Site Activity

I’m really looking forward to trying this. A million-token output limit is impressive, but what interests me more is whether the model can stay coherent, follow requirements, and verify its work throughout a long task.

For software development and automation, the real gain would be spending less time correcting an agent or helping it recover context between steps. If Argon delivers on that, it could make a meaningful difference to how I build projects. Eager to see how it performs on my own...

It's getting hard to judge which LLM subscription will be the best for your individual use case. This Gemini 4 costs more than GPT-6.1-Sol for solving tasks, but scores much higher in the APEX-Agents benchmark.

For me it comes down to personal preference: don't give Google, Microsoft, or Meta any data if I can help it. So I stay with Claude/OpenAI.

Has started its own censorship. Relies on non-free software such as Apple Maps instead of OSM. With it's end of partnership with Yandex will probably be just a shell for Bing results. As a long-time, DDG user, I should say I had to emigrate from it.

After Warner bought them out, they removed the AI models and put in inferior models so the average person could not compete with their artists. They just did this in September 2026.

Subscription on windows, asked prices are just sad, better get lifetime office.

Never saw this working out, webkit is too niche and limited. I like what kagi is trying to do... but practically speaking I think they are better off spending their time and resources on different things. Apple isnt the golden goose it used to be and i dont see the average 'iphone user' downloading Orion Browser