TankDarshan7 Profile Banner
Darshan Tank Profile
Darshan Tank

@TankDarshan7

Followers
45
Following
876
Media
44
Statuses
517

AI + Data guy @SentientAGI

India
Joined June 2019
Don't wanna be here? Send us removal request.
@TankDarshan7
Darshan Tank
18 hours
BREAKING 🚨: AI generated photo of Elon Musk is making headlines
@alpaysh
Alps
1 day
BREAKING🚨: Elon Musk and Sydney Sweeney are reportedly dating
0
0
0
@TankDarshan7
Darshan Tank
2 days
I'm thinking of learning RL…
0
0
0
@TankDarshan7
Darshan Tank
4 days
Vibe coding isn't as easy as it sounds.
0
0
0
@TankDarshan7
Darshan Tank
8 days
Personalised Memory will restrict you to explore new things!
0
0
0
@TankDarshan7
Darshan Tank
11 days
You get stuck when your AI does guesswork for sample input and expected output, and that's where vibe coding sucks. If you give clear instructions with a proper input-output structure, it does well.
0
0
0
@TankDarshan7
Darshan Tank
14 days
My inner instinct keeps telling me to build and ship my first SaaS by the end of 2026.
1
0
1
@TankDarshan7
Darshan Tank
16 days
I just tried Manus AI to see why it's valued so highly, and I'm convinced!!! Meta got the cheap deal.
0
0
0
@TankDarshan7
Darshan Tank
25 days
DeepResearch and DeepSearch are big problems that I think will be solved in 2026. It's interesting to see some evolving ideas around them!!!
0
0
0
@TankDarshan7
Darshan Tank
27 days
I just published How Far Are We from Genuinely Useful Deep Research Agents?
0
0
0
@TankDarshan7
Darshan Tank
1 month
Yoohoo, check out our work!
@SentientAGI
Sentient
1 month
Announcing SERA-Crypto (Semantic Embedding & Reasoning Agent): our new reasoning architecture built for SOTA crypto research. #1 open-source agent on DMind #1 on our live crypto benchmark Outperforms GPT-5, Grok 4, Gemini 2.5 Pro, and Perplexity Finance…all under 45 seconds.
0
0
0
@TankDarshan7
Darshan Tank
1 month
Are we really trusting stats? Humans always have their own biases—that's just how it works!
0
0
0
@TankDarshan7
Darshan Tank
1 month
Surprising part for me: majority of production agents rely on prompt optimisation, which i was under estimating, with their own architecture rather than existing frameworks!! Good paper:
0
0
0
@TankDarshan7
Darshan Tank
1 month
It will be interesting: your code runs in some environment, you give instructions from your phone in voice mode on what to do and how, and the agent handles the rest!
0
0
0
@TankDarshan7
Darshan Tank
1 month
Continuous learning from past memory in agents is a big thing!
0
0
0
@TankDarshan7
Darshan Tank
2 months
Give it time!
0
0
0
@TankDarshan7
Darshan Tank
2 months
This is banger🔥
@deepseek_ai
DeepSeek
2 months
🚀 Launching DeepSeek-V3.2 & DeepSeek-V3.2-Speciale — Reasoning-first models built for agents! 🔹 DeepSeek-V3.2: Official successor to V3.2-Exp. Now live on App, Web & API. 🔹 DeepSeek-V3.2-Speciale: Pushing the boundaries of reasoning capabilities. API-only for now. 📄 Tech
0
0
0
@TankDarshan7
Darshan Tank
2 months
We say LLMs are biased as evaluators! After all, they are trained by humans!!
0
0
0
@TankDarshan7
Darshan Tank
2 months
Even setting improper max_token limit affect the eval results 👀
0
0
0
@TankDarshan7
Darshan Tank
2 months
Research papers, and even projects, from Stanford are something different!
0
0
0
@TankDarshan7
Darshan Tank
2 months
We are literally scratching the surface only!
0
0
0