siquick

30 days

There is actually an interrupt mode in NotebookLM now.

Overall I've found it the best AI product Google have. Only complaint I have about it is the hyper positive US corporate accents get pretty annoying pretty quickly.

The realtime voice in ChatGPT is excellent, the newer model is a big step up too.

He runs one of the industries leading analyst firms, probably not worth him having a reputation of making numbers up.

https://semianalysis.com/

They're making a "few hundred million of ARR" - not bad for a company who only launched their first product, a training platform called Tinker in October last year.

https://x.com/deedydas/status/2072340532718887068

amazing thanks

Very nice - would love to see the ability to open a Dockerfile directly in the UI to build/run it.

Likert scale just doesn't work in LLM evals. My idea of 3/5 is different from your 3 and definitely different from an non-deterministic system's 3.

DGX Spark is really poor at inference due to the memory bandwidth so hopefully they’ve fixed that before touting this as a way to run local models.

You're right, I use Brave on iOS but Safari doesn't let you choose beyond a defined list.

Only downside is the Search on mobile. You have to install an app and enable it as extension on safari. Logging in never worked and couldn't enable my premium Kagi on iPhone.

I just have Kagi set a custom search engine in mobile browser - no seperate app needed.

https://kagi.com/search?q=%s

+1 for Kagi. Been a subscriber for almost 2 years and no intention of cancelling, it just works.

Solved !== Good

This is exactly my experience of working in an agency. Made worse by Figma defaulting to 1440px so every design only really works at that width.

It’s just gambling without the stigma of being called an addict.

Love what you guys have done with Unsloth. Any plans to have this running as a hosted product where Unsloth provide the GPUs?

These days I hit the quick answer button inside Kagi more often

Just incase you didn’t know you can append ? to any query and get a quick answer straight away

This may help you work out the best quant to use for your use case.

https://www.siquick.com/blog/model-quantization-fine-tuning-...

Sure sounds like automatic weapons targeting using Anthropic models to me.

However much they try to make us think otherwise, at this point in time there’s not really any “good guys” in the AI race.

Start here

https://modal.com/docs/examples/vllm_inference

or give this a go

https://modal.com/docs/examples/opencode_server

You get $30 free credits each month on Modal which is enough to play around (i have no affiliation, just think they run a great service)

Rent a H100 on Modal which scales down to zero when not in use - you can set the time out period.

Cold boot times are around 5m but if your usage periods are predictable it can work out ok. Works out at $2 an hour.

Still far more expensive than a ChatGPT sub.

Skills in CC have been a bit frustrating for me. They don't trigger reliably

Referencing them in AGENTS/CLAUDE.md has increased their usage for me.

This is truly great - just joined the universal fund.

I tried to signup from the nav bar but kept getting a 500 error from the sign_up.json endpoint. I had to go through the Donate flow to be able to create an account.

Misread the post - it doesn’t include the API

2 weeks notice to migrate to a different style of model (“normal” 4.1-mini to reasoning 5.1) is bad form.

In football we’d call the US “tap-in merchants”.

Running one of the world’s leading UI libraries is far more impactful than anything 99% of FAANG engineers have or will ever work on.

Is there a way to see the shape of the metadata?

That links gives an error and so does https://openrouter.ai/docs/guides/overview/multimodal/pdfs

Personally, I think a big driver of this belief is a tendency in the West to not challenge each other's views or hold each other accountable - "don't talk politics at Thanksgiving" sort of thing

We’re in such a “you’re either with us or against us” phase of politics that a discussion with the “other team” is difficult.

Combine that with people adopting political viewpoints as a big part of their personality and any disagreement is seen as a personal attack.

Suggestion - don’t require the latest iOS26. A lot of people aren’t installing it as it’s not great. You’re missing out on a lot of users and unless you require a specific feature that only 26 has then it’s no necessary to mandate 26.