| Age | Commit message (Expand) | Author |
|---|
| 2021-01-20 | In-lined as much as a i dare | tslil clingman |
| 2021-01-18 | First steps towards character LCD | tslil clingman |
| 2021-01-18 | Finally fixed move generation | tslil clingman |
| 2021-01-18 | Finally fixed memory order of weights! | tslil clingman |
| 2021-01-17 | Opps, wrong stone | tslil clingman |
| 2021-01-17 | Inlined placements, should be faster | tslil clingman |
| 2021-01-17 | Memory oob fix | tslil clingman |
| 2021-01-17 | Revert "Starting work on MCU port" | tslil clingman |
| 2021-01-17 | Leftover from another branch | tslil clingman |
| 2021-01-17 | Starting work on MCU port | tslil clingman |
| 2021-01-17 | New weights from a wider training | tslil clingman |
| 2021-01-16 | Beginning to work on probabilistic depth now that MCU is out | tslil clingman |
| 2021-01-16 | Went back up to 1986 weights | tslil |
| 2021-01-16 | Quick sketch of non-determinism | tslil |
| 2021-01-16 | Another road bug | tslil |
| 2021-01-15 | Dragon is not separate, fixed concession, allowing playing as b/w | tslil |
| 2021-01-15 | Changed function back to macro | tslil |
| 2021-01-15 | There was a bug in the minimax! | tslil |
| 2021-01-14 | Better trained weights, an important oversight in minimax (steps <=) | tslil |
| 2021-01-14 | So after a small tweak, it actually plays well! | tslil |
| 2021-01-14 | Seems tolerable, but not great. Still wont win or lose ??? | tslil |
| 2021-01-14 | Trying alpha-beta pruning. There's a bug somewhere ... | tslil |
| 2021-01-13 | Fixed minimax (!), fixed bugs in tak.c | tslil |
| 2021-01-13 | Trying minimax | tslil |
| 2021-01-13 | Crass error | tslil |
| 2021-01-13 | Weights? | tslil |
| 2021-01-13 | Wider? | tslil |
| 2021-01-13 | Trying various things to teach ti | tslil |
| 2021-01-12 | Have to account for CPS | tslil |
| 2021-01-12 | Well it works, and it's bad. Many bugs fixed in interim | tslil |
| 2021-01-12 | Closing in! | tslil |
| 2021-01-12 | Auto-generating weights | tslil |
| 2021-01-12 | New weights | tslil |
| 2021-01-12 | one output (of course), Pade approximant of logistic for activation | tslil |
| 2021-01-12 | Train on data that is close to the end of the game only | tslil |
| 2021-01-12 | This finally works! | tslil |
| 2021-01-11 | Close in principle, but there;s a bug in ct1997 &/ pptdb! | tslil |
| 2021-01-10 | This is the general idea, but i'm sure order is incorrect somewhere | tslil |
| 2021-01-10 | Starting on importing network! | tslil |
| 2021-01-08 | Fixed a small bug in PTN parsing, other stuff | tslil |
| 2021-01-07 | Check for road wins before flat wins | tslil |
| 2021-01-04 | Tabs for indentation, spaces for alignment | tslil |
| 2021-01-04 | Fixed indentation and some bugs, stats programme | tslil |
| 2021-01-03 | Set dialect to C99 | tslil |
| 2021-01-03 | Incorrect usage of globals in header | tslil |
| 2021-01-01 | In-lined a few things, reworked flat count to iterate only once | tslil |
| 2021-01-01 | tak.h now tracks win state, optimisations, saved a byte on counts | tslil |
| 2020-12-31 | Line-mode mostly complete | tslil |
| 2020-12-31 | Fixed road DFS errors | tslil |
| 2020-12-30 | Board printing | tslil |
