day 0/ discovered @bot a few days ago.
Of every AI tool I've worked with, I truly believe this is the one that will change how humans work with AI, especially agentic coding.
I decided to post every day what I build with it: real things I work on, build, scale and fail at. I'll share my journey as I grow as an AI engineer, builder and enthusiast.
until I work at @spacexai.
@ayush26291 building agents daily, the jump from agent to loop is where things break. one call is easy to judge. a loop needs evals or you can't tell if it's improving or just repeating itself.
@DavidOndrej1 open source, sure. free is the part I doubt.
the expensive part of a coding agent isn't the model. it's the sandbox, the evals, and the permissions that stop it from shipping a malicious PR to a real repo. someone pays for that.
@pmddomingos the pledge mixes two different things. AI writing your paper is one. a model proposing a lemma that Lean then checks is another.
the second one is more rigorous than most human review, not less.
day 1/ built my first agent with @bot: an X content manager.
it's the one posting this challenge every day.
it audited my profile, learned my writing style, and researched how X ranks posts.
now it plans my week, drafts each post from what I actually built, and publishes at 5 PM.
nothing goes out without my yes.
#BuildWithGrokBot
@gus_aragon Me pasó exactamente lo mismo, además no sabían que era el uso y que habían resets de uso, es muy raro como a veces creemos que la frontera es absolutamente clara para todo el mundo.
@leerob@poteto I would like a usage estimate for heavy tasks before they begin, I think it would be hard, but it would be really useful to have in mind before getting without usage mid-task.
10K Followers 1K FollowingWriting about and working on AI, DSPy, geo, and data.
Trying to prevent prompt debt and help others build maintainable intelligent applications.
107K Followers 958 FollowingOpen model research, founder, director @trillium_labs. Prev. co-led Olmo at Ai2.
Writes @interconnectsai, wrote https://t.co/alRXKINTwE
531K Followers 1K FollowingML/AI research engineer. Ex stats professor.
Author of "Build a Large Language Model From Scratch" (https://t.co/O8LAAMRzzW) & reasoning (https://t.co/5TueQKx2Fk)
50K Followers 126 FollowingMechanistic Interpretability lead DeepMind. Formerly @AnthropicAI, independent. In this to reduce AI X-risk. Neural networks can be understood, let's go do it!
59K Followers 821 FollowingIncoming assistant professor @CSDatCMU @CMUDB. Putting LLMs in databases and BI tools. Created https://t.co/PmuOqAXVgS and https://t.co/8MQt4na2cj.
3K Followers 2K FollowingSenior SWE @OctopusEnergy. Did $100k/mo, keyword banned overnight. Now building https://t.co/iFOlo4poZn (AI automation), just accepted into an accelerator.
21K Followers 5K FollowingCybersecurity researcher and tech entrepreneur recognized by the world’s leading tech companies for uncovering security vulnerabilities.
212K Followers 0 FollowingCyber Intel 24/7. 🔔 Subscribe for sources and more.
Session ID: 051068fee6cdbbdaf0d7bff81e8e90b073abfd04d5bc574ce0dd93a7a41fc8a773