scosman

> MCP of today is not the MCP of yesteryear

MCP is 22 months old. Pi is 10 months old :)

send it "play minecraft", honestly strange

honestly it's horrible compared to some of the Opus 5.5 ones. But yeah, at the latency/speed you're looking for it's a different ballpark. Let Opus write the style and reference screens/animations, let your small fast model assemble it from parts.

These AI explainers are taking over. I tried getting this working back in May. The models were okay but not quite there and it was a ton of effort. Opus 5.5 seems like the tipping point.

I made an OSS framework for these for when you want to go beyond one-shoting it: https://github.com/scosman/videowright

- Voiceovers: aligns animations to the voiceover, can generate voiceover with elevenlabs, or will transcribe and timestamp a real voiceover

- can reorder scenes both in code, and using ffmpeg for audio.

- interactive controls during authoring, can ask for micro edits or re-builds

- MP4 export/encoder

- Generates a video from a prompt (obvs)

I have an OSS framework for this: https://github.com/scosman/videowright

- Voiceovers: aligns animations to the voiceover, can generate voiceover with elevenlabs, or will transcribe and timestamp a real voiceover

- can reorder scenes both in code, and using ffmpeg for audio.

- interactive controls during authoring, can ask for micro edits or re-builds

- MP4 export/encoder

- Generates the video with agent of your choice (obviously)

well same applies to GPT OSS 120. Qwen is just the much smarter model of the 2 public options on Cerebras.

Or better: Qwen 2.8 27b

hmm, I was talking about Opus 5.1 but apparently it was a real life hallucination!? Time for bed.

Excluding Opus 5.1 from the coding benchmarks is telling. Opus 5 already matches Astra, Opus 5.1 is much better than 5, and 5.5 is much better again.

OpenAI seems really competitive in most areas, and extremely competitive on cost, but still behind on coding.

Why is the link to a (seemingly) AI summary?

Their page: https://opennoodle.de

Their GitHub: https://github.com/open-noodle/gallery

The number of vibe coded apps accidentally hosted on dev laptops is about to explode.

They can plan, but no guarantee it will produce what you want. Sometimes most of the work is aligning on what to build. And I'm not handing over technical planning to it yet.

I use this skill and it makes the specing process progressive. Human driven for the "what", 50/50 for higher level technical planning, only where it has questions in the low level details: https://github.com/scosman/vibe-crafting

Oh, Canada wouldn't actually welcome a local monarch. Ceremonial across a sea... sure, why not. A King moving to our shores, nope.

I've done this exact mode on my Mitsubishi ACs. Despite being old units that came with the house, they are instantly responsive and report back current temperature flawlessly.

ESPHome device are consistently faster and more reliable than any smart home tech I buy at 10x the price (not hard with $3 boards).

I made https://froogle.fyi out of a desire to get that old school search back. Source: https://github.com/scosman/froogle

It hasn’t replaced Kagi as my daily driver but the UX is fun.

highly recommend clicking "Listen to this blog post". Not what I was expecting...

one box of cables?

those are rookie numbers

why is it jumping through hoops to get online if it's already online?

> “nobody asked for this”

I absolutely want a general purpose assistant.

I absolutely don't trust Facebook with the necessary data.

Ah yes. Using that OTA update it got via AM radio.

Reminder: you can connect it to your network, but block it from the internet at the router. That way you can still use Airplay/Chromecast.

I have an LG. Great OLED panel. It's never seen the internet.

Proxmox + community-scripts.org is pretty great.

I wanted to say "You actually can't fly a helicopter to the top of Everest, the air is too thin", but apparently it's been done exactly twice. Stripped down specially chopper and ideal weather conditions.

Community effort happening here to build the ideal dataset: https://github.com/scosman/pelicans_riding_bicycles

The year is 2031, the Meta LlamaBrush won't start until it's played a 30s unskipable ad for Doritos spearmint.

They were investing in ANE and Metal before everyone in consumer. Hardly asleep. They just underestimated the market size, as pretty much everyone did.

Right now sweet spot is voice transcription. Meeting recording apps are genuinely better locally than in cloud. Can run on an M1 easily. Latency matters. I built https://github.com/scosman/Biscotti and see zero reason to use cloud ever again.

LLMs are harder: not much useful below 12B, and the 700B+ ones are really much better. Models like Qwen 3.8 27b show promise: in a few years pretty good local AI should be in reach for anyone willing to buy a $1000 computer (but who knows what your $20 sub buys you then).

z.ai is using all Chinese hardware for flash: https://thenewstack.io/glm-5-3-flash-chinese-chips/

There are other providers with much faster inference, like BaseTen at >100t/s: https://openrouter.ai/z-ai/glm-5.3-flash#performance

You can't compare models released 6+ months apart. GLM 5.2 was same architecture as 5.3 and not nearly as good. Takes time to build frontier intelligence and distill down to smaller sizes.