ssk42

Straight up - why not just name them Cheapest, Cheaper, Expensive and More Expensive? Cost seems to be the main driver of the intuitive difference between models.

/model then roles and also /agents for when a model chooses to delegate out sub agents

My gut instinct is that this is about when all of their on prem servers were EOL and their /public cloud solution was required. This must have had something to do with that

That’s what my KimiClaw has literally been doing

What is your favorite harness for the open weights?

If I recall correctly, in their pivot to Codex they took a sizable amount of compute away from ChatGPT

I’m sorry but in this day and age, why would you not use AI with safeguards? With giving it the proper context and best practices you’re looking for. These are all very solved in Claude and any agentic system. Are you saying that you don’t? This just feels insulting to those of us who do care about code but do love Claude

Can you defend that though? Does living mean needing cells? Does it mean possessing the ability to think and reason? Is Claude thinking and reasoning?

What

Well I mean yes. I think people ought be aware for how the harnesses compare for their stacks. But clean room applies for this RGR situation too

Fun to see you not on tildes.

Setting up a clean room is one of the only ways to do Evals on agentic harnesses. Especially prevalent with Windsurf which doesn’t have an easy CLI start.

So how? The easiest answer when allowed is docker. Literally new image per prompt. There’s also flags with Claude to not use memory and from there you can use -p to have it just be like a normal cli tool. Windsurf requires manual effort of starting it up in a new dir.

ClawdBots can now more easily interact with the Internet than regular agents, so you wind up with Moltbook leaking

Probably. It was on my tiktok FYP

The biggest clue I’ve seen is someone using it to do cold calls on websites. Claw searches for shoddy-looking construction sites, makes a better version on Vercel, and sends out a pitch.

I saw an interesting comment somewhere that this will ultimately be Anthropic’s goal: creating the next generation of of App Store. The idea that Anthropic could just be building the mini vibe code to whatever the user wants. This post clearly exemplifies that me-apps can and should be a thing. That anyone can put forth reasonable effort and make an app without having to cross hard learning barriers of effort.