Shubhang Kandiraju

[Shubhang Kandiraju @KShubhang]

@tanaypadhi Flaude code

[Shubhang Kandiraju @KShubhang]

Exa code has honestly been very useful for me!

[Exa @ExaAILabs]

Introducing exa-code, a big step towards eliminating LLM code hallucination.

We indexed 1B+ docs pages, Github repos, StackOverflow posts, and more. Given a query, exa-code initiates a hybrid search over this data, chunks it, and returns a concatenated, token-efficient string. In our code hallucination eval, exa-code outperforms every popular web search tool (including Exa!).

Available for free: https://t.co/BQ3Y6gcq8W

How we built it: https://t.co/NnTm5Enrc3

[Shubhang Kandiraju @KShubhang]

he is a ferrari fan

[Film Updates @FilmUpdates]

Cillian Murphy photographed by Antonio Olmos for The Observer

[Shubhang Kandiraju @KShubhang]

Drove a tractor and still recorded the fastest lap in history - max is truly the 🐐

[Holiness @F1BigData]

The fastest lap in the history of our sport

[Exa @ExaAILabs]

We raised $85M in Series B funding at a $700M valuation, led by Benchmark.

Exa is a research lab building the search engine for AI.

[Shubhang Kandiraju @KShubhang]

@athyuttamre You are so artsy atty! How do you do it?

[Shubhang Kandiraju @KShubhang]

Lfg!!! 18 years of pain but totally worth it

[Royal Challengers Bengaluru @RCBTweets]

Patience wasn’t passive. 🥹
It was powerful. ✊
It was red. ❤️
It was royal. 👑

[Shubhang Kandiraju @KShubhang]

As an RCB fan nothing better than watching Kohli play like this

[Royal Challengers Bengaluru @RCBTweets]

Louvre, keep a place ready for a portrait. 😮‍💨🤌

[Shubhang Kandiraju @KShubhang]

@corytomlinson @AravSrinivas for 2 and 3 which models are you using?

[Shubhang Kandiraju @KShubhang]

@patrickdevivo @AravSrinivas what is your desired rate limit?

[Shubhang Kandiraju @KShubhang]

@testingcatalog Total context window is actually 128k - we have fixed it on our documentation now.

[Shubhang Kandiraju @KShubhang]

A powerful tool for developers to supercharge their product experiences. We are excited to see what people build with this!

[Perplexity @perplexity_ai]

Deep Research, our latest and most advanced research tool, is now available through our Sonar API.

We're excited to see the variety of custom research agents and workflows that developers will create using Sonar.

[Perplexity @perplexity_ai]

Perplexity's Sonar—built on Llama 3.3 70b—outperforms GPT-4o-mini and Claude 3.5 Haiku while matching or surpassing top models like GPT-4o and Claude 3.5 Sonnet in user satisfaction.

At 1200 tokens/second, Sonar is optimized for answer quality and speed.

[Shubhang Kandiraju @KShubhang]

@athyuttamre @pypi @npmjs 100%

[Perplexity @perplexity_ai]

Introducing Sonar Reasoning, our new API offering powered by DeepSeek's reasoning models.

Build products with chain-of-thought reasoning, plus real-time internet search and citations.

Sonar Reasoning is uncensored and hosted in US datacenters. As with Sonar and Sonar-Pro, Perplexity protects your privacy by never collecting or sharing API data.

[Shubhang Kandiraju @KShubhang]

@athyuttamre Amazing!

[Perplexity Supply @PPLXsupply]

new sonar gear available now on perplexity(dot)supply

[Shubhang Kandiraju @KShubhang]

@SullyOmarr @AravSrinivas @SullyOmarr DMed you about this. Will get this figured out

[Shubhang Kandiraju @KShubhang]

Excited to launch this today! Please DM me with any feedback or feature requests.

[Aravind Srinivas @AravSrinivas]

The excitement around trying to make agents and vertical answer engines (legal, health, travel, academic, patents, etc) happen is pretty clear. We want to support it through Perplexity's search-grounded LLM API: Sonar.