Creative, Developer, Inspired.

Now Grok Bot started to rate limit as well even i have 50% quota left, why is it happening and stopping me from work! @elonmusk
1
18
DeepSeek-V4.1-Flash-1017 Created Model in Blender 5.1 headless, Animated it! all at once.
1
80
DeepSeek-V4.1-Flash-1017 Just Nailed the 3D Modeling. Created outclass 3D Slugg in Pink.
1
64
AI is moving from generating snippets to coordinating whole playable systems. A developer reports that 26 Opus 5.5 agents built a multiplayer heist game overnight, with five nested worlds, bots and co-op play. The real test now: can agent teams ship games people want to keep playing? x.com/jsnnsa/status/21028620…
I had 26 Opus 5.5 agents build a game overnight. It's a heist through five nested worlds, with go-karts on a giant's kitchen table, bots hunting you, and friends stealing your loot. Most vibe-coded games are demos. This one is different.. it's multiplayer and you can play it right now.
1
65
Put @typesafeai's Jev against plain keyword rules on 12 messages. Keywords 11/12. Jev 12/12. But rules cost $0 and 0ms. What rules can't do: say "unsure". Jev gave 45% on a negated trap, so you can escalate. What Jev missed: bare "cancel" at 100%, though it's ambiguous.
1
2
66
Full results. 12 support messages, categories cancel/refund/bug/praise/other. 1 "please cancel my plan" -> cancel | rules cancel | Jev cancel (100%) 2 "i want to stop paying for this" -> cancel | rules other MISS | Jev cancel (100%) 3 "discontinue my membership" -> cancel | rules cancel | Jev cancel (100%) 4 "don't cancel my order, i changed my mind" -> other | rules other | Jev other (45%) 5 "can i get my money back" -> refund | rules refund | Jev refund (100%) 6 "i was charged twice this month" -> refund | rules refund | Jev refund (100%) 7 "this broke again, third time this week" -> bug | rules bug | Jev bug (100%) 8 "it's not working" -> bug | rules bug | Jev bug (100%) 9 "the app crashes when i upload a file" -> bug | rules bug | Jev bug (100%) 10 "you guys are genuinely amazing" -> praise | rules praise | Jev praise (100%) 11 "how do i change my email address" -> other | rules other | Jev other (100%) 12 "cancel" -> cancel | rules cancel | Jev cancel (100%) Score: rules 11/12, Jev 12/12. 12 Jev calls ran at once: 1.0s wall, ~970ms each, ~$0.0001 total. Things I'd rather not gloss over: - #2 is the only miss, and it's the interesting one. There is no cancel/stop/end keyword in that sentence at all. You cannot write rules for phrasings you didn't anticipate. - I gave the keyword rules a hand-written negation guard, and that's the only reason they got #4 right. Without it, rules fail #4 too and go 10/12. - #12 is where Jev disappointed me. One bare word, genuinely ambiguous, and it returned 100%. Calibrated is not the same as infallible. Validate it on your data, don't trust the pitch. - Rules are free, instant and deterministic. Jev is a network call. On a keyword-friendly task plain code is a genuinely strong baseline, which is the part most demos leave out. - The real edge isn't the score, it's #4: rules said "other" and had no way to express doubt. Jev said "other" at 45%, so your code can decide to escalate instead of guessing. Method: 12 messages through @typesafeai jev-latest via the official SDK, keyword baseline written by hand. Code and page are local.
1
81
GPT-6 Just nailed the Gaming industry. Made outclass gaming Demo within 15 minute using GPT-6 Astra + Blender + Godot. Let me know in comment for full tutorial :)
2
46
37,972
GPT-6 Astra Light created very nice 2D storyboarding in Blender within 5 minute from character selection to idea and finishing.
1
3
197
OMG! ChatGPT 6 Astra is killed the 3D Modeling. Made cool cartoonist style Castle in Blender within 10 Minute! check the results!
2
2
33
6,508
DigitalCloud retweeted
ChatGPT 5.6 Terra Light is Insane! It automatically Created cool fur ball animation by creating the full realistic room in Blended and then animated it and rendered. All within 5 Minutes.
2
5
2,508
Found a way to run Kimi K3 for FREE with daily credits on 😳 it's a 2.8T parameter model. 1M context. beats Fable 5 on coding benchmarks. what you get for $0:
-2.8 trillion parameters
-1M context window
-beats Fable 5 on SWE Marathon (42 vs 35) kimi-bot.com/activities/vira…
2
3
236
KIMI K3 is very expensive, most of people lying here saying it is close to AGI. It just eat your money and not make even smaller tool you expect and can be done under $1 by the deepseek flash model.
1
1
186