Shivay Lamba

@HowDevelop

AI Architect & Builder - Inference, LLMs, SLMs GSoC Org Admin - Jenkins | Docker Captain | CNCF Ambassador

New Delhi

shivaylamba.me

Replies Reposts Media Articles

Pinned
Shivay Lamba
@HowDevelop
Apr 8
What an amazing day! Presented a poster at @PyTorch Conference: how we optimised the RLM paper with pre-fix caching & batched Sub calls with @vllm_project And a full house for our Pytorch Conference talk on running LLMs using Executorch on Android!
4
Shivay Lamba
@HowDevelop
3h
What a wonderful start to @agentsnexus by @yashrajnayak and @sidagarwal04 Great discussions on multi agent architectures in production, security, monitoring and ofcourse on device AI agents @Qualcomm_Dev
1
Shivay Lamba
@HowDevelop
14h
I built an interactive 3D portfolio with GPT‑6 Astra: it turned my photo into a @Blender character, placed it inside an editorial WebGL experience, and created a revolving “Speaking Orbit” containing Earth globe mapping my talks around the world. The most impressive thing to
00:00
dominik kundel
@dkundel
18h
GPT-6 Astra is now available to all Pro, Enterprise, and Business Premium users alongside the API. I’ve been using it to build apps, LEGO models, and 3D scenes. Here are five things that changed how I use Codex 👇
Article
Five things I learned from using Astra
Back in February, getting Codex to build LEGO models took a custom skill, complicated instructions, and hours of iteration. And it was still not great. I came away thinking it wasn’t something models...
4
Shivay Lamba
@HowDevelop
18h
Time to cook with @OpenAIDevs GPT 6 Astra 👨‍🍳
1
Shivay Lamba
@HowDevelop
Sep 3
One problem I keep running into when building AI systems: which model should I actually use for each task? Benchmarks rarely give a complete answer. @withmartian AI Frontier looks at what matters in practice: - quality - reliability - real cost - performance across tasks The
Martian
@withmartian
Sep 3
00:30
We got 46% fewer errors than the single best LLM across the 16 most used benchmarks (TerminalBench, LiveCodeBench, etc). Here's how that's possible and what each model can achieve when used optimally (every benchmarks misses the majority of model capabilities) 👇 Interactive
6