AI Coding Live News — Real-Time 𝕏/Twitter Updates & Breakthroughs

Perplexity@perplexity_ai·Collected 49d ago

👀48

🔥91

Perplexity Portable Computer hits Windows: local agents on 24GB+ NVIDIA RTX with MCP and scheduled tasks

Perplexity says Portable Computer is now available on Windows PCs with NVIDIA RTX GPUs: run the harness, agents, and models locally, work with local files and apps, and fall back to frontier cloud models when needed. On-device work does not consume Computer credits; follow-ups add local MCP and scheduled tasks, and NVIDIA confirms 24GB+ VRAM.

Key Takeaways

Portable Computer now runs on Windows with NVIDIA RTX for local harness/agents/models.
On-device work skips Computer credits; cloud frontier models remain optional.
Adds local MCP and scheduled tasks; NVIDIA lists GeForce/RTX PRO 24GB+ VRAM.

Read full story

Linked Models & Agents:

🌐 perplexity 🌐 Nvidia (NIM)

#Perplexity#Portable Computer#Windows#NVIDIA RTX#local agents#MCP#scheduled tasks#24GB VRAM

Perplexity@perplexity_ai·Collected 60d ago

👀53

🔥88

View on 𝕏 ↗

Perplexity Portable Computer lands on Linux for NVIDIA RTX GPUs with 24GB+ VRAM

Perplexity (@perplexity_ai) says Portable Computer is now available on Linux for NVIDIA RTX GPUs with 24GB of VRAM or higher. It is a local-first AI assistant stack: orchestrator and subagent models can run privately on-device, with optional cloud escalation. After the earlier DGX Spark launch, this extends local deployment to consumer/workstation RTX cards.

Key Takeaways

Linux build needs NVIDIA RTX with 24GB+ VRAM.
Local-first: orchestrator LLM, subagent LLM, and agent harness can run on-device.
Complements the DGX Spark edition and lowers the bar for high-VRAM RTX workstations.

Read full story

Linked Models & Agents:

🌐 perplexity 🌐 Nvidia (NIM)

#Portable Computer#Perplexity#Linux#NVIDIA RTX#local AI#On device#Agent

Perplexity@perplexity_ai·Collected 64d ago

👀44

🔥92

View on 𝕏 ↗

Perplexity Launches Portable Computer: Local-First Autonomous Agent Stack on NVIDIA DGX Spark

Perplexity introduced Portable Computer on NVIDIA DGX Spark, providing a fully local-first agent stack powered by on-device PPLX 27B where private documents never leave the machine by default.

Key Takeaways

Commercializes local-first agents: private documents stay on-device unless explicitly approved for cloud calls;
Lightweight harness custom-engineered for 27B models with compact CLI connectors and on-device sandboxing;
Hybrid escalation allows optional pay-per-task cloud frontier calls (~$0.42) lifting Terminal Bench to 73.0%.

Read full story

Linked Models & Agents:

⚡ Pplx 27b⚡ Claude 3.7 Sonnet (Hybrid Reasoning)