Perplexity Pro just became the best $20/month I spend. I use it for market research, trend analysis, and competitive intelligence. Here are 12 prompts that replaced my $500/month research subscriptions:
LLMS
-
Using AI Agents and NotebookLM for Personalized News Analysis
By
–
Personalized news is in my house. I don’t know if you all are seeing what I am doing with bleeding edge AI. From @blevlabs
. His AI agents “Braygents” analyze the news in ways way beyond human. I had it write me an Economist article. Then copied that over to Notebook LM -
LLMs create observability blind spots in systems
By
–
LLMs create a new blind spot in observability – The New Stack https://
share.google/huI6TXsfZoELW4
nqt
… #LLMs #LLM #GenerativeAI #GenAI #artificialintelligence -
First Non-Faceless YouTube Video on Agentic AI and RAG
By
–
Finally recorded my first non-faceless YouTube video. Been inspired by @dabit3 for years (back to his Amazon then web3 days)—the way he explores something new, learns it, builds with it, then teaches it publicly. That loop is what I'm trying to do more of this year. So here's my first attempt on Agentic AI basic—LLMs, RAG, and Agents explained simply with a hands-on @FlowiseAI demo where we build a working RAG agent for CX. I know many folks are advanced Clawding at this point, but if you're a bit fuzzy on how these pieces connect this is a quick way to dive into without the hype. 🎥 piped.video/watch?v=4WWQV6hg…
→ View original post on X — @flowiseai, 2026-01-25 20:13 UTC
-
Using AI Agents and Cognitive Architecture for Automated Data Reporting
By
–
It isn’t a tool. It is @blevlabs cognitive architecture. And the agents it builds. It is way way way better than any other AI. Had it grab 5,000 posts from my lists via X API. Then it wrote this report.
-
Test-Time Learning: RL Discovers Solutions During Inference
By
–
Learning to Discover at Test Time This paper TTT-Discover shows that by replacing best-of-N prompting with RL at test time on a continuous verifiable reward (via LoRA), it can learn from its own attempts and reliably push past the prior performance. The “learn-while-solving”
-
Google urged to adopt Cloud Run with exclusive Gemini model support
By
–
Google should push for a Cloud Run-powered setup where only Gemini models are supported 😛
-
OpenAI’s reliance on Codex for internal tooling and rapid development
By
–
Can confirm – we made the OpenAI MCP server in ~3 days (and scale proof), there’s Sora android app in ~3 weeks and a lot more internal tooling built by codex, reviewed by codex. Hard to see how OpenAI could still ship at the speed it does without codex. Anecdotally, I spend a
-
Programmer’s passion for the new AI-powered world
By
–
i always loved programming but am loving the new world even more
-
xAI introduces Dev Models on Grok for system prompt and tool calls
By
–
BREAKING : xAI is implementing a new "Dev Models" section on Grok, which allows users to override the base model system prompt, tool calls and more. It could be an enterprise-specific feature