Shivay Lamba

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

[Shivay Lamba @HowDevelop]

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!

[Base Labs @baselabs]

Today we release mammoth-1 and elephant-1!

We post-trained mammoth-1, the #1 ranked best decision model in the world, and elephant-1, which is the best model under 15B (and beats Jev).

We're open-sourcing all model weights and provide a technical report detailing all our training and data methods.

[Shivay Lamba @HowDevelop]

@reflection_ai @huggingface I built Kubetrace - using Beam with @nebiustf
https://t.co/cGzKIpKNzI

[Shivay Lamba @HowDevelop]

An AI coding agent becomes useful when it can investigate a problem, change the code, test the fix, and follow through to a working deployment.

That’s what I wanted to explore with the newly launched @reflection_ai Beam 🚀

Beam is built for coding, reasoning and agentic workloads. KubeTrace AI puts those capabilities to work on @kubernetesio incidents, with inference through @nebiustf.

The agent can:

→ Investigate logs, events and application code
→ Trace a failure to its cause
→ Propose code or Kubernetes manifest changes
→ Run regression tests in a sandbox
→ Build and deploy the repaired application
→ Check whether it recovered

The execution layer checks every proposed change against policy, and hidden checks decide whether the incident is resolved. You can inspect the evidence, patches, test output and failed attempts.

[Reflection @reflection_ai]

We teamed up with @huggingface to give away $20,000 to anyone who's building with Beam 🤗

Use Beam for any project - make a demo or a dataset, benchmark the model, create an RL environment - and comment your link in the model's repo page by Monday, November 2.

We choose the winners. Winners choose cash or credits. Claim $25 in Hugging Face credits to build with Beam and enter the competition 👇

https://t.co/XCxKkWB9Bp

[Shivay Lamba @HowDevelop]

Inspired by @BhosalePratim's Macbrow, I built Winbrow: a Windows voice assistant.

@GradiumAI speech + @typesafeai Jev routing + browser automation adapted from @browser_use’s Jev Ultrafast project.

@Alibaba_Qwen 4B LLM handles replies. Phonon (TTS) speaks them both running locally on @Qualcomm_Dev X Elite’s NPU.

Built for Phonon’s OSS launch!

[Shivay Lamba @HowDevelop]

@superplanehq congrats@!

[Shivay Lamba @HowDevelop]

@tonykipkemboi @nebiusai congrats!!!

[Shivay Lamba @HowDevelop]

@dabit3 such an underrated feature on how to use Devin

[Reflection @reflection_ai]

Model customization recipes are live on our website and in the cookbook repo.

Beam is now supported across RL and SFT stacks including @axolotl_ai, NeMo RL, NeMo AutoModel, Megatron Bridge (@NVIDIAAI), Miles (@radixark), SkyRL (@NovaSkyAI), and TRL (@huggingface).

Get cooking 🧑‍🍳
https://t.co/gRHcqEsa0s

[Shivay Lamba @HowDevelop]

@vclusterlabs @deutschetelekom @nvidia this is great!

[Shivay Lamba @HowDevelop]

@vedantj_03 very exciting to check it out

[Arindam Majumder 𝕏 @Arindam_1729]

https://t.co/Td98XYIxDh

[Shivay Lamba @HowDevelop]

@TheIshanGoswami you deserve it!

[Shivay Lamba @HowDevelop]

@carrycooldude So cool

[Shivay Lamba @HowDevelop]

@LoveneeshDhir @agenttrailhq @samc621 This is a great use case

[Shivay Lamba @HowDevelop]

@BhosalePratim @GradiumAI @typesafeai @browser_use @Alibaba_Qwen @ashwinexe How it works:
🎙️ Microphone → Gradium STT
🧭 Jev → chooses the action
🖥️ Windows controls / browser agent → executes
🧠 Local Qwen → answers questions
🔊 Local Phonon → speaks replies

STT and routing use cloud APIs. Qwen and Phonon inference run on-device.

[Shivay Lamba @HowDevelop]

Inspired by @BhosalePratim's Macbrow, I built Winbrow: a Windows voice assistant.

@GradiumAI speech + @typesafeai Jev routing + browser automation adapted from @browser_use’s Jev Ultrafast project.

@Alibaba_Qwen 4B LLM handles replies. Phonon (TTS) speaks them both running locally on @Qualcomm_Dev X Elite’s NPU.

Built for Phonon’s OSS launch!

[Pratim Bhosale @BhosalePratim]

I've always wanted a way to talk to my Mac and do things on the go.

Until now, it was super slow.

So I built Macbrow.

Voice-controlled browser and computer-use agent.

Built using @GradiumAI @browser_use and @typesafeai
Still early and a work in progress.

https://t.co/af8abnSfuV

[Shivay Lamba @HowDevelop]

@abhinavd26 @SantoshYadavDev @JuanPa heyyy, i live in Delhi 😁

[Shivay Lamba @HowDevelop]

I got to build with @GradiumAI Phonon on launch day!

A smart mirror that sees your outfit and gives spoken style recommendations - all running locally on @arduino Ventuno Q.

@Alibaba_Qwen VLM to understand what you’re wearing
Phonon TTS to talk through suggestions

Both accelerated by the @Qualcomm_Dev Hexagon NPU

[Shivay Lamba @HowDevelop]

@apirela_dev @GradiumAI @arduino @Alibaba_Qwen @ashwinexe @BhosalePratim definitely will keep you posted on that

[Shivay Lamba @HowDevelop]

I got to build with @GradiumAI Phonon on launch day!

A smart mirror that sees your outfit and gives spoken style recommendations - all running locally on @arduino Ventuno Q.

@Alibaba_Qwen VLM to understand what you’re wearing
Phonon TTS to talk through suggestions

Both accelerated by the @Qualcomm_Dev Hexagon NPU

[Gradium @GradiumAI]

A new frontier for on-device speech.

We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date.

Phonon-31m is available under Apache 2.0.

https://t.co/d3qa9qmnzY🧵

[Shivay Lamba @HowDevelop]

@carrycooldude 404