I got pretty good mileage out of context engineering, adding my personal coding heuristics to my AGENTS.md and referencing subdocuments on a "when doing X, consult Y" pattern. I assume others are doing similar things, but I was pretty surprised when I was able to get it to generate code that is pretty close to what I would do if I was doing it manually. I'm curious if scientists and mathematicians are doing things like that. "When I see X, I typically immediately check Y" or whatever their domain heuristics look like.
JOjohnnyApplePRNG4小时前
Not surprised to see Claude significantly higher in scientific intelligence than Sol.
You can tell that Claude really does grasp a wide array of highly specific scientific and mathematical nuances... where's codex is just basically for coding and that's it.
That's the feel I get from the both of them anyways and I've used both on the 20x plan for the past week at length.
Don't get me wrong, codex is great at finding bugs and building games. It's great.
AKakshay_akula6小时前
Evals on actual research workflows is the right direction, most agent benches are toy tasks.
JEjerpint4小时前
The fact that opus 5 is outperforming fable is odd to me
From personal experience, opus 5 feels net inferior to fable on almost every aspect (for coding tasks)
RErespectattentio3小时前
Like you were reading my mind. I was waiting for such benchmark to land. This will improve models for such scientific research workflows.
AI should have started with science from the beginning, not after 4 years.
I am building on top of it with agents to improve scientific workflows.
评论
5 条预览评论 · 正在加载完整讨论请先登录 h4cker 账号，然后连接 Hacker News 后发表评论。
I got pretty good mileage out of context engineering, adding my personal coding heuristics to my AGENTS.md and referencing subdocuments on a "when doing X, consult Y" pattern. I assume others are doing similar things, but I was pretty surprised when I was able to get it to generate code that is pretty close to what I would do if I was doing it manually. I'm curious if scientists and mathematicians are doing things like that. "When I see X, I typically immediately check Y" or whatever their domain heuristics look like.
Not surprised to see Claude significantly higher in scientific intelligence than Sol. You can tell that Claude really does grasp a wide array of highly specific scientific and mathematical nuances... where's codex is just basically for coding and that's it. That's the feel I get from the both of them anyways and I've used both on the 20x plan for the past week at length. Don't get me wrong, codex is great at finding bugs and building games. It's great.
Evals on actual research workflows is the right direction, most agent benches are toy tasks.
The fact that opus 5 is outperforming fable is odd to me From personal experience, opus 5 feels net inferior to fable on almost every aspect (for coding tasks)
Like you were reading my mind. I was waiting for such benchmark to land. This will improve models for such scientific research workflows. AI should have started with science from the beginning, not after 4 years. I am building on top of it with agents to improve scientific workflows.