades ago Probably counterfeit and made by fans Some really good ones too

If you encounter strange behavior on your Apple Silicon Mac during LLM experiments, reboot. This resolves 80% of my issues.

@ivanfioravanti @PromptInjection @QuixiAI Haven't tried with MiniMax 2.5, but Qwen3-coder-next mxfp4 is very close to 8bit, like margin of error close. Lower results than 4bit is strange, that should not happen with mxfp4.

@FritsKarl @PromptInjection @QuixiAI Are you sure? In the past I got lower results vs 4bit.

MLX MiniMax 2.5 running LOCALLY on a single M3 Ultra 512GB! Writing a poem on LLMs at 6bit quantization! 🔥 Let's start some coding, context and distributed tests! Generation: 40.2 tokens-per-sec Peak memory: 186 GB

@ivanfioravanti @PromptInjection @QuixiAI Try mxfp4, 4bit size close to 8bit performance.

@PromptInjection @QuixiAI Moreover 4bit is a bit too much for this model.

@lost_nomad__ The Netherlands fits in that area at least three times.

Should we offer refugee status for the Dutch? Maybe we could send them to drain the Carolina lowlands and build a new city somewhere here Any thoughts?

@ID_AA_Carmack I just rewatched Person of Interest. Many such ideas in that show.

The modern age has richly rewarded people with a combination of high intelligence and high agency. Now that many aspects of intelligence are successfully being automated, it seems likely that people with relatively lower intelligence but exceptional agency will come into their own if they are willing to egolessly accept AI advice. Imagine a ruthless criminal that completely trusts everything their always-on AI glasses are telling them, knowing that it is carefully looking out for their best interests and isn’t scheming to betray them.