alt Hacker NewsAnthropic would be better off letting the community do this. Their harness sucks. Great scientists but not the best app developers. I suspect they just dont want to relinquish control of anything because they think the world cant be trusted with AI, we can only be trusted to pay them.
Replies
Someone1234 • today at 3:53 AM
Could you go into more details about why their "harness sucks?" This feels like a shared conclusion, but I've used several and theirs is better than many.
➕ show 1 reply
cultofmetatron • today at 6:52 AM
I've been greatly enjoying jetbrain's air IDE for some tasks. it uses claude behind the scenes.
paulddraper • today at 2:43 AM
?
Anthropic made the most popular harness for developers.
Anthropic made the most popular desktop tool for AI automation.
➕ show 2 replies
Custom agents using the low level completion APIs tend to outperform these generic tools, especially when you are working with complex problems.
It's hard to beat domain specific code. I can avoid massive prompts and token bloat if my execution environment, tools and error feedback provide effectively the same constraints.
If I had to pick only one tool for a generic agent to use, it would definitely be ExecuteSqlQuery (or a superset like ExecuteShell). If you gave me an agent framework and this is all it could do, I'd probably be ok for quite a while. SQL can absorb the domain specific concerns quite well. Consider that tool definitions also consume tokens.