@natjin
Account based inUnited States
About this account
- Account based in
- United States
- Connected via
- United States App Store
Account-level information from X, not a live location or the device used for a specific post.
currently obsessing over developers + apis @perplexity_ai | recovering finance bro | humanities degree doing more work than expected | views completely my own
sf
Joined December 2018
- Tweets1.7K
- Following1.9K
- Followers4K
- Likes5.7K
quants are cooked
just one-shotted arb
prediction markets (Polymarket, Kalshi) and sportsbooks (DraftKings, FanDuel) often price the same event differently. buy both sides across platforms and you lock in guaranteed profit regardless of outcome
this scans all of them in real-time and surfaces the gaps
free internet alpha. yw
perplexity.ai/computer/a/arb…
nat jin retweeted
Fast Search is now the default search in Hermes Agent for Nous Portal subscribers.
It’s built for agentic tasks, with single-search-call latency of 160 ms at p50 and 230 ms at p95.
Learn more: pplx.ai/hermes-fast-search
nat jin retweeted
we’re excited to share that we’ve raised $20M (from Accel, Index, & Emergence) to build the 'ai-native Slack' you've all been craving
TLDR; ando is a team messaging platform built fresh, from the ground, up for a world where agents act as real collaborators alongside us.
we have teams using us across 15 countries, and spanning industries like software, financial services, real estate, & more
request access if any of this resonates 💌
nat jin retweeted
We released pplx-embed-v1 early this year, with Q2D benchmark to evaluate how embedding model performs for web search, not looking at nDCG@10, but Recall@1000.
Q2D-Web further scale it up 7 times. With 70k agentic reformulated queries and 190 million web corpus. We hope the benchmark becomes the modern “MS MARCO”
We're introducing Q2D-Web (Query2Doc-Web), a benchmark and public leaderboard for evaluating retrieval in agentic RAG systems.
Q2D-Web tests how embedding models perform on large-scale web search using agent-reformulated search queries.
Read more: perplexity.ai/hub/blog/q2d-w…
nat jin retweeted
Perplexity Search API is now available in Hermes Agent.
Search API gives Hermes access to an index of more than 400 billion URLs. It returns real-time results and ranks snippets by relevance.
pplx.ai/hermes
We're working to get Perplexity's Search index on as many surfaces as possible (more to come here).
If you're building agents, you should be using the most efficient and performant search index on the market.
DMs are open if there's a framework/integration we're not currently covering.
Perplexity API is now available in Stripe Projects.
In the Stripe CLI, type "stripe projects add perplexity/api" to get started.
Provision a Perplexity API project, API key, and prepaid credits straight from your terminal or coding agent using the Stripe Projects CLI.
pplx.ai/pplx-stripe-pro
nat jin retweeted
meet @mostik_ai!
what happens when you put 12 PhDs in one room for four months? first place on the ARC-AGI leaderboard, which I can't say much about while the competition is still running. and this, which I can.
everyone's arguing about whether open models will catch up to frontier models. we think it's the wrong question. here's the one we pose: why does a frontier model have to generate your answer at all, when the only thing you need from it is the reasoning?
we do this by enabling models to communicate in latent space. through our protocol, hidden states pass straight from a frontier model into a small one running on your infrastructure -- no text between them, and neither model is fine-tuned. two models from different families, sharing reasoning, both left untouched.
how do we know it works? we tested it on a setup where a 753B model reads the problem, and a 4B edge-class model writes the answer. with this approach, we get results 80% as accurate as the frontier model, but at 20x faster performance.
we're committed to preventing frontier model lock-in and are already partnering with inference providers to accelerate open-weight adoption. we've done this between 15 of us, in four months, 12 PhDs and a Fields medalist, backed by @generalcatalyst
WIRED has the first external account of the company and the work: wired.com/story/russian-star…
full writeup, the setup, and all the numbers: mostik.ai/read-more
Great to see rigorous, open benchmarking for search.
All three Perplexity Search context settings debut at the top of the index.
Perplexity Search debuts on the Artificial Analysis Search Index, with all three context size variants taking top positions on the leaderboard
The @perplexity_ai Search API comes with three context settings (low, medium, and high) that control how much extracted content each search result carries. We tested all three variants using our standardized methodology: the same model (GPT-5.6 Luna at medium reasoning), running inside Stirrup, our open-source agent harness, with tools for searching and fetching pages from the web. Only the provider behind the search tool changes.
Key results:
➤ Perplexity Search (medium) scores 80 on the Artificial Analysis Search Index, ahead of the previous leaders, Parallel (advanced) and Brave Search (LLM context), at 75. The high and low variants score 79 and 77 respectively. Its lead is concentrated in BrowseComp results, with AA-Omniscience and DeepSearchQA scoring comparably to other leading providers
➤ Efficient search payloads: smaller overall search results mean the model reads less per task, so Perplexity has the lowest model inference cost per task of providers we’ve tested so far, ranging from $0.028 to $0.034 across the three variants vs $0.036 for the next lowest provider
➤ Total cost per task is ~$0.091 for the medium and high context variants, at mid-pack latency. For comparison, Parallel (advanced) costs $0.084 per task and Brave (LLM context) costs $0.13 per task
Best CX Agents 🤝 Best Web Search for Agents
We’re partnering with @Perplexity_AI to bring live web search to Decagon agents.
Customer questions often depend on information that changes by the hour.
Agents can now search the live web mid conversation, pull in current information, and respond with cited sources.
nat jin retweeted
at perplexity we are really excited about multi-agent collaboration! we recently explored a simple instantiation of this with advisor escalation from a local model to a remote frontier model, where we showed it can significantly boost the local model's performance.
an alternative way i like to think about this: the local model becomes a **gateway** to remote models. its main job is to preprocess all the raw tokens, package them into fewer, more information-dense tokens, and send only those to the server. this preprocessing has several advantages: it reduces cost and latency, enables personalization, and allows privacy controls. already such approaches can save 50% of tokens, but imagine a future where 90%+ of tokens are processed locally and only 10% are sent to the server for the last-mile hardest reasoning. that is a 10x cost reduction and a much more pleasant UX due to low latency.
training such a multi-agent system is not an easy problem and still requires a lot of research in multi-agent RL, but we are making good progress and actively hiring for this. if this sounds interesting please DM me
Today we’re launching Portable Computer on @NVIDIA DGX Spark.
Portable Computer is a fully local version of Perplexity Computer, where the entire runtime: orchestrator LLM, subagent LLM, agent harness all run on your local hardware. No cloud dependency.
We are heavily investing in our APIs and our developer community here at Perplexity.
Come join us on the journey of building the primitives -- the fundamental building blocks -- for Agent development.
Sales (SF/NYC): jobs.ashbyhq.com/perplexity/…
PMM / Marketing (SF / NYC): jobs.ashbyhq.com/perplexity/…
Eng Manager API Platform (SF): jobs.ashbyhq.com/perplexity/…
Eng (SF / NYC): jobs.ashbyhq.com/perplexity/…
...and many more. If you don't see your exact role but want to work on frontier AI primitives, DMs are open.
.@perplexitydevs Search API topping charts across the board (quality, value, speed). why?
> 400bn unique URLs and growing
> hundreds of millions of daily queries used in product by perplexity computer + perplexity ask
> if search quality is bad, we're first to hear about it from our users
> if search is token inefficient, our margins suffer
> if search is slow, our product deteriorates
buy primitives from people with skin in the game
Introducing Web Search Benchmarks 🌐
Rankings of search tools across different models and configurations to help you decide how to ground your agent: openrouter.ai/benchmarks
nat jin retweeted
We just raised $5.7M for @PolarBrowser, the AI browser that beats Anthropic and OpenAI on every major web agent benchmark.
- 4,500,000+ actions taken for users, automating sales, recruiting, and ops
- One company cancelled Clay and saves 25+ hrs/wk per person
- Team is from MIT, YC, Prod, Citadel, Jane Street, Perplexity, Modal, and Apple
100 hours of work. From 30 seconds of typing.
Download the world's most powerful AI browser: polarbrowser.com
