Swapna Kumar Panda's banner

Swapna Kumar Panda

@swapnakpanda • 226,263 subscribers

| Tech Writer, Educator | Python, Java, JavaScript, SQL | DSA, Development | Free Resources, AI Tools | Other Version: @therealswapna | Building @JabardastDEV |

Shorts

Coding agents build frontends effortlessly. But what about the backend? - Authentication, Database, APIs. Well, I found one. It did everything in seconds. Fully FREE to start. Best part: It works perfectly with Claude Code, Cursor, Copilot, etc.

Coding agents build frontends effortlessly. But what about the backend? - Authentication, Database, APIs. Well, I found one. It did everything in seconds. Fully FREE to start. Best part: It works perfectly with Claude Code, Cursor, Copilot, etc.

112,318 views

Unpopular opinion: Most agent evals are theatre. You run them once before the deployment. It'll take 800ms+ as another LLM would be judging your LLM. Most annoying part - no one tells where in the chain things went wrong. I wasted a lot of time in this loop. And then I came across Future AGI bringing 5 different tools under one umbrella, best part - the platform is completely open source. They open sourced their entire platform and the eval layer is noticeably different. It is multimodal - works on everything text, image, audio, pdf. Not an LLM-as-judge adding latency but an agent with memory and tools. The biggest win are learned classifiers trained on actual production failure patterns to run evals at low cost. It also runs across the full reasoning chain, not just the final response. Check out → Try it here →

Unpopular opinion: Most agent evals are theatre. You run them once before the deployment. It'll take 800ms+ as another LLM would be judging your LLM. Most annoying part - no one tells where in the chain things went wrong. I wasted a lot of time in this loop. And then I came across Future AGI bringing 5 different tools under one umbrella, best part - the platform is completely open source. They open sourced their entire platform and the eval layer is noticeably different. It is multimodal - works on everything text, image, audio, pdf. Not an LLM-as-judge adding latency but an agent with memory and tools. The biggest win are learned classifiers trained on actual production failure patterns to run evals at low cost. It also runs across the full reasoning chain, not just the final response. Check out → Try it here →

49,557 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

After huge public demand, Dhurandhar 2 makers decided to add a scene of Yalina meeting Hamza.

After huge public demand, Dhurandhar 2 makers decided to add a scene of Yalina meeting Hamza.

Swapna Kumar Panda

411,676 views • 3 months ago

Freshers get ₹2-3LPA. Meanwhile, the CEO dances with swag with his $18.6 million package. 🕺

Freshers get ₹2-3LPA. Meanwhile, the CEO dances with swag with his $18.6 million package. 🕺

Swapna Kumar Panda

89,992 views • 3 months ago

Got early access to TRAE SOLO Mobile. Thought of an idea while on a morning walk → started on phone → finished on desktop. This is how AI agents should work in 2026.

Got early access to TRAE SOLO Mobile. Thought of an idea while on a morning walk → started on phone → finished on desktop. This is how AI agents should work in 2026.

Swapna Kumar Panda

52,850 views • 2 months ago

Can you solve this puzzle: - 3 people check into a hotel room that costs $30. They each pay $10. - Later, the manager realizes the room is only $25. - He gives $5 to the bellboy to return to the guests. - The bellboy gives each guest $1 and keeps $2 as a tip. Now, each guest has paid $9 (totaling $27), and the bellboy has $2, totaling $29. Where is the missing dollar?

Can you solve this puzzle: - 3 people check into a hotel room that costs $30. They each pay $10. - Later, the manager realizes the room is only $25. - He gives $5 to the bellboy to return to the guests. - The bellboy gives each guest $1 and keeps $2 as a tip. Now, each guest has paid $9 (totaling $27), and the bellboy has $2, totaling $29. Where is the missing dollar?

Swapna Kumar Panda

38,183 views • 2 months ago

Imagine getting a $300K FAANG offer while your interviewer thinks you're a coding genius!!! But. But it's an AI whispering every perfect line of code in your ear that's completely undetectable. Sounds amazing? Read on:

Imagine getting a $300K FAANG offer while your interviewer thinks you're a coding genius!!! But. But it's an AI whispering every perfect line of code in your ear that's completely undetectable. Sounds amazing? Read on:

Swapna Kumar Panda

21,328 views • 6 months ago

No more content to load