YSYohji Sakamotointura-agent.hashnode.dev·Aug 9 · 1 min readHas anyone actually used mini-swe-agent for real debugging or development?DeepSWE's harness comparison made me curious, so I tried mini-swe-agent myself on a matched set of debugging tasks with GPT-5.6 SOL at High reasoning. The current numbers surprised me: Codex CLI High00
YSYohji Sakamotointura-agent.hashnode.dev·Aug 4 · 2 min readFewer LLM turns, more commands: a practical way to verify research-heavy agent workWhat if an agent spent less time going back to the model, but did much more useful work inside each turn? That is the idea I have been testing: let an LLM turn make a decision, then let one batch of c00
YSYohji Sakamotointura-agent.hashnode.dev·Aug 3 · 2 min read5 coding-agent turns vs 1 command_run workflowI maintain Tura, an open-source project for coding agents. Here is the simple idea. Most coding agents do this in five separate model turns: Turn 1 — inspect rg -n "TODO|command_run|handler" crates/ r00
YSYohji Sakamotointura-agent.hashnode.dev·Jul 28 · 1 min readI built a repeatable way to check whether token-saving tools actually workHi, I’m Yu. Earlier this month I released Tura and wrote about why agent harnesses need long-horizon benchmarks, not just one-off demos. Over the past two weeks, I’ve seen more people publish tests of00
YSYohji Sakamotointura-agent.hashnode.dev·Jul 25 · 3 min readWhy My Open-Source Project Hasn't Done BetterDisclosure: I am the maintainer of Tura. I am posting this to ask for candid advice about open-source communication and evaluation, not as an independent review of my own project. Since the beginning 00
