Chaithanya Kumar (@chaithanyak42) 's Twitter Profile
Chaithanya Kumar

@chaithanyak42

an engineer who loves taking long aimless walks - I share my learnings and thoughts around AI.

ID: 1724769335842099200

linkhttp://chaithanyak.com calendar_today15-11-2023 12:40:52

1,1K Tweet

1,1K Followers

358 Following

shyamal (@shyamalanadkat) 's Twitter Profile Photo

greatest gift you can give yourself is irrational optimism about the long term paired with brutal honesty about the short term

Taranjeet (@taranjeetio) 's Twitter Profile Photo

It is interesting that the headline here is not just what the model can do, but how many tokens it takes to do it. For a while, model capability mostly meant: can the model handle the task at all? Progress looked like bigger models, bigger context windows, more tokens, and more

Ganesh Subramanian (@ganeshsub) 's Twitter Profile Photo

One of my friends is Looking for a ceo for an agentic ai start up. If you are someone who can lead a team and grow globally - tech + growth mindset , DM me …

Chaithanya Kumar (@chaithanyak42) 's Twitter Profile Photo

“For all our failings, despite our limitations and fallibilities, we humans are capable of greatness.” - Carl Sagan Early morning runs are a bliss

“For all our failings, despite our limitations and fallibilities, we humans are capable of greatness.” - Carl Sagan

Early morning runs are a bliss
Saket Aryan (@whysosaket) 's Twitter Profile Photo

spent the weekend on a browser harness for claude code that uses your real browser. honestly surprised it works this well.

mem0 (@mem0ai) 's Twitter Profile Photo

Mem0 is partnering with Basis Set on the 2026 AI Fellowship, Agentic Memory Track. If you’re an early-career builder excited about AI agents, memory, retrieval, and context engineering, this is for you. As agents move from demos to real products, memory becomes core

Mem0 is partnering with <a href="/BasisSet/">Basis Set</a> on the 2026 AI Fellowship, Agentic Memory Track.

If you’re an early-career builder excited about AI agents, memory, retrieval, and context engineering, this is for you.

As agents move from demos to real products, memory becomes core
Mayank Gupta🧑🏻‍💻 (@waghnakh_21) 's Twitter Profile Photo

future of coding is neither traditional ide interfaces nor the agentic coding cli.. it's going to be best of both worlds and Li Yin is trying to build one

Adithya S K (@adithya_s_k) 's Twitter Profile Photo

Excited to release the Ultimate guide to RL environments! Definitions of RL environments differ wildly in the LLM era, so we spent the last month building several RL environments across 6 different frameworks, domains and complexities to map out which are easiest to build with

National Geographic (@natgeo) 's Twitter Profile Photo

Wishing a Happy Birthday to Sir David Attenborough. Thank you for the knowledge, passion, and hope you’ve passed on to all of us. Celebrate 100 years of Sir David Attenborough with Ocean with David Attenborough on Disney+ and Hulu

Chaithanya Kumar (@chaithanyak42) 's Twitter Profile Photo

Most agent memory systems optimize for storage. But production agents need relevance over time. Memory Decay is our first step toward making memory more time-aware. This matters a lot for long-running agents. The longer memory grows, the more old context competes with current

Ellen (@liviaellen13) 's Twitter Profile Photo

We wrote more about why agent memory gets noisy over time, and how mem0 Memory Decay keeps recent context easier to surface without deleting the past. Read more 👇