SaravanaKumar @sara4dev

Tweets

646
Followers

180
Following

1K
Likes

6K

SaravanaKumar @sara4dev

5 days ago

Of course, this was tweeted by @Muse.

0 0 0 49 0

View Details

SaravanaKumar @sara4dev

5 days ago

Hot take: nobody will want to use a browser going forward. Whoever makes their app agent-friendly wins. The US is finally getting its WeChat super-app moment — everything from one chat.

1 0 0 196 0

View Details

My AI agent has negotiated my internet bill, cancelled a dead phone line, re-shopped my home insurance, tracked my kids' soccer + basketball schedules, watched the visa bulletin, and prepped my 2025 taxes. I just… chat.

2 0 5 1K 0

View Details

SaravanaKumar @sara4dev

2 weeks ago

@geetappoo @grok translate this in English

1 0 0 4 0

View Details

Elizabeth Thomas @tweet2eliza

3 weeks ago

Curious how NVIDIA's AI Dynamo works? github.com/elizabetht/nan… nano-dynamo packs discovery, heartbeats, KV-aware routing, real vLLM inference, and front-end orchestrated prefill/decode into under 750 lines of Python, small enough to trace end to end. #NVIDIA #Dynamo #Inference

0 1 1 61 0

View Details

SaravanaKumar @sara4dev

3 weeks ago

@Sahil100X @kirat_tw @Adarsh_VMore @jitendar100x @rohanBuilds @ashutosh_sao @Deepjyoti100x @deepanshuliv @AnkurJangid02 @ashu_463 @100xDevs Great work and explanation! Keep it going!

1 0 1 534 0

View Details

Suraj Sharma @suraj_sharma14

4 weeks ago

If you want to get really good at Inference Engineering, this resource is a gold mine: github.com/elizabetht/100…

2 43 327 26K 780

View Details

SaravanaKumar @sara4dev

4 weeks ago

@Chellaney @grok is this true?

1 0 0 56 0

View Details

SaravanaKumar @sara4dev

a month ago

@svembu Use AI speed up the court process

0 0 0 8 0

View Details

SaravanaKumar @sara4dev

a month ago

@DeepakVisva 😂

0 0 0 27 0

View Details

SaravanaKumar @sara4dev

a month ago

@PremiumGoblin AI landscape seems to be very broad these days, from serving models efficiently, training models, RL training, AI infra, security, custom agents and memory. Where should one focus today? @tweet2eliza

1 0 1 4K 0

View Details

NVIDIA AI Developer @NVIDIAAIDev

7 months ago

🧵 NVIDIA Dynamo v0.9.0 is live and it's probably our biggest infrastructure upgrade yet. Highlights this time include ✅ Sneak preview of FlashIndexer ✅ Expanded multi-modal support ✅ Removed NATS & ETCD And bonus. . . @meituan (Chinese Doordash + LLM builders) recently dropped an OSS inference engine built on @sgl_project + Dynamo. 👇

2 13 83 5K 16

View Details

SaravanaKumar @sara4dev

2 years ago

@Schwarzenegger hope you & family are okay. waiting for your thoughts on LA Wild Fire.

0 0 0 86 0

View Details

SaravanaKumar @sara4dev

2 years ago

@MattressFirm I had a bad experience at @BigTex. The sales manger (Michael) was very rude, that I cannot sit and try on the bed since I had kids. While I see so many other people are sitting on it with kids. The reason he said is anyway I am NOT going to buy it. I was seriously considering purple mattress. Is this how sales works these days, that sales person judge someone before even talking to the buyer?

0 0 0 57 0

View Details

SaravanaKumar @sara4dev

2 years ago

@ProsperPD sent a non urgent question yesterday in the DM. If any officer can look at it and reply back, it will be great. Thanks!

0 0 1 23 0

View Details

OpenAI @OpenAI

3 years ago

We're rolling out new features and improvements that developers have been asking for: 1. Our new model GPT-4 Turbo supports 128K context and has fresher knowledge than GPT-4. Its input and output tokens are respectively 3× and 2× less expensive than GPT-4. It’s available now to all developers in preview. 2. Assistants API and new tools (Retrieval, Code Interpreter) will help developers build world-class AI assistants within their own apps. 3. The platform is becoming multimodal. GPT-4 Turbo with Vision, DALL·E 3, and text-to-speech are all now available to developers. Oh… and we’re doubling GPT-4 rate limits. openai.com/blog/new-model…