decide1000

In the Netherlands there is a computer museum with a huge collection. The computers can be used by anyone. Really a great experience for kids these days and adults.

https://www.homecomputermuseum.nl/en/

I use Whisper in combination with Qwen3.8 27b to create Dutch subtitles for Russian videos. I follow Ukrainian channels about the war and I am now able to understand them. In my tests with other languages Voxtral was better then Whisper. Whisper often makes mistakes which I now solve with an extra layer (qwen).

Sadly Mistral does not support Ukrainian. I hope this changes! I expect better from a European model

I agree. A better approach would be to have everyone access the harness for free, make it open source, when more resources are needed move the workload to Perplexity for a fee.

Qwen3.8-27B-PrismaAQUA-5.5bit-vllm

The output quality is higher. It's held at full precision (not quantized).

On the DGX I get 44.5 tokens per second (NVFP4). With 8 concurrent it's 241 t/s total.

I am using the PrismaAQUA

standard 9.7 t/s

+ Dflash2 30 t/s

+ torch-compile 37 t/s

c8 = 177 t/s

This should have been the link!

https://pplx-dgx-spark-lp-demo.pplx.app/

Looks very useful

update:

It advertises with local harness and models but its closed source and you need a pro or max account

It creates a hyper personal daily podcast with latest niche news which is interesting for me alone. And it does that pretty well.

You can probably create it yourself using an LLM, search and Elevenlabs.

Intel did some promising deals (dc, Europe, arc gpu) but still no real answers to AMD and Nvidia. I pulled out from Nvidia, MSFT and Intel and ramp up AMD. Too much happening for me in the AI space and miss the base that Intel used to have.

I use it for a while now. One thing that is super frustrating is that it saves it data (prompts etc) to the cache folder instead of applications data. Cache obviously can be deleted by the OS when disk space is limited or when there is a cleanup. I had to start over many times because of this. Also there is no way to report bugs bug for Spotify Studio.

I wouldn't describe it as luck, it's politics. The mother of Bill Gates had access to the board of IBM. She was also the co-founder of Microsoft.

That is just an amazing website and initiative.

https://rvembedded.com/products/project-lab/

Definitely interested!

It's not just the AI. The post mentions poor choices because of a product management mindset instead of engineers leading the PMs.

Great read. Exact pinpointing of my feelings about CF lately.

A lot of replies here are about Mac devices and their support for these 27B models. I own a MacBook but use a Lenovo Thinkstation PGX to run my models. It has a gb10 Blackwell gpu and 128gb unified memory. You can connect multiple ones.

If this is real I will stop my monthly subscriptions.

Finally! Now it becomes economic for us to make the move! Goodbye CloudFlare!

As a Nvidia Spark owner I can confirm that Linux is much more performant then Windows on that chip. If the goal is "doing stuff with AI" Windows is the last OS you want to look at.

Isn't voxtral much better?

Mostly ecommerce and pricing data. I work for marketplaces, brands, retail stores and even our own saas competitors. We match the EAN (gtin) to the correct SKU within seconds (Google Shopping, Amazon, etc). Part of it is our own trained ML models.

Despite that I find the goal of what you are trying to achieve questionable, I believe it should not be the AI that judges you here.

We are all witnessing the start of an AI era that will not end soon. Guiderails are a part in this development. I do have questions about the people, or systems, that decide on what's good and bad behavior. This tech is used in any country in the world. As long as they are able to pay their subscription in dollars, someone is able to use it. Is it up to a company to decide what's good or bad behavior? Is this a debate? Is this politics? Is this just a vision of one company? Would it shift in time? Will it be stricter for more hyper-intelligent models? Will it change when open source models are becoming better and better?

With scraper tech I mean a rust binary that is able to download and process thousands concurrent urls (millions per hour). Not to the same domain obviously. Paying more is not the issue here, its more the idea that an AI decides on what part of the spectrum I operate. Why is it opinionated? I am not doing anything wrong, why does it make me feel like I have to defend myself.

I am not using brew. Just checked and it still says 2.1.98. Will try manual update.

I am on the latest version available for me 2.1.98

I built a distributed DuckDB setup using OpenRaft for state replication. Every node holds a full copy of the database. Writes go through Raft consensus, reads are local. It's more like etcd-with-DuckDB than MotherDuck-lite.

OpenDuck takes a different approach with query federation with a gateway that splits execution across local and remote workers. My use case requires every node to serve reads independently with zero network latency, and to keep running if other nodes go down.

The PostgreSQL dependency for metadata feels heavy. Now you're operating two database systems instead of one. In my setup DuckDB stores both the Raft log and the application data, so there's a single storage engine to reason about.

Not saying my approach is universally better. If you need to query across datasets that don't fit on a single machine, OpenDuck's architecture makes more sense. But if you want replicated state with strong consistency, Raft + DuckDB works very well.

I'm building a Redis real-time backup platform with PITR (point in time recovery) to the exact millisecond. Besides downloads it has an emergency recovery option where you connect the Redis client directly to the master-replica to receive the latest version.

The key explorer let's you change data on the fly and receive notifications in real time when a condition is met (if value contains X).

It's build in Rust on bare metal wit isolation between clients and data.

ReplicaSafe.com (nothing there yet, will take a few weeks)

I think this model proves it's very efficient and accurate.

I am on Linux for 26 years. Last 5 years I run PopOs! on my desktop. User friendly and stable, Ubuntu based.

China and Europe (Mistral) show that models can be very good and much smaller then the current Chatgpt's/Claudes from this world. The US models are still the best, but for how long? And at what cost? It's great to work daily with Claude Code, but how realistic is it that they keep this lead.

This is a new tech where I don't see a big future role for US tech. They blocked chips, so China built their own. They blocked the machines (ASML) so China built their own.

I am the co-creator of ShoppingScraper. Convert an EAN / GTIN to pricing information, product specs, content or image. API-based and rapid with pricing and barcode data.

The website needs some love, but the webapp is going well.

https://shoppingscraper.com/features

They say: Dashboard Login Latency and Timeouts

They mean: You server will get connection timeouts through CloudFlare proxy