Gatien (@gatien7) 's Twitter Profile
Gatien

@gatien7

Co-Founder @ Doana IA

ID: 1878902328075366400

linkhttp://doanaia.com calendar_today13-01-2025 20:30:17

286 Tweet

20 Followers

277 Following

Gatien (@gatien7) 's Twitter Profile Photo

Quick recap : - Montreal is the place to be - Vibecoding is real and it works - Designer can now push to prod - Claude Code is not only for code - MCP is pronounced MPC at Shopify /s - you can’t one shot prompt your way to Shopify

Gatien (@gatien7) 's Twitter Profile Photo

shout out to Mark Savic , great talk yesterday at botpress, supercharging vibecoding with pragmatism and thoughtful approach. This is the way ! I definitely need spend more time on BMAD

Maze (@mazeincoding) 's Twitter Profile Photo

guys what gpt-5 model should i use in cursor gpt-5.1 codex gpt-5.1 codex mini gpt 5.1 codex high gpt 5.1 codex fast gpt 5.1 codex high fast gpt 5.1 codex low gpt 5.1 codex low fast gpt 5.1 fast gpt 5.1 high gpt 5.1 high fast gpt 5.1 low gpt 5.1 low fast gpt 5 codex high gpt 5

Rajjan Dube (@rajjandubbe) 's Twitter Profile Photo

8 years of design taught me: your portfolio gets you interviews. your personality gets you hired. your problem-solving keeps you employed. your communication gets you promoted. invest in all four, not just the first one.

Theo - t3.gg (@theo) 's Twitter Profile Photo

It's kind of sad to see the slow death of Mistral. Their new model is: 1. Dumber than Deepseek 2. 3x more expensive than Deepseek 3. Slower than GPT-5

Gatien (@gatien7) 's Twitter Profile Photo

Claude code meetup in MTL is not happening, I tried 😅 In the meantime our next supabase community meetup is approaching 160 people. Can’t wait 🔥🔥

Dan Mac (@daniel_mac8) 's Twitter Profile Photo

Opus 4.5 used with Claude Code as opposed to a more generic agent scaffold doubles performance on CORE-Bench. CORE-Bench tests AI's ability to reproduce scientific papers when provided with raw data. Opus 4.5 + Claude Code is the closest thing to AGI that exists today.

Opus 4.5 used with Claude Code as opposed to a more generic agent scaffold doubles performance on CORE-Bench.

CORE-Bench tests AI's ability to reproduce scientific papers when provided with raw data.

Opus 4.5 + Claude Code is the closest thing to AGI that exists today.