David 🖇️ (@dd_tch) 's Twitter Profile
David 🖇️

@dd_tch

Off The Edge of The Earth and Into Forever, Forever. Alongside with @AgentOpsAI

ID: 95100277

linkhttps://agentops.ai calendar_today07-12-2009 00:24:32

487 Tweet

416 Followers

115 Following

David 🖇️ (@dd_tch) 's Twitter Profile Photo

To be honest last think I want my code editor do is “dreaming” I don’t want pay for that. But still cute reminds of “Do Androids Dream of Electric Sheep?” By Philip K. Dick

To be honest last think I want my code editor do is “dreaming” I don’t want pay for that. But still cute reminds of “Do Androids Dream of Electric Sheep?” By Philip K. Dick
David 🖇️ (@dd_tch) 's Twitter Profile Photo

Vibe not only with code but with universe as well. Started to tackle small problem yesterday and found about EmbeddingGemma from Google today. What a nice coincidence. Who’s already tried it out? Share your experience please

David 🖇️ (@dd_tch) 's Twitter Profile Photo

This definitely best weekend reading you can get today! Free book on Agentic Design Patterns. Thanks to Antonio Gulli Fun fact: “gulli” means “heart” on 🇬🇪 lang. Well Antonio you have my heart ❤️ docs.google.com/document/d/1rs…

David 🖇️ (@dd_tch) 's Twitter Profile Photo

What makes android experience bad is google. So obnoxious, intrusive and annoying. Can we gooogle you here? And more details here, can we have your data from here, connect this, share that, some more data from here, tell us everything, one more step to complete your profile…

David 🖇️ (@dd_tch) 's Twitter Profile Photo

Enjoyed new meta connect presentation, felt very live and genuine. Fails that built more trust and gives you real picture rather any polished recorded demo of non existing projects.

Rohan Paul (@rohanpaul_ai) 's Twitter Profile Photo

This paper builds an agentic LLM that can run the whole data science workflow by itself. It is an 8B model that plans work, reads structured files, writes and runs code, checks results, and iterates. Standard “workflow agents” break here because fixed scripts do not adapt well

This paper builds an agentic LLM that can run the whole data science workflow by itself.

It is an 8B model that plans work, reads structured files, writes and runs code, checks results, and iterates. 

Standard “workflow agents” break here because fixed scripts do not adapt well