<feed xmlns='http://www.w3.org/2005/Atom'>
<title>ctak/Makefile, branch main</title>
<subtitle>An implementation of Tak and a computer opponent in C</subtitle>
<id>https://git.l-3.space/ctak/atom?h=main</id>
<link rel='self' href='https://git.l-3.space/ctak/atom?h=main'/>
<link rel='alternate' type='text/html' href='https://git.l-3.space/ctak/'/>
<updated>2026-08-28T18:37:41Z</updated>
<entry>
<title>new neural network arch (faster + better) &amp; minor changes + fixes</title>
<updated>2026-08-28T18:37:41Z</updated>
<author>
<name>tslil clingman</name>
<email>tslil@posteo.de</email>
</author>
<published>2023-01-15T15:03:37Z</published>
<link rel='alternate' type='text/html' href='https://git.l-3.space/ctak/commit/?id=ee216c008a188a9436fedb85c70ee5d1719733b1'/>
<id>urn:sha1:ee216c008a188a9436fedb85c70ee5d1719733b1</id>
<content type='text'>
Gone is the convolutional neural network, for it turns out not only is
it more difficult to train, but all of the extra information about
board layers didn't make much of a difference at this size.

So cnn1986 has been replaced by nn1986, a standard, two-layer, dense
nn configured as a binary classifier and (mis)used in that capacity.
Note: total number of parameters is unchanged.

HARK: this new nn exposes a bug somewhere in ctak. Run ctlm with
self-play to see the completely borked board state at the end.
</content>
</entry>
<entry>
<title>--fast-math seems saves some time</title>
<updated>2026-08-28T18:37:41Z</updated>
<author>
<name>tslil clingman</name>
<email>tslil@posteo.de</email>
</author>
<published>2021-10-22T19:33:06Z</published>
<link rel='alternate' type='text/html' href='https://git.l-3.space/ctak/commit/?id=7cf3a656d0c923dd92025c09747461f2f2d1bed0'/>
<id>urn:sha1:7cf3a656d0c923dd92025c09747461f2f2d1bed0</id>
<content type='text'>
That i can tell at a glance, the largest relevant change this
introduces is flush-to-zero for floats. Some testing is required to
ensure that the CNN isn't too sensitive to this. Preferable to that
option is to simply train it without relying on subnormal floats in
the first place.
</content>
</entry>
<entry>
<title>Welcome geminict!</title>
<updated>2026-08-28T18:37:41Z</updated>
<author>
<name>tslil clingman</name>
<email>tslil@posteo.de</email>
</author>
<published>2021-10-05T22:22:23Z</published>
<link rel='alternate' type='text/html' href='https://git.l-3.space/ctak/commit/?id=cf175fc346f1b208766b1f55d3673a7b208f322a'/>
<id>urn:sha1:cf175fc346f1b208766b1f55d3673a7b208f322a</id>
<content type='text'>
This is a special interface to negamax_cnn1986 which is designed to
generate output for use in a CGI tak interface to be used over gemini.

Also in this commit is a reformating of the various source files to
use the traditional tab width of 8 spaces.
</content>
</entry>
<entry>
<title>Renamed binaries</title>
<updated>2026-08-28T18:37:41Z</updated>
<author>
<name>tslil clingman</name>
<email>tslil@posteo.de</email>
</author>
<published>2021-02-05T19:02:36Z</published>
<link rel='alternate' type='text/html' href='https://git.l-3.space/ctak/commit/?id=5c475a552dbf16589d212bc7de7ed526b47aad08'/>
<id>urn:sha1:5c475a552dbf16589d212bc7de7ed526b47aad08</id>
<content type='text'>
</content>
</entry>
<entry>
<title>TEI interface working!</title>
<updated>2026-08-28T18:37:41Z</updated>
<author>
<name>tslil clingman</name>
<email>tslil@posteo.de</email>
</author>
<published>2021-02-03T00:23:54Z</published>
<link rel='alternate' type='text/html' href='https://git.l-3.space/ctak/commit/?id=40c6b1dafab4de169bac8a799e7953e85061218e'/>
<id>urn:sha1:40c6b1dafab4de169bac8a799e7953e85061218e</id>
<content type='text'>
</content>
</entry>
<entry>
<title>Fairly important bug fixes to lcdlib, LCD now echoes input!</title>
<updated>2026-08-28T18:37:41Z</updated>
<author>
<name>tslil clingman</name>
<email>tslil@posteo.de</email>
</author>
<published>2021-01-31T20:33:30Z</published>
<link rel='alternate' type='text/html' href='https://git.l-3.space/ctak/commit/?id=399d90f1b94717aa0ca5abb1dc43bdb6f4160d13'/>
<id>urn:sha1:399d90f1b94717aa0ca5abb1dc43bdb6f4160d13</id>
<content type='text'>
Input polling without line-buffering is done using ncurses, so the
buildroot configuration had to change accordingly to include that
library.

The Makefile changed to accommodate stand-alone building of ct1986 and
to include -lcurses where appropriate. There were also some typos
about copying ct1986 and ctaklm to the correct directories.
</content>
</entry>
<entry>
<title>Try to squeeze out a little more performance</title>
<updated>2026-08-28T18:37:41Z</updated>
<author>
<name>tslil clingman</name>
<email>tslil@posteo.de</email>
</author>
<published>2021-01-30T21:47:48Z</published>
<link rel='alternate' type='text/html' href='https://git.l-3.space/ctak/commit/?id=84ad2e3c12cb505e3c5e3dd29d05edb529b82174'/>
<id>urn:sha1:84ad2e3c12cb505e3c5e3dd29d05edb529b82174</id>
<content type='text'>
``Common wisdom'' dictates that placements are often better than stack
moves, so we bias the generated move list in this fashion. Seems to be
a little faster.
</content>
</entry>
<entry>
<title>Purged uninteresting statistics</title>
<updated>2026-08-28T18:37:41Z</updated>
<author>
<name>tslil</name>
<email>tslil@posteo.de</email>
</author>
<published>2021-01-29T22:52:58Z</published>
<link rel='alternate' type='text/html' href='https://git.l-3.space/ctak/commit/?id=bda3a7edb76c9fe3dc21cbe5a0836829b705b407'/>
<id>urn:sha1:bda3a7edb76c9fe3dc21cbe5a0836829b705b407</id>
<content type='text'>
</content>
</entry>
<entry>
<title>Cleaned up build system</title>
<updated>2026-08-28T18:37:41Z</updated>
<author>
<name>tslil clingman</name>
<email>tslil@posteo.de</email>
</author>
<published>2021-01-29T18:06:49Z</published>
<link rel='alternate' type='text/html' href='https://git.l-3.space/ctak/commit/?id=6c1154d80e7f7a04444d01d97942ac9e8138297a'/>
<id>urn:sha1:6c1154d80e7f7a04444d01d97942ac9e8138297a</id>
<content type='text'>
</content>
</entry>
<entry>
<title>Added license information!</title>
<updated>2026-08-28T18:37:41Z</updated>
<author>
<name>tslil clingman</name>
<email>tslil@posteo.de</email>
</author>
<published>2021-01-29T02:30:30Z</published>
<link rel='alternate' type='text/html' href='https://git.l-3.space/ctak/commit/?id=a77062ce3dc9a99ad0662010cc7eeb00dd5036a6'/>
<id>urn:sha1:a77062ce3dc9a99ad0662010cc7eeb00dd5036a6</id>
<content type='text'>
</content>
</entry>
</feed>
