We have continued with the testing/research. We have seen a gigantic improvement with the `PASSING` tests. When we changed the objective agents/models to more careful model, we had a failed test after 3 continue attempts. We will continue with this test, the failed test was: `research/05-memory/atomics.md`. We also published the `issues` which are both capable of displaying failed and passed tests: https://git.revivesparc.com/riscvcxh1/xh1-research-fork/issues.
We are going to continue more tests, and make sure that the `atomics` research will pass.
riscvcxh1