XIndustry23:03Perplexity@perplexity_aiGemini 4 Argon sets a new record on WANDR. It is now available in Perplexity for Pro and Max subscribers. https://t.co/n1TyI9RhBXCollected by WispRead in full↗
XIndustry01:03Perplexity@perplexity_aiWe tested SPACE by attacking it with frontier models. In Escaping SPACE: Part I, nine model configurations with root inside the VM made 108 escape attempts, and none reached the host. Read the research: https://t.co/UD6qHuCuO4Collected by WispRead in full↗
XIndustry02:03Perplexity@perplexity_aiNVIDIA’s Nemotron 3.5 Super VL is now available in Perplexity for Pro and Max subscribers, and in Agent API. https://t.co/fMVGtyZFFQCollected by WispRead in full↗
XIndustry01:03Perplexity@perplexity_aiWe're open sourcing SPACE, the sandbox platform that runs every task in Perplexity Computer. SPACE gives each agent task its own Firecracker microVM and controls credentials and outbound traffic from outside the VM. Available now under Apache 2.0: https://t.co/DzSmq6o1xACollected by WispRead in full↗
XIndustry01:03Perplexity@perplexity_aiSPACE is the first component of Perplexity's Agentic Runtime Platform. We're open sourcing it to raise the security bar for agentic products. Read the blog: https://t.co/miVD6FecqZCollected by WispRead in full↗
XIndustry01:01Perplexity@perplexity_aiUltrafast versions of GPT-6 Astra and SOL 6.1 are now available in Perplexity Computer for Max subscribers. Both generate tokens faster, completing long Computer tasks sooner. Choose Astra or SOL 6.1 under Custom, then set speed to Ultrafast. https://t.co/g428a2Q0SCCollected by WispRead in full↗
XIndustry00:02Perplexity@perplexity_aiOur sandbox, SPACE, handles millions of executions a day with an error rate below 0.0002%. We’re sharing how it uses cryptographic identity to keep requests tied to the right execution as sandboxes pause, resume, and move. Read more: https://t.co/jH6TX2cgI9Collected by WispRead in full↗
XIndustry00:02Perplexity@perplexity_aiTerminals and file watches can outlive their opening requests. Once a receiver installs the new execution identity, SPACE stops the old streams. Eligible operations can reconnect once, passing the identity checks again. Read the article: https://t.co/jH6TX2cgI9 https://t.co/BQWAdFZK3iCollected by WispRead in full↗
XIndustry00:02Perplexity@perplexity_aiEach request carries short-lived, signed proof of which execution may handle it and what access is allowed. The receiving worker checks that identity against its own runtime record and rejects mismatches before forwarding. https://t.co/H6fWrAmb5pCollected by WispRead in full↗
XIndustry02:05Perplexity@perplexity_aiBecause each sandbox holds a real checkout, agents search it with grep and standard file tools instead of relying on broad semantic searches. On an internal benchmark of 150 financial-document questions, this reached 0.627 answer accuracy versus about 0.37 for semantic search. https://t.co/w1nmA0N8yzCollected by WispRead in full↗
XIndustry02:05Perplexity@perplexity_aiA single long-lived sandbox per project would need provisioning for peak load and months of uptime. Instead, repositories live on S3-backed storage and each agent runs in its own ephemeral sandbox, so a crash loses only unsubmitted work. https://t.co/dglC3ZI6AXCollected by WispRead in full↗
XIndustry02:05Perplexity@perplexity_aiThis is how we built the filesystem behind Perplexity Projects as a Git forge for agents. Each agent works in its own sandbox and commits to a shared repository where people and other agents can build on its work across sessions. Read more: https://t.co/jcrTptb2IW https://t.co/dXnhroO4mgCollected by WispRead in full↗
XIndustry00:10Perplexity@perplexity_aiOn MADQA, 500 questions over 800 PDFs, it reaches 92.4%, the top result among retrievers. https://t.co/uxW8LDau2cCollected by WispRead in full↗
XIndustry00:09Perplexity@perplexity_aiWe'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. https://t.co/AM7YEyQkKE https://t.co/fR8kaYmHs1Collected by WispRead in full↗
XIndustry00:10Perplexity@perplexity_aiIn agentic search, a GPT-OSS-120B agent using the 9B model answers 64.0% of BrowseComp+ questions correctly, 4.9 points ahead of the next ColBERT model, with fewer searches than any baseline. https://t.co/hFngH5ES7DCollected by WispRead in full↗
XIndustry00:10Perplexity@perplexity_aiOn Q2D-Web, about 70,000 production-derived search queries over 190M web documents, the 9B and 0.6B models reach 74.8% and 73.6% Recall@1000, against 69.3% for nemotron-embed-8b. https://t.co/FwltQP6jGNCollected by WispRead in full↗
XIndustry00:12Perplexity@perplexity_aiPerplexity 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. https://t.co/AItBm2tN07Collected by WispRead in full↗
XIndustry03:07Perplexity@perplexity_aiView pplx-embed-v2-context-9b-preview on Hugging Face: https://t.co/EeqI2xCFOlCollected by WispRead in full↗
XIndustry03:07Perplexity@perplexity_aiOn ConTEB, the preview has the highest average nDCG@10 of the models tested, though not on every task. It also beats voyage-context-4 on chunk retrieval while using 8x less storage per vector: 1 KB (1024 dims, int8) vs 8 KB (2048, float32). https://t.co/PsyAwyU0ZoCollected by WispRead in full↗
XIndustry03:07Perplexity@perplexity_aiWe 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. https://t.co/tkBUEjWVio https://t.co/yz1eVPrJjRCollected by WispRead in full↗