Perplexity Computer is the AI that actually does your work
Claude reasons, Gemini researches, GPT recalls, and 16 other models do the rest — all coordinated automatically by Perplexity Computer.https://gadgetbond.com/perplexity-computer-ai-orchestration-system-explained/
Perplexity Computer can now hear you — voice mode officially launches
The new voice mode in Perplexity Computer includes an Extended Speaking option, so the AI waits until you're done talking before it responds or acts.https://gadgetbond.com/perplexity-computer-voice-mode-ai-agent-launch/
AI orchestration is the new operating system — Perplexity got there first
Perplexity Computer started as a Slack experiment called ASI, and it grew into a 19-model orchestration platform that works while you sleep.https://gadgetbond.com/perplexity-computer-ai-orchestration-system/
Perplexity Computer unifies top AI models into one powerful worker
Built on Comet, deep research, tasks, and persistent memory, Perplexity Computer is the moment Perplexity’s accuracy‑first stack comes together.
Perplexity AI's revolutionary browser 'Comet' is setting foot on iPhone this March 11, 2026. Known for its AI-driven features like interactive search and task automation, Comet aims to transform how we browse, now optimized for iPhone users. Dive into this innovative AI-first browser that's already making waves across Mac, Windows, and Android. Get ready for seamless browsing with a personal assistant right at your fingertips!
Perplexity and Comet just made voice mode feel truly real‑time
Instead of tapping and typing, you can now talk your way through tabs, articles, and research sessions with a more stable, expressive AI on Perplexity and Comet.
Perplexity Comet AI browser launches on iOS this March
Perplexity is finally shipping its AI‑first Comet browser to iPhone owners, after rolling it out on Mac, Windows, and Android.https://gadgetbond.com/perplexity-comet-ai-browser-iphone-ios-preorder-launch-date/
Protecting the "Mind" of AI Browsers: Why Agentic AI Needs Robust Defenses Against Prompt Injection 🛡️
Fellow Mastodonians in #CyberSec and #AISecurity,
As we wrap up 2025, agentic AI browsers like ChatGPT Atlas (OpenAI), Perplexity Comet, Microsoft Edge Copilot Mode, and others are redefining productivity. These tools let AI agents autonomously navigate, summarize, interact with authenticated sessions, and execute tasks—turning browsers into true digital assistants.
But this autonomy expands the attack surface dramatically. Prompt Injection tops the OWASP Top 10 for LLM Applications 2025 (LLM01:2025). Attackers hide malicious instructions in web content, emails, Google Docs, URLs, or even screenshots—hijacking the agent to leak data, perform unauthorized actions, or worse.
Key real-world developments this year:
OpenAI openly states prompt injections are unlikely to ever be fully solved—comparable to social engineering. They're using an LLM-based "automated attacker" for red teaming Atlas defenses.
CometJacking in Perplexity Comet: A single crafted URL exploits query parameters to exfiltrate data from connected services (Gmail, calendars) via encoded payloads (LayerX research).
Indirect injections via hidden text in Docs/emails affected Atlas on launch day; Brave called it a systemic issue across agentic browsers.
Broader demos: Agents tricked into sending resignation emails, downloading malware, or navigating phishing sites.
Traditional tools (AdBlock, etc.) can't help—they block scripts/domains, not semantic manipulations of LLM prompts.
Toward Multi-Layered Protections:
Model hardening: Adversarial training & instruction hierarchies (e.g., OpenAI's ongoing updates).
Runtime guards: Tools like Lakera Guard, NeMo Guardrails, Protect AI LLM Guard for injection detection, sanitization, and sandboxing.
Architecture: Least-privilege sessions, explicit approvals, audit logs.
Enterprise best practices: Align with OWASP LLM Top 10—red teaming, zero-trust for agents, limit access (e.g., "logged-out" mode in Atlas).
Prompt injection isn't going away—it's the new frontier. How are you approaching agentic AI security in your setups?
#GenAI #PromptInjection #AgenticAI #OWASP #ChatGPTAtlas #PerplexityComet
P.S. Devs & sec folks: Explore open-source like NeMo Guardrails or Lakera for prototyping browser-level defenses. Let's build safer AI together. 🚀
My in-depth review of Perplexity Comet is now live! 🚀
I've shared my honest experience with this AI-powered browser, covering its 'agentic' capabilities, what I genuinely liked, the significant drawbacks (including security concerns like prompt injection), and how it stacks up against my current workflow.
If you're curious about the future of web browsing, dive in: https://www.ctnet.co.uk/my-thoughts-on-perplexity-comet/
Shubham Sawarkar
Renaud JOLY
DataDef(AE)
CTNET