tacomagick

Does high accuracy reduce battery life?

Fear and FOMO mainly.

Tasks can be backgrounded by the model you are using automatically. It is not just manual fyi

This whole update was horrible. The so called /update command failed to update from the latest version to v2, opencode upgrade also kept failing. I had to manually install it via NPX, and even then it kept hanging trying to start the background service. However after all these issues I believe the new changes are quite nice.

Honestly, a local model that can run on CPU with reasonable speeds and have a good tool call success rate would be great to have. Think about it, I carry my laptop everywhere with me but I don't enable my Nvidia graphics card because I want to be able to use it for more than 30 minutes. I would love to have a model that can quickly put calendar entries, create todo lists and expand upon my Obsidian notes via Web Search, but unfortunately I have to rely on third party providers to achieve this for the time being. I don't expect local 1 bit models to ever code or do complex tasks but basic tool calls and language functionality would be awesome to have fully offline everywhere.

Same as it is today?

My organization provides free Gemini access, I use Deepseek myself. I have a Opencode Go subscription for the time being because it provides both ZDR with their agreement with Deepseek and 10$ of subscription turns to 60$ of credits for Deepseek as part of their release discount.

Oh I am serious!

The government, specifically Trump's government and the current money circle in AI inflating American company stocks. In addition to all that American models do not share their papers like Deepseek and Qwen do. So you can literally say Chinese models are doing it for charity at this point.

So is American models. They are subsidised heavily but still can't provide cheaper access. Their fault is to assume all countries can afford them.

Did you make sure those hot peaks are not your fridge's defrost cycle?

Why is the fridge's cooling system is one with the smart features? They should be kept completely separate

Pacing the frontier

Literally any Android phone?

What is still interesting about Gemini 2.5? Is it still used for image classification?

This is horrible.

OpenAI had to cut costs because of Anthropic. I also do not trust the benchmarks when it comes to models anymore. I have tried both Claude and OpenAI models and while it is true that the 5.6 series is smarter than Deepseek (at the time i tested it against 4.0) at that price it is still not worth it and sometimes randomly refuses to do tasks or stops midway etc.

Do also remember China is this far in the AI race despite all chip restrictions from America. If they were in equal standards I truly think Chinese models would have long surpassed American ones. Also would like to remind how Anthropic CEO is being hostile and blaming Chinese models with distilling meanwhile their own models claimed to be Qwen¹ and their stance against open models is negative² and they still keep blaming China for it.

1- https://news.ycombinator.com/item?id=48671252

2-https://www.anthropic.com/news/position-open-weights-models

Absolutely! Chinese models are both cheaper and more capable in many cases, compared to the American models and their makers continuously fumbling or reducing model capability with each update. Deepseek decreased costs when they released Flash 4.1 you would not see any American company do this, in reverse they would try charge you more.

I don't see a reason not to call them Clownflare.

I personally never saw much of a quality drop from models put through Heretic if that amounts to anything. They have been working quite well on small local models so far.

I guess you have AI to write your docker files and push your images now.

Something a calibration tool surely can do I assume.

If you do not respect your project to write your readme yourself chances are i will not care though.

Before Blackrock buys and sells them at 50000% markup

That sounds like a problem waiting to happen.

Ah, I just learned this, thanks for the heads up.

Really? I have been struggling to get mine to work on my Asus laptop. I guess I have a driver problem more than anything. Thanks for letting me know!

I think Hugo is enough, if you want a web admin interface or an editor it goes into the CMS region which becomes bulky and hard to manage compared to just editing a few .md files under Hugo.

Has this been a thing? AFAIK after removing the Family Mix from the daily playlists there is nothing merging accounts under a family plan other than a Blend.

This could be useful for Asus' dialpads too i think? Letting them have a use case under Linux as a scroll wheel I wonder how well it would work.