DW (@dken_w) header
DW (@dken_w) profile picture

building some stuff in gaming

Joined November 2020
Photo by DW (@dken_w)Photo by DW (@dken_w)Photo by DW (@dken_w)Photo by DW (@dken_w)Photo by DW (@dken_w)Photo by DW (@dken_w)Photo by DW (@dken_w)Photo by DW (@dken_w)Photo by DW (@dken_w)Photo by DW (@dken_w)
Pinned Tweet
Been vibecoding a little spaceship arcade arena shooter with Astra and Opus 5.5. Game is still sloppy, but the combat looks pretty cool so far. Here’s a bit of late-game gameplay
6
796
codex tip: when building internal tools, ask for an "application interface" and it'll drop unnecessary padding and make things neat and compact
3
1
5
441
Pixel art by Opus 5.5 "Passing Light"
2
1
12
605
Made with @kitao's Pyxel, which is actually a retro game engine. In 1200 lines of python. gist.github.com/dkenw/b0f4aa…
1
2
172
fyi, opus 5.5 medium ranked higher than max/xhigh in the previous version of FrontierCode (1.1), but it was more of a grading issue that 2.0 has solved.
such a big gap between opus 5.5 xhigh and high
151
such a big gap between opus 5.5 xhigh and high
Introducing FrontierCode 2.0: our new coding benchmark that measures a model’s ability to go beyond the spec. Most coding evals measure a model’s ability to write code that meets a spec. With FrontierCode 1.0, we asked a new question: would you actually merge the PR? FrontierCode 2.0 is comprised of more diverse tasks, featuring larger scopes and higher mergeability standards. We are now asking: not only would you merge this PR, but should you? One key feature of FrontierCode 2.0 is underspecified prompts. Rather than including every engineering decision, prompts are deliberately ambiguous, giving the models room to demonstrate their judgment. The result is a benchmark that is far from saturated, with the top model scoring just 45%.
43
25
9
1,269
263,441
the graph shows claude models are way more sensitive and reliant to thinking effort than GPT models. (green: gpt models; orange: claude models)
3
1
32
14,162
Opus just has a better game designer sense. It knows all the low-hanging fruits, like swing smear, sigil, shockwave rings
Pushing GPT 6 Astra for the best sorcerer attack animation in pixel art This one is its ~40th iteration
1
138
hey @X please fix your GIF color rendering when u upload a GIF (sRGB), X converts it to MP4 using Rec.601, but doesn't store these color metadata in the file. then, when viewing it on chrome or X app, they fall back to Rec.709 (a different color formula), causing a shift in hue.
95
Pushing GPT 6 Astra for the best sorcerer attack animation in pixel art This one is its ~40th iteration
opus 5.5, animated pixel art wizard, pure code prompt shared below 👇
2
1
6
510
lol it's funny to ask chatgpt pro to write a full research paper in latex for just a small question/problem set
1
129
Astra (surprisingly) performs consistently better than Opus 5.5 at drawing **low-res pixel art visual effect**. Opus 5.5 gets the idea quick and is often more creative, but couldn’t draw well without supervision. Astra is lazy, always draws badly in the 1st pass, but if u keep pushing it to iterate, it’ll often arrive at something much nicer
1
5
378
I guess i should post some examples later
1
92
Turns out the 32MB rom size limit is the biggest hurdle.
Porting a Pyxel game to Butano (GBA ROM), ffs how could GBA devs build games in such crazy constraint of CPU and RAM??? My 6.1 sol has been porting the game for 16hrs and still hasn’t finished optimizing the game enough to run in the emulator.
1
3
1,106
Porting a Pyxel game to Butano (GBA ROM), ffs how could GBA devs build games in such crazy constraint of CPU and RAM??? My 6.1 sol has been porting the game for 16hrs and still hasn’t finished optimizing the game enough to run in the emulator.
1
1
1
5
1,390
for context, it’s 384 kb RAM and 16.78 MHz clock speed
96
GPT 6.1 Sol isn't as good at pixel art as I would've hoped :/
107
when i see the model starts writing code like this, I know it must be cooking something big
2
133
2 Valve games 2 ARPGs 2 MMOs 1 open-world 1 niche iOS game football manager
1
163
reality:
the new development timeline
1
6
587
i'm just a caveman when my claude and codex weekly quotas all ran out just now
105