
Chad Thiele
@ChibiChaddeus
Followers
1K
Following
2K
Media
455
Statuses
5K
USAF Veteran 🇺🇸 | Founder of Chibi AI & Koubou | CISSP certified | Prompt engineering expert | The guy AI was trained on, iykyk. 💥🤖
Joined October 2022
🚨 Forget boring AI prompts. These perspective-shifting frameworks force AI into uncomfortable positions that reveal things you'd never find otherwise. Taken from my new post, link at the end:.
2
0
6
RT @OpenRouterAI: New stealth model: Horizon Beta 🌄. An improved version of Horizon Alpha.
0
90
0
Okay, this has some serious potential. Cerebras is SO FAST. If Qwen3 can do anywhere near as well as Claude 4 (the benchmarks claim it can), then this would be worth it. I'll test it in about a month after it's had some time to iterate and improve (plus I have things to get.
Cerebras Code: 20x faster than Claude, 1x the price. Today we are launching two monthly coding plans:. ➡️Cerebras Code Pro: $50/m – for indie developers.➡️Cerebras Code Max: $200/m – for power users with 5x rate limits. Both plans get: Qwen3-Coder at 2,000 tokens/s, 131K context,
0
0
0
This is accurate. For the most part… the average user probably will barely notice an improvement in GPT-5. Might be a bit easier to get quality results even with less-effort prompts. But if it is more reliable at tool calling, faster, and perhaps low-cost per token then it.
We likely won't see jaw-dropping improvements in intelligence in future models. How could we? They are already crushing most benchmarks. I suspect they'll keep getting better in more subtle ways like tool calling, adherence to instructions, creativity, etc. They'll get.
0
0
2
What's the video to watch to become excited to try @laravelphp?. I haven't used PHP for nearly 15 years and never Laravel. But I'm curious.
0
0
0
Is anyone working on an AI robot that removes seeds from watermelon? . Will Optimus do this @elonmusk ? đź«¶
1
0
3