Deepesh Bansal

AI@ | BITS Pilani | tinkering in GenAI

[Deepesh Bansal @deepeshbansal_]

Built Forklift: a local CLI/TUI inspired by @cohere @vllm_project fork-maintenance agent workflow, with Codex as the review + repair engine.
Get started in three commands: uv tool install forklift-ai, forklift init, then forklift run.

Repo - https://t.co/5mxFOVuSIr
Check out the demo below -

[Deepesh Bansal @deepeshbansal_]

@ViditOstwal Congratulations 🥳

[Deepesh Bansal @deepeshbansal_]

Can LLMs be good conversational assistants if they can’t write good?

[Yashi @yashi__X]

Whenever I think am doing something ground breaking...it just turns out to be conversational AI

[DeepSeek @deepseek_ai]

⚠️ Note

🔷 DeepSeek-V4-Flash-0731 keeps the exact same model architecture and size as the preview version.
🔷 Today's upgrade applies ONLY to the DeepSeek-V4-Flash API. The DeepSeek-V4-Pro API and App/Web models remain unchanged for now.

The official release of DeepSeek-V4-Pro is coming ASAP! Stay tuned.

[Deepesh Bansal @deepeshbansal_]

Finally

[DeepSeek @deepseek_ai]

🚀 DeepSeek-V4-Flash Official API is now LIVE in public beta!

🔷 We’ve massively upgraded its Agent capabilities—benchmark scores are now far surpassing the V4-Pro-Preview. Check out the massive performance leap below! 👇
🔷 The official V4-Flash now natively supports the Responses API format and is fully adapted for Codex!

Check out the configuration details in our official API docs: https://t.co/smCwQZMeiq

[Marion Lepert @marionlepert]

Catching skin cancer early is a home robotics problem.

Melanoma is highly treatable when detected early, yet today’s screening process depends heavily on patients noticing tiny changes across their entire skin surface. This requires patients to solve a near-impossible visual-memory and registration problem.

I built OpenDerm, an open-source 4-DOF robot that captures high-resolution images of the skin and uses them to reconstruct and track the skin surface in 3D over time.

The best way to make skin screening truly routine is to bring it into the home. OpenDerm shows that inexpensive robotic skin imaging is possible, but the path to scale is not a dedicated screening robot in every household—it is to make skin screening one of the many useful things a general-purpose home robot can do.

Read more about why I built OpenDerm and how it works here:
Blog: https://t.co/KYlNIkF3TV
Project: https://t.co/c9d4KuwXUP

[Deepesh Bansal @deepeshbansal_]

@dhruvdoshi_ XD

[Deepesh Bansal @deepeshbansal_]

if you see this and still think you are on the right side, fuck you.

[Cockroach Janta Party - CJP @Cockroachisback]

Shame on you @NagpurPolice
Is this how you treat the students of the country peacefully demanding accountability?

[Deepesh Bansal @deepeshbansal_]

We have moved from reproducing academic papers to academic ChatGPT conversations

[Prime Intellect @PrimeIntellect]

Scaling agentic RL environments: today we're publishing 365,000+ tasks for SWE, terminal, and search agents - 23 tasksets behind one API, one sandbox lifecycle, one command.

[Jared Zoneraich @imjaredz]

Proud to say that Devin has cracked three more unsolved problems today

1) REFUTED: Graffiti Conjecture 154 (open for ~40 years)
2) PROVED: Graffiti Conjectures 39 & 40 (~40 years)
3) REFUTED: Brandt's Regular Supergraph Problem from West's open problems list (~20 years)

My methodology is explained below, but basically I showed Devin the original tweet and told it to find similar problems and crack them.

The flood gates are open.

[Deepesh Bansal @deepeshbansal_]

@MainzOnX informative! Waiting for the next in the series. Would also love it if you have any other good resources to refer to as well!

[Deepesh Bansal @deepeshbansal_]

@dhruvdoshi_ Implementation consultants

[Tencent Hy @TencentHunyuan]

Introducing Hyra-1.0, the first version of Hunyuan Research Agent. 💡💡💡

Built to recursively improve solutions for performance-driven research and engineering tasks.

Explore our demos in AI4AI, AI4Science, and AI4Fun:
https://t.co/GClJMuT8XN

[Deepesh Bansal @deepeshbansal_]

@yashi__X Thanks for explaining it clearly!! Will definitely use it in my future workflows

[Yashi @yashi__X]

@deepeshbansal_ Dynamic loading is loading only allowed/required tools in the prompt whereas with tool masking you can have all the tools in the promo but append to the prompt some hints or allowed prefixes to only use specific set from all the listed tools.

[Deepesh Bansal @deepeshbansal_]

@MainzOnX looks very very appetising 🫠

[Deepesh Bansal @deepeshbansal_]

Get ready to learn Chinese buddy

[Qwen @Alibaba_Qwen]

Qwen3.8 is launching and going open-weight soon!🌐

With a massive 2.4T parameters, this model is continuously evolving. We believe it’s one of the most powerful model available today, compatible to leading frontier AI models , second only to Fable 5.

You don't have to wait to test it. Just now, the Qwen3.8-Max-Preview made its debut on Alibaba’s Token Plan, Qoder, and QoderWork. Be among the very first to try it out.

Can't wait to hear what you build. Stay tuned! 🚀 

Token Plan
international：https://t.co/YRvcGdB9Bv
China：https://t.co/PKMUNwUuRp

[vik @vikhyatk]

joining the fight against datacenters. on the datacenters’ side