Design & Code @CommandCodeAI ✹ Building a Frontend ecosystem https://nitter.gq/t.co/zjrS1rOibJ
Joined January 2023
- Tweets2.9K
- Following258
- Followers1.1K
- Likes2.2K
Naymur Rahman retweeted
Introducing Cut for macOS.
Cut ⌘X and Paste ⌘V files in Mac. Finally.
Open source. MIT. No network.
Naymur Rahman retweeted
Ling 3.1 Flash 1019 is FREE in Command Code for the next 4 days.
It's the latest upgrade to Ling 3.1 Flash, an open-weight model for advanced reasoning and agentic workflows.
- 1M token context window
- 560B total params, 25B active
Available on all plans & subscriptions.
Naymur Rahman retweeted
If you’re using DeepSeek harness with Command Code’s provider API, we are shipping several updates to make your experience better and faster.
DeepSeek harness needs more than a standard chat completions endpoint. I’m excited to pass along our learnings and improvements we have made here without y’all having to do anything on your end.
LFG!!
Naymur Rahman retweeted
Earlier today we detected and stopped a security incident linked to a large-scale distillation attack targeting Anthropic and OpenAI models.
As a precaution, we've revoked all API keys. To keep using Command Code, log in to Studio again to generate a new key.
So far, we've found no evidence that any users were impacted. We're working with Cloudflare, Anthropic, and OpenAI to investigate.
We appreciate your patience and trust. 💜
Naymur Rahman retweeted
I compared Mimo-V2.6-Flash, Grok-4.7, and DeepSeek-V4.1-Flash.
Same prompt with the /design command from Command Code.
Reviewed gameplay UX/UI and cost:
- Mimo-V2.6-Flash: 9/10 · $0.005 · one-shot playable game with the cheapest price
- DSV4.1-Flash: 9/10 · $0.0089 · one-shot with good UI/UX & playable
- Grok 4.7: 8/10 · $0.20 · expensive, and I had to iterate to fix the bird
Naymur Rahman retweeted
Extremely simple to understand,
$1 plan has no API ❌
$10 plan includes API ✅
I don't know why it's really hard for someone to understand.
Stop abusing good things 😊
Naymur Rahman retweeted
makes me happy to see our users enjoying command code, faster inference on deepseek has literally cut my work hours in half.
think i'm shipping 2-3x more prs a day now. and we're growing so fast, winning hearts, minds, and support of the dev community!
50t tokens now! 🐐
Naymur Rahman retweeted
I compared DeepSeek-v4.1-Flash against Opus 5 and GPT-5.6 Sol.
Same prompt with the /design command from Command Code.
Opus 5 is extremely good at UI/UX, but DSV4.1-Flash was almost 90% cheaper than GPT-5.6 Sol and Opus 5💀
What do you think? is DSV4.1-Flash really that good?
Naymur Rahman retweeted
DSV4.1-Flash is good and fast.
Compared DSV4.1 with GLM-5.3 Flash and Gemini 3.8 Flash.
- GLM-5.3 Flash ($0.0043): was low-cost and strong on design tasks.
- Gemini 3.8 Flash ($0.205): was pricier and needed many iterations to finish it.
GLM-5.3 Flash wins this benchmark.
Naymur Rahman retweeted
I ran flappybench with Fable 5.1 vs GLM 5.3 and Kimi K3
3 models. Same prompts. All using Command Code /design feature.
Kimi K3 and GLM 5.3 beat Fable 5.1 on both design and price.
GLM 5.3 stands out, clean, smooth visuals, a strong UI, and the best bird design (better than Kimi).
OS works really well with GOATed harness.
Naymur Rahman retweeted
I ran a Flappybench test on the DSV4 Pro 0813 with Kimi K3 and Opus 5.
I used /design command from Command Code.
DSV4 Pro is 462x cheaper than Opus 5 in FlappyBench test.
Reviewed gameplay, UX/UI and cost.
→ DSV4 Pro 0813 → 8/10 · $0.0005
→ Kimi K3: 9.5/10 · $0.0740
→ Opus 5: 9/10 · $0.2539
OS models works great with goat harness🐐
Naymur Rahman retweeted
I ran a test between Grok 4.6, Opus 5 and Kimi K3
I used the /design command from Command Code.
Grok 4.6 nails the UI and beats Opus 5 on gameplay, UX & Pricing.
Reviewed gameplay, UX/UI and cost.
→ Kimi K3: 9.5/10 · $0.0740
→ Grok 4.6: 9.5/10 · $0.095
→ Opus 5: 9/10 · $0.253
Naymur Rahman retweeted
Kimi K3 leads in scroll-driven Three.js performance
What I tested
- A scroll-based Three.js site
- Compared Kimi K3 vs Claude Opus 5
- Built with Command Code /design feature (Kimi K3)
What i found
- Kimi K3 stayed more consistent as scrolling interactions kicked in
- Opus 5 looked strong initially, but issues became noticeable during scroll
Ranking (DX, features, and cost):
- Kimi K3: 10/10 · $0.24
- Opus 5: 6/10 · $0.37
Naymur Rahman retweeted
Grok 4.5 & GPT-5.6 Sol Cooked by Opus 5
I tested Opus 5 with a 2D games using /design feature from Command Code.
The result is insanely good, it gimme the most playable games with drift, sounds, coin, perfect opposite car, car crashes, smooth controlling etc.
It only cost $0.24 and it's one-shotted.
Naymur Rahman retweeted
Opus 5 beats Fable 5 & Grok 4.5.
It’s absurdly good, outclassing everyone and one-shotted with ease.
It’s got everything, leveling up, coming boss, multiple bullets for coins, speed-ups and buttery-smooth gameplay.
All are done using the /design feature from Command Code.
Naymur Rahman retweeted
We run the same test with Fable 5 vs Kimi K3 vs Grok 4.5
Same prompt for all the models, using /design feature from Command Code.
Kimi K3 is actually playable with a 3D player in a 3D environment. Fable 5 & Grok 4.5 almost feel the same, just in different environments.
Ranking (DX, features, and cost):
• Kimi K3: 9.5/10 · $0.12
• Grok 4.5: 9/10 · $0.40
• Fable 5: 9/10 · $0.60
Naymur Rahman retweeted
Fable 5 vs GPT-5.6 Sol vs Grok 4.5 vs Kimi K3
I ran the same /design prompt in Command Code across 4 model
Kimi K3 tries to use ASCII sprites to make it an actual retro game and has solid gameplay, level up, add bullets, and fight a boss at each level.
Cost breakdown:
• Kimi K3: $0.15
• Grok 4.5: $0.20
• Fable 5: $0.65
• GPT-5.6 Sol: $0.45
Ranking based on DX & features:
• Grok 4.5: 10/10
• Kimi K3: 9/10
• Fable 5: 8/10
• GPT-5.6 Sol: 8/10
Naymur Rahman retweeted
I tested Gemini 3.6 Flash with Kimi K3 and GPT-5.6 Sol
All are done using the /design feature from Command Code.
Kimi K3 and GPT-5.6 Sol played well. Gemini 3.6 Flash struggled, I needed 6–7 iterations to fix the bird’s jump/fall bug, though its UI was cute.
Ranking (DX, features, and cost):
• Kimi K3: 10/10 · $0.024
• GPT-5.6 Sol: 9/10 · $0.52
• Gemini 3.6 Flash: 6/10 · $0.15