sde | prev ziti (build3) | https://xitter.cf/t.co/qrNSzWq0SN (150k+ users) | dm for work / collab
Mars
Joined September 2023
- Tweets3.9K
- Following510
- Followers2.7K
- Likes10.3K
Pinned Tweet
Bookmark it first and thank me later
linktokeep.com
pranav patil retweeted
$25K in a single swap. A @Hyperdex_app user turned 248 SOL into 24,980 USDC on Solana on Sunday, the biggest swap on RAVN over the weekend.
See it with every other swap at app.ravn.exchange/transactio…
pranav patil retweeted
Launching iMessage API
Give your AI agents blue bubbles, with all native features in < 5 minutes.
> Launch your app on iMessage
> Grow to 1000s of users
> Built in observability
Starts free, then just 30$/month.
linktokeep.com is growing like crazy! we got 1k+ download requests in just 2 hours
pranav patil retweeted
Introducing Cardboard for ChatGPT and Claude.
You never know when your best ideas will find you.
So we made sure that @usecardboard is there, whenever they do.
At your desk, or on the go, wherever you are :)
pranav patil retweeted
The internet made scrolling addictive. We think it can make thinking addictive too.
With Matiks, we're bringing the thrill of mental competition to everyone's phone. Math, memory, logic and puzzles, played against real people. A reason to open your phone and play, compete and connect instead of just scroll.
In September, 2.2M people played 48M games on Matiks.
Today, we're sharing that we've raised $10M, led by @generalcatalyst, with participation from @RonnieScrewvala and existing investors.
We're building towards a world where mind sports are as mainstream as physical sports and esports.
Maybe one day, solving puzzles will be as cool as playing cricket.
pranav patil retweeted
Today, I'm launching llmdojo.dev:
- The hands-on way to learn AI engineering: LLMs, RAG, agents, evals and inference.
- 50+ interactive labs. Tweak tokenizers, attention, embeddings and KV caches live.
- Train a neural network in your browser and watch it learn.
- Build agentic workflows with tool calls, memory, guardrails and bounded autonomy.
- Ship RAG that works: chunking, hybrid search, reranking, and LLM-as-a-judge evals.
- Production AI: model routing, fallbacks, quantization, caching and cost per request.
- 490+ interview questions, reported from OpenAI, Anthropic, Google, Meta, Amazon, Microsoft, Mistral and 50+ more.
- Every answer is cited from papers and books, or measured on real models.
