31. there's a lot of cool apps you can build on @X , and easy to get started with this grok bot! get so... there's a lot of cool apps you can build on @X , and easy to get started with this grok bot! get some inspiration at developer.x.com/exhibit Paul Vann @pjvann want to build on 09/26 02:28 ♡
32. H here's a prompt to improve your agent harness based on what we've learned at cursor. enjoy # Improv... here's a prompt to improve your agent harness based on what we've learned at cursor. enjoy # Improve this agent harness's token efficiency You're working on an LLM 09/24 04:12 ♡
33. agents like to read a lot to gather context before and after working, so optimizing for reading make... agents like to read a lot to gather context before and after working, so optimizing for reading makes a big difference! if you're building agents, i highly recommend reading th 09/24 01:09 ♡
34. i remember when we built the first scrappy version of this ~1.5 years ago just to handle insane volu... i remember when we built the first scrappy version of this ~1.5 years ago just to handle insane volume what we learned then is still true: crawl, walk, run. identify flywheels for 09/23 03:45 ♡
35. video editing video editing vogel @ryanvogel Grok 4.7 is here! And it's good at Video Editing???? watch here: youtube.com/watch?v=XOQXWQ… Your browser does not support the video tag. ὑ 09/22 06:01 ♡
36. stop motion starship stop motion starship DreW @devteamdrew I asked Grok 4.7 to use a previous video as reference to create a stopmotion of @SpaceXAI Starship launching off I used real videos of Starsh 09/22 06:01 ♡
37. some grok 4.7 use cases in the wild! flight sim some grok 4.7 use cases in the wild! flight sim aditya @adxtyahq GROK 4.7 IS ACTUALLY COMPETING WITH GPT-6 ASTRA. I gave GPT-6 Astra, Grok 4.7, Kimi K3 and Fable 5.1 the same promp 09/22 06:01 ♡
38. and here’s the grok 4.7 model card. a few jumps vs 4.6 that stood out: - Terminal-Bench: 20.3% → 38... and here’s the grok 4.7 model card. a few jumps vs 4.6 that stood out: - Terminal-Bench: 20.3% → 38.0% - SWE-Marathon: 31.9% → 46.0% - HealthBench Pro: 48.5% → 56.7% - Legal Agent: 09/22 01:49 ♡
39. grok 4.7 is here, and its our best model so far! try it out in cursor, grok build, api or anywhere ... grok 4.7 is here, and its our best model so far! try it out in cursor, grok build, api or anywhere you get your tokens! curious to hear what you think here's grok 4.6 vs 4.7 bu 09/22 00:20 ♡
40. H how are you using grok bot this weekend? share your best tips! how are you using grok bot this weekend? share your best tips! 💬 67 🔄 3 ❤️ 166 👀 26046 📊 92 ⚡ Powered by xgo.ing 09/21 05:48 ♡
