seaal

Just ask one of the Chinese models.

The monthly API credits for Max plan seems fantastic, especially considering Haiku pricing. Being able to actually use my Claude plan for other harnesses and use-cases on top of regular CC usage is everything I wanted.

Anthropic has really been doing all the right things in the past few weeks, while OpenAI continues to fumble the bag.

Just got access in Codex, looking forward to trying it out. Opus 5.5 has blown me away with what it's capable of doing, hopefully 6.1 will actually be a worthwhile contender.

Excited to tryout Decisions API as well.

Brave has the best filter lists built into a blocker. Between Bypass Paywalls Clean Filters and Brave Experimental Adblock rules for blocking twitch.tv ads, it's just the best option for most people.

Giving away Brave Origin for free on Linux is just the cherry on top.

The madlads finally did it, now if only I could use my Claude sub in other harnesses without risking getting banned.

Seriously, it’s funny how confident people can be about something despite their awful reading comprehension.

Well, Luna debuted with 5x higher pricing than is currently available. With the pace of recent development these models might not be relevant by Thanksgiving.

Only 73K output tokens too. Anthropic should really be embarrassed with their Sonnet 5 price/performance.

There's a lot of brand confusion among the American models right now. ChatGPT, Claude, Gemma, OpenAI, Meta, Google, Muse Spark, Anthropic, Microsoft, Gemini. We might know the difference (or I should say, someone does because I'm losing track already) but these models have no chance at end user penetration and loyalty until there's a single focused survivor.

It took me a year talking about it until my wife knew that Kimi K3 and GLM 5.3 are two different things.

Seriously, I wonder how many tokens are generated (wasted) every day on someone recreating another agent memory, context management, code graph, etc.

I can’t wait until Qwen 4.5 27B or Gemma 5.

this seem disingenuous, seems like his company just is the natural evolution of companies having phising attack simulation training.

>And can SOMEONE please tell artificialanalysis that using dark blue for both Deepseek AND OpenAI is an especially unfortunate choice of colors, especially today?

uhh openai is dark gray: `rgb(31, 31, 31)` and i'm pretty sure it always has been?

Is there any resource or benchmark actually comparing how different harnesses perform with a given model?

Really just feels like endless FOMO with how fast the iteration cycle is for harness and model development.