Source record
Advanced AI models work better when the prompt defines the goal and success criteria instead of micromanaging every step.
8 and how it had mixed reviews. 8 for three days and I gotta say, kind of like it.
8 so much and why it might have got mixed reviews at first. 8, I did feel it was a little verbose, sterile, academic, but over the last three days I've realized it's really smart. I also think they might have changed the system prompt after release.
A lot of you are pointing out that it seems like it was forcing disagreement with you to avoid being sycophantic, and it would give these overly long explanations of why it was doing what it was doing. This is just anecdotal, of course, but I feel like that stopped after the first day or two.
8 really shines is when you give it a clear goal. 8 the way you used dumber models, where you give it explicit step by step instructions, it's gonna overthink the task and just spend all your tokens.
But if you treat it like the super smart senior level member of your team that it really is, and just to find exactly what success looks like, let it come up with the step by step instructions, it's phenomenal. It just gets me now.
I'm not saying to give it shorter prompts or less context. You should still be loading in all the context you possibly can, but the focus of your instruction should be on the goal for the task. What are you really trying to accomplish?
8 has excelled the most for me is when creating skills for clod. So much better than me at articulating what I want each skill to do. And this aligns with some of the benchmarks that Anthropic put out.
8 is four times more likely to catch bugs in code that it wrote.
8 is the best model at using Claude. I think we're truly starting to see the recursive self improvement flywheel take off.
And in just a few weeks, Anthropic will be releasing their methodos model. Except it won't be the methodos they already showed us. 8 has.
And yes, it will definitely be incredibly expensive, but it's also the model that's writing almost all of the code at Anthropic.
The model's improving itself. We're using the model to improve the systems. We're building on the model.
I don't know where I'm going with any of this, but it's all really exciting.
Advanced AI models work better when the prompt defines the goal and success criteria instead of micromanaging every step.
For senior-level model work, load the relevant context, state what success looks like, and let the model choose the intermediate steps rather than forcing a brittle step-by-step script.
If you try to use 4.8 the way you used dumber models, where you give it explicit step by step instructions, it's gonna overthink the task and just spend all your tokens. But if you treat it like the super smart senior level member of your team that it really is, and just to find exactly what success looks like, let it come up with the step by step...
Base2026 attributes this public source record to @tjrobertson52, published 2026-06-03, with the original platform link and correction/removal path kept on the page.