Perplexity (@perplexity_ai) — posts, photos & videos | PeekX

Perplexity

@perplexity_ai

Curiosity changes everything. Download our free app on iOS, Mac, Windows, and Android.

San Francisco, CA perplexity.ai/personal-compu… Joined December 2022

508KFollowers

68Following

1.3KPosts

677Media

13.5KLikes

@perplexity_ai

We're releasing pplx-embed-v2-late, two late-interaction embedding models that retrieve text, images, and pages with a shared embedding space for cross-model querying.

Both models achieve frontier performance and are publicly available on Hugging Face.

perplexity.ai/hub/blog/multi…

66 123 39 655 110K 356

@perplexity_ai reposted

Perplexity Developers

@perplexitydevs

pplx-decider-v1.1-27b, our updated open weights multimodal decision model, is now available.

It scores the highest on the new @huggingface Decision Index 0.3 benchmark. pplx-decider-v1.1-27b costs half as much as v1, at $0.02 per million input tokens.

huggingface.co/spaces/multimo…

47 62 44 559 166K 335

@perplexity_ai

Perplexity Computer now creates interactive charts and visualizations directly in your thread.

For financial data, Computer uses @tradingview Lightweight Charts for candlesticks, volume, and moving averages.

1:02

76 42 20 406 75.3K 73

@perplexity_ai

We built a new way to train contextual embedding models, which encode each chunk of a document with the whole document in view.

pplx-embed-v2-context-9b-preview sets a new state of the art on ConTEB and @turbopuffer's new, privately held context-bench.

perplexity.ai/hub/blog/conte…

58 67 29 712 256K 493

@perplexity_ai

Introducing Automations in Perplexity Computer.

Automations are for ongoing work. They can take action in response to event-based triggers or on a schedule.

Automations work with your memory, skills, and connected apps like Slack, Gmail, Outlook, and Linear.

1:32

54 74 63 786 156K 274

@perplexity_ai

Agent governance is an engineering problem.

We’ve built safeguards into Perplexity’s infrastructure, harnesses, and tools, and put them to work across our products.

Today we're sharing how we engineer safer agents:
perplexity.ai/hub/blog/how-w…

32 42 16 300 96.1K 117

@perplexity_ai

We’re partnering with Nvidia and 100+ industry partners to build infrastructure that contains rogue AI agents.

In this research, we gave 9 AI models root access inside SPACE and told them to break out.

Across 108 runs, none breached the VM boundary.
perplexity.ai/hub/blog/escap…

61 56 15 434 150K 98

@perplexity_ai

Introducing Fast Search in the Perplexity Search API.

Fast Search runs on Photon, our new Rust-based retrieval and ranking service that we built with a small team of engineers and hundreds of agents.

It returns 95% of search results in 230 ms or less.

66 39 28 548 149K 137

@perplexity_ai

Portable Computer for Windows is now available on @AMD Ryzen AI Max Series processors.

It makes it easy to run local AI agents that work with your connected apps and local files. Kick off tasks or schedule recurring work that runs entirely on your device.

0:41

47 51 16 379 77.7K 59

@perplexity_ai

New research: We post-trained a Computer model to learn from its own errors using hint-guided self-distillation.

In a live A/B test, a later trained checkpoint reduced tool-call failures by 21.2% relative to an earlier checkpoint.

40 32 15 386 114K 139

@perplexity_ai

GPT-6 Sol is now available in Perplexity and Computer.

It's now the default Light option in Computer's effort selector.

25 23 6 388 29.6K 25

@perplexity_ai

Claude Opus 5.5 is now available as the Standard effort level in Perplexity Computer.

On our WANDR benchmark, it scored 0.610 at $4.13 per task, slightly outperforming Claude Fable 5.1 while costing 67.6% less per task.

25 21 4 418 33.7K 28

@perplexity_ai

Perplexity Computer can now create videos using MiniMax H3 and ByteDance Seedance 2.5.

Ask Computer for a campaign clip, product demo, or social asset, and it produces finished video next to copy and creative in same thread.

Available now for Pro and Max subscribers.

0:30

61 62 30 789 144K 206

@perplexity_ai

We’re rolling out effort controls in Computer’s model selector.

Effort presets combine the orchestrator model and reasoning depth to control how deeply and efficiently Computer works through a task.

Available now on web. Coming to mobile and desktop soon.

0:11

71 46 31 533 175K 86

@perplexity_ai

We’re publishing research on how we built CobbleDB, our key-value database that serves web content for Perplexity search.

Two engineers and a team of hundreds of proactive, always-on AI agents built the core infrastructure in two months.

84 92 38 963 498K 508

@perplexity_ai

Perplexity Computer will now come pre-installed on HP ZBook Ultra G3a. .

Use Computer to run complex multi-step work from a simple interface. Computer agents are grounded in accurate deep research and connected to hundreds of tools, now including Autodesk.

27 33 4 328 34K 50

@perplexity_ai

Portable Computer is now available on Windows PCs with @nvidia RTX GPUs.

Run the harness, agents, and models locally on your PC.

Work with local files and connected apps without sending tasks to the cloud. Use frontier cloud models when needed.

0:33

119 130 99 1.1K 666K 381

@perplexity_ai

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…

30 42 12 292 98.1K 114

@perplexity_ai

GPT-6 Astra is now available in Perplexity Computer for Pro and Max subscribers.

Perplexity@perplexity_ai · Sep 3

We evaluated GPT-6 Astra on WANDR. It scored 0.682 at $11.98 per task, the highest score of any model we tested.

GPT-6-Astra scored 13.5% higher than Fable 5.1 at 6.1% lower cost, and 27.0% higher than Opus 5 at 3.3% higher cost.

Open quoted post →

47 48 8 805 1.8M 67

@perplexity_ai

Every answer in Perplexity starts with embedding and ranking models picking the most relevant results for the query.

Today we published research on how we built SoTA serving infrastructure behind those models.

Read the research: perplexity.ai/hub/blog/fast-…

30 53 11 528 131K 358