syntaxing

Ive been 3D printing for over a decade, SLA printers are just not worth it IMO. There useful for certain applications, especially industry but for home hobbyist, FDM + 0.2mm nozzle would go further as a first 3D printer

Wow this price is interesting. I guess the Chinese competition is really driving prices down. I do miss the first generation (I think second was too) where they were "true" SLA but they got sued into oblivion by 3D Systems.

I had really good results with using Solidcraft (https://solidcraft.io/) for home stuff. Does 99% (I use solidworks makers for the remainder 1) of what I need and has a MCP connection which makes it fun. They use Nvidia’s recently open sourced BREP engine but Solidcraft is porting it to Rust.

As mentioned by another commenter, I mean Home Assistant. Essentially the main orchestrator for all my smart home things but it doesn’t limit to just smart home. You can add calendar and location sharing to HA.

I’ve been using 2.6B as my main home assistant model and it’s been good. I switched to Ling 3.0 Tiny since it’s faster with A1B. Really hoping 1.7B is good enough (2.5 version was too dumb for HA) so I can run everything on one machine.

I tried using thinkingcap Qwen 27B for about two weeks. It definitely does dumber things than vanilla 27B but isn’t too far off. Swift 1.5 is noticeably dumber that I stopped using it after one day. Oddly, I switched back to regular 27B because the thinkingcap one is noticeably more censored. Anything explicit gets instantly shot down by thinkingcap while vanilla 27B will chug along.

There’s also been documented cases of owners using AI edited images to claim guests damage. Airbnb has a systemic cultural issue.

I figured LLMs nowadays would be good enough to catch issues like this. Is it because it’s too costly to do it?

If only we can buy Huawei Ascends!

Opencode but mainly because I"m used to it from work. I also use Pi and OMP

The cost vs performance is insane for all these new models. I’ve been using Deepseek Flash 1017 and it does whole projects and asks for $0.10 on US provider with ZDR on Openrouter. I convinced a few friends to drop their Claude $20 subscription because DS Flash 1017 brings so much better value. They can still use Opus 5.5 for planning though each call will cost north of $2. Excited to try this model out too once there are US providers.

Wow it references some “old” models in the evaluations. Very nostalgic to hear some of these.

“ Those who would give up essential Liberty, to purchase a little temporary Safety, deserve neither Liberty nor Safety.”

- Benjamin Franklin

Step models were IMO the first local model you can run on 128GB shared memory that worked well. Really excited to see how it compares to Qwen Flash Next.

Edit: bummer, didn’t know it’s 600B-A27B. No way to run that on 228GB.

I like this so much. Maybe I’m romanticizing but hoping tools like this give local news a chance against monopolies like Sinclair Broadcasting.

Hah you’re probably dating yourself. Keras came out in 2015 and that was one of the early examples with Theano backend. You could train MNIST since 2015 pretty straight forward. But comparing Jev to image classification is an unfaithful argument. Comparing it to ELmo or BERT is analogously better.

I conduct interviews pretty often for various levels. Interviews seems so broken from both sides. Hard to find jobs that aren’t ghost jobs. Hard to find candidates that won’t cheat using AI and actually know their stuff. Just feels like AI has made hiring in tech even more inefficient which says a lot.

Interesting, I think it would be interesting to gauge how a 4B model would run compared to a frontier one

Surprised they didn’t try Qwen’s recently open sourced driving model https://huggingface.co/Qwen/Qwen-Drive-1.0-4B

I actually find the name System-1 as a nod to Daniel Kahneman’s Thinking fast and slow book kinda nice. It’s an interesting analogy

All these new models are such tease for us folks with 128GB of shared memory. Buying another unit now to expand to 256GB is a mortgage payment but it’s getting tempting…

Thanks! I really like how the author packaged everything into a container. Definitely going to give it a go over the weekend!

Halogen as in this right? https://github.com/peonist-ai/halogen-flash-server

Thanks! Have you seen issues with quantizing the kv cache?

Vulkan, I have never used ROCm on it but have been debating since the latest big update. How is your prefill? Do you hit over 1K? If it’s 1000K prefill, and 40 TG, I might have to try this over the weekend. Also, can you fit 128K without offload the ngram onto SSD?

Can you point me towards the model you use, both the main model and the flash model? Curious if I can get ~30 with a higher quant.

I’m on a strix halo @ GPU-5 with MTP and I get 600 prefill and 30 TG which pushes it into a very usable range. The odd thing is that Dflash2 is really slow for me, like sub 10 TG.

> audio-visual performance close to Gemini 3.8 Flash and overall audio performance that exceeds Gemini 3.8 Flash

Wow crazy if true. I think Gemini's audio capability and multi language was the "selling point" for a lot of people. Other capability also matches or exceeds 3.8 Flash.

They also made a new harness but github link seems to 404.

I said this before but I wonder if Dan Kan will reboot Atrium. Rally up some old partners and hope Anthropic buys them out for a couple billion.