sid pfp

sid

@siddani

68 Following
129 Followers


sid pfp
sid
@siddani
Day 1 of building an AI SaaS app to clone yourself! 🖼️ Goal: Upload images, train AI model, generate images in scenarios. Tech: Next.js, Clerk, Supabase, Replicate, Vercel. Approach: Used Grok for docs (PRD, App Flow, Backend/Frontend Guidelines) + Claude for project scrutiny. - Created 5 docs for MVP structure. - Grok gave up-to-date tech insights (e.g., Supabase updates). - Claude caught doc inconsistencies (e.g., backend vs. frontend fields). - Frontend looks rough—buttons barely work. Mild success, learned a lot. Day 2: Fix UI! 🛠️
0 reply
0 recast
6 reactions

sid pfp
sid
@siddani
While establishing a U.S. Crypto Strategic Reserve might legitimize crypto assets, doesn’t government ownership fundamentally undermine the decentralized ethos that drew us to crypto in the first place? Curious to hear how the community sees this potential paradox.
26 replies
32 recasts
92 reactions

sid pfp
sid
@siddani
where do i find what people are talking about topics like the new crypto reserve on farcaster?
1 reply
0 recast
2 reactions

sid pfp
sid
@siddani
i have access to GPT 4.5, send me prompts you’d like me to try
0 reply
0 recast
6 reactions

sid pfp
sid
@siddani
Well I’ll be damned. I didn’t think it would actually happen, but as of today, Grok 3 is the best AI model out there. We have a new player in town. xAI just dropped Grok 3, their latest large language model, packed with a reasoning engine and a mini model. And it’s delivering some serious results: • LMArena: 1400 ELO (#1 ranking) • AIME 24: 52% (96% with reasoning!) • GPQA: 75% (85% with reasoning) • LiveCodeBench (Coding): 57% (80% with reasoning) • AIME 2025 (Math): 93%, outperforming o3-mini-high The AI game just got interesting.
18 replies
28 recasts
99 reactions