Sabitlenmiş Tweet
Yoni - Best BBQ Show
4.6K posts

Yoni - Best BBQ Show
@BestBarbecue
Host: Best BBQ Show | Former EP: @killtony
Austin, TX Katılım Temmuz 2017
534 Takip Edilen1.4K Takipçiler

AI gives me exactly what I want on the first try now.
Tested thousands of prompts and found the same 5 components in every single one that worked. Every time I got garbage, at least one was missing.
Role. Task. Context. Format. Tone.
That's it. Five things. Works on Claude, Gemini, Grok, ChatGPT. Any AI tool.
You tell it who to be, what to do, the background that matters, how to structure the output, and how it should sound.
Most people type "help me write an email" and wonder why the result is useless. The AI has a thousand possible interpretations and you gave it zero direction.
Put together a full playbook with ready-to-use templates, a 30-second pre-prompt checklist, and a 3-phase iteration method that turns a solid first draft into exactly what you need.
15 minute read. The results last forever.
Comment "CODE" and I'll DM it to you (must be following)

English

@francisjfoster Thanks Francis! We need this out there!
English

@Jason 100% agree. We need to see what happened after the fall of them empire.
English

@learning_yohei Explain Japanese to me:
いくら-how much
いくら-salmon roe
日本語

@BrianRoemmele @zakrogoff I wish I could give this comment an award
English

@BridgetPhetasy I don’t even know where to start!! I need a guide just for this collection
English

I am in awe of this collection. Binging it. Sending it to all my friends. The most punk rock thing to happen online in decades.
Block Club Chicago@BlockClubCHI
From early Nirvana to Phish, a Chicago fan’s secret recordings of 10,000 shows are now online. blockclubchi.co/4t6zW7R
English

@Codie_Sanchez Thank you for sharing so much info and making these great small business episodes! Grateful for you 🙏🏽
English

@mattariver3 This is just thr normal droving test in America!
English

@XFreeze Wait, how is Haiku better than the other claude models???
English

Grok 4.20 Non-Hallucination rate improved to even higher than previous highest
Just days ago, it hit a record-breaking 78% Non-Hallucination Rate - already #1 in the world, smoking Claude Opus 4.6 (max), Gemini 3.1, GPT-5.4 (xhigh), and every other major model
Now, it just pushed that number even higher to 83%
While every other AI confidently makes up stuff and fabricate answers it doesn't know - Grok simply says "I don't know"

X Freeze@XFreeze
Most AI models hallucinate more than you'd think and make up stuff that doesn't exist Grok 4.20 just ranked #1 in Non-Hallucination Rate with a 78% score - beating Claude Opus 4.6(max), Gemini 3.1, GPT-5.4(xhigh), and every other model on the list xAI is quietly winning the accuracy game… and it’s built to be truthful
English

@kotosan_dayo Macintosh Classic: Motorola 68000 processor running at 8 MHz
Dansk

@tanpukunokami In Texas we do salt, pepper and smoke!
English
























