# perplexity (blogs) — RSS Amplifier Recent posts from the 3 feeds in the RSS Amplifier directory that cover perplexity. Page: Feed: --- ## [This Second Brain Will Change How You Write Your Newsletter: Cluing Review + AI Agents Preview](https://karozieminski.substack.com/p/cluing-review-ai-agents-second-brain-2026) _2026-08-19 · Karo (Product with Attitude) · Product with Attitude_ The new Cluing agents, MCP into Claude, Codex, Perplexity and Gemini, plus a gift for my readers. ## [Discounts for Premium Members (Q3 2026)](https://karozieminski.substack.com/p/premium-membership-ai-tool-discounts-2026) _2026-08-19 · Karo (Product with Attitude) · Product with Attitude_ Your PwA subscription pays for itself in tool discounts and credits. ## [I Build AI Products for a Living. Here Are 5 Things All Model Comparisons Miss.](https://karozieminski.substack.com/p/chatgpt-work-vs-claude-cowork-vs-perplexity-computer) _2026-08-11 · Karo (Product with Attitude) · Product with Attitude_ What ChatGPT Work, Perplexity Computer and Claude Cowork assume about us, the users, and what they reveal about perceived AI intelligence. ## [AI for Crime Junkies: When ChatGPT Prompts Become Evidence](https://karozieminski.substack.com/p/pig-butchering-ai-scam-compounds) _2026-08-04 · Karo (Product with Attitude) · Product with Attitude_ Inside the operation that assigned every victim a "kill value." Updated daily, with ChatGPT's help. ## [Google Analytics 4 Cluing Agent Instructions + Daily GA4 Analysis Prompt](https://karozieminski.substack.com/p/google-analytics-4-ga4-cluing-agent-instructions-daily-analysis) _2026-08-01 · Karo (Product with Attitude) · Product with Attitude_ A ready-to-customize Cluing AI agent prompt for monitoring Google Analytics 4, diagnosing traffic and conversion changes, detecting anomalies, and generating daily GA4 reports. ## [Skill: Weekly Reader Question Review](https://karozieminski.substack.com/p/weekly-reader-question-review-content-planning-skill) _2026-08-01 · Karo (Product with Attitude) · Product with Attitude_ Analyze recent reader questions and identify recurring themes, pain points, and content opportunities. ## [5 Protocols Now Decide How AI Agents Shop. Here's What Each One Does.](https://karozieminski.substack.com/p/agentic-commerce-protocols-acp-ap2-x402-mpp-ucp) _2026-07-30 · Karo (Product with Attitude) · Product with Attitude_ An AI PM reads the specs behind agentic commerce: what ACP, AP2, x402, MPP, and UCP each do, ZeroClick's unpublished pricing, and how to sell to AI agents. ## [1 Community, 164 builders, 100 methods, Y Combinator, and OpenAI Build Week 2026.](https://karozieminski.substack.com/p/ai-builder-community-showcase-july-2026) _2026-07-27 · Karo (Product with Attitude) · Product with Attitude_ The Product with Attitude community is building. A lot. ## [AI-assisted Craft: A Manifesto](https://karozieminski.substack.com/p/ai-assisted-craft-vs-ai-slop) _2026-07-22 · Karo (Product with Attitude) · Product with Attitude_ The missing category between human-made and AI-made. ## [How to Build Your First Agent. One That Works.](https://karozieminski.substack.com/p/how-to-build-your-first-ai-agent) _2026-07-21 · Karo (Product with Attitude) · Product with Attitude_ A beginner-friendly visual guide to building your first AI agent in Claude Code, based on questions from my readers. ## [Find it on Amazon (Sponsored)](https://crawlproof.com/a/LBhPBTwwkLOJ) _2026-07-21 · **Sponsored**_ Open the Amazon product listing to see details and availability ## [Cattle not Pets, for Code](https://samek.fyi/pets-cattle-ai-code/) _2026-06-21 · samek.fyi_ Cattle not pets , for software developers: The shift from handcrafted servers to immutable infrastructure taught us that mutability is the sworn enemy of understanding. Any artifact that is edited in place creates drift. Drift is what makes systems impossible to maintain. Our ability to kill and regenerate infrastructure components is the reason we trust it. At Honeycomb, we kill the oldest Kafka… ## [When a Change Feels Risky](https://samek.fyi/risky-ai-changes/) _2026-06-12 · samek.fyi_ I’m trying to get into a new habit. Previously, when I wrote some code, and it felt risky, I would reread the code more carefully, read the surrounding code, try it out locally or in staging, and monitor closely after deploying. When I write code with AI, I’m grateful to have the intuition that a particular code change is risky, since that represents years of experience with the types… ## [I am getting faster (and duller)](https://dhariri.com/2026/faster-duller) _2026-05-01 · David Hariri_ Reflecting on a month of shipping a lot, but with a noticable trade off to understanding. ## [From Working in the Business to Working on It](https://samek.fyi/from-working-in-the-business-to-working-on-it/) _2026-04-12 · samek.fyi_ There’s an old business idea, usually attributed to Michael Gerber, about the difference between working in your business and working on your business. Working in the business is doing the thing. Working on the business is improving how the business works. I think this distinction works in an analogous way in software engineering. Writing code is working in the business. Everything around… ## [Compress, Please](https://dhariri.com/2026/compress-please) _2026-04-10 · David Hariri_ On using LLMs to write shorter letters, not longer ones. ## [MCP is not for you](https://dhariri.com/2026/no-mcp-is-good) _2026-03-24 · David Hariri_ The one in which I refute the recent arguments against MCP and where I think it's coming from. ## [Brain Fry](https://dhariri.com/2026/brain-fry) _2026-03-22 · David Hariri_ Reactions to a recent HBR article and my own experience with over-delegation to Claude Code ## [Benchmarks](https://samek.fyi/benchmarks/) _2026-03-12 · samek.fyi_ This is a list of AI benchmarks I’m watching. Last updated July 27, 2026. ALE-Bench ARC Prize Artificial Analysis Bullshit Benchmark CursorBench DeepSWE Design Arena Epoch AI Models EQ-Bench 3 EQ-Bench Creative Writing ExploitBench Frontier Code GameDevBench GBA Eval Gert Labs Rankings LiveBench LLM Debate Benchmark LMArena MathArena Mercor Apex METR Time Horizons RuneScape Bench SimpleBench… ## [Let the LLM Try First](https://samek.fyi/let-the-llm-try-first/) _2026-03-11 · samek.fyi_ I had an deck in Anki, a flashcards app, with an annoying problem that I had caused when I imported the cards. On some cards, the front of the card had text that linked to a URL. On others, the URL was only on the back, which meant I couldn’t click it when I actually wanted it. My first instinct was to export the deck to CSV, use AI to write a script to transform it, and then import it… ## [Reflections on Prototyping a Sysadmin Benchmark](https://samek.fyi/reflections-on-prototyping-a-sysadmin-benchmark/) _2026-02-13 · samek.fyi_ I’ve been doing a bunch of keeping up with and experimenting with AI. It’s still a surprise to me that I can create a Chrome extension in minutes, having never written one before, and having rarely programmed in JavaScript. I wrote a Chrome extension to copy page content, and another to send the same prompt to multiple LLMs, then a CLI tool to do the same with Simon Willison’s… ## [Point a Domain, Start a Pit (Sponsored)](https://crawlproof.com/a/7uyiR90ZyhQL) _2026-02-13 · **Sponsored**_ Point any domain to a blacked-out, poison-green coming-soon page with an email waitlist. ## [My Dream iPhone](https://dhariri.com/2025/dream-iphone) _2025-10-28 · David Hariri_ A man can dream and this man dreams of an iPhone that puts the power of the iPhone 17 Pro in the palm of my hand. ## [Benchmarks I'm Watching Now](https://samek.fyi/benchmarks-im-watching-now/) _2025-10-20 · samek.fyi_ Whenever a new model is released, I read the benchmarks. I haven’t seen a good list of benchmarks. I tend to see them referenced and then bookmark them. Here’s my list. I keep a continually updated list of benchmarks at samek.fyi/benchmarks . I deleted the old list that used to live in this post so that I could link to the updated one instead. ## [Make macOS Faster](https://dhariri.com/2025/fast-macos) _2025-10-19 · David Hariri_ How I made macOS feel as fast and productive as Linux without leaving the walled garden. ## [Dia Browser](https://samek.fyi/dia-browser/) _2025-06-13 · samek.fyi_ I tried Dia , a new Chromium-based browser with built-in AI features from the creators of Arc . It has an AI chat sidebar that can reference any open tab, plus writing assistance that pulls context from multiple tabs. Their YouTube video shows someone writing an email in Gmail based on their Google Calendar tab. It’s a UX improvement over existing options. Brave’s Leo only works with… ## [Pocket to RSS is No More](https://dhariri.com/2025/pocket-rss-dead) _2025-06-07 · David Hariri_ I pulled the plug on pocket-rss.com ## [Coding Agent with Simon Willison's LLM](https://samek.fyi/coding-agent-with-simon-willisons-llm/) _2025-05-28 · samek.fyi_ Simon Willison released tool calling in his llm CLI. A tool is just a python function. Inspired by Coding agent in 94 lines of Ruby , I wrote a coding agent in Python. Here’s the code . aider helpfully explains the various editing formats people use for LLMs: whole returns an entirely new document. diff is a series of search and replace blocks. diff-fenced is like diffs but puts the filename… ## [Pareto Frontier LLMs, Aider Edition](https://samek.fyi/pareto-frontier-llms-aider-edition/) _2025-05-08 · samek.fyi_ Google released an impressive improvement to Gemini, which now tops the WebDev Arena Leaderboard . That position had been held by Claude for quite a while. Here’s a Pareto frontier for the Aider polyglot coding leaderboard . The analysis of March’s Gemini didn’t include reasoning tokens in the cost. They fixed the problem for May’s release. It’s too bad it… ## [Pareto Frontier LLMs, Kagi Edition](https://samek.fyi/pareto-frontier-models-kagi-edition/) _2025-05-03 · samek.fyi_ Kagi benchmarks LLMs on a private benchmark. I asked Claude to build a Pareto frontier chart for Kagi’s April 17th, 2025, update ( source code ). Claude has the strange property of doing well on some benchmarks and not others. It creates half as much slop in longform writing as Gemini and OpenAI models, for example, and does well in a number of coding benchmarks, while doing much worse than… ## [About Me](https://samek.fyi/about-me/) _2025-05-01 · samek.fyi_ I’m Brian Samek. I began my career as a sysadmin in public and university libraries. I’ve been at MongoDB for a decade, as Software Engineer, Lead, Director, and now Staff Engineer. I’ve helped scale our Continuous Integration system to handle hundreds of millions of tests a day, led a major software supply chain security initiative, and built teams that consistently deliver useful and… ## [Model Context Protocol, Simply](https://samek.fyi/model-context-protocol-simply/) _2025-05-01 · samek.fyi_ I keep seeing descriptions of Model Context Protocol (MCP) that are either vague metaphors or get too specific too quickly. From the official docs : MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP… ## [Refer a Friend, Earn Rewards (Sponsored)](https://crawlproof.com/a/N1jXg8p7QkOz) _2025-05-01 · **Sponsored**_ Earn rewards when friends get the Graphite Business Card through your referral. ## [o3 Is the Research Assistant I Wanted](https://samek.fyi/o3-is-the-research-assistant-i-wanted/) _2025-04-30 · samek.fyi_ Deep Research (three separate products! from Perplexity, OpenAI, and Gemini) is usually more than I want. Instead I want something that stops when it has the answer. Here’s a great example about predicting the next pope. It searched the web to find out what prediction markets said, aggregated and normalized the data, and gave me a chart of probabilities. Then it made a second chart… ## [ChatGPT's Improved Search](https://samek.fyi/chatgpts-improved-search/) _2025-04-28 · samek.fyi_ A few days ago I wrote that Perplexity is better for quick searches. That may have changed. OpenAI announced some search improvements, though sources were not among them, and Sam Altman mentioned improvements to the model. ChatGPT now does a better job at my example query, explicitly noting that the two models have different behavior. I’m curious if this will be reflected on Search Arena . ## [Steam Engine Time](https://samek.fyi/steam-engine-time/) _2025-04-27 · samek.fyi_ o3 and gemini 2.5 pro being a single Elo point apart on LMArena with style control feels very steam-engine time . There’s an idea in the science-fiction community called steam-engine time, which is what people call it when suddenly twenty or thirty different writers produce stories about the same idea. It’s called steam-engine time ­because nobody knows why the steam engine happened when it did.… ## [Perplexity Is Still Better at Quick Searches](https://samek.fyi/perplexity-better-at-quick-searches/) _2025-04-25 · samek.fyi_ Simon Willison writes that “AI assisted search-based research actually works now.” o3 and o4-mini agentic research is truly impressive, as are ChatGPT’s and Gemini’s Deep Research. But I consistently find queries where Perplexity gets it right, and ChatGPT and Gemini get it wrong. An example: “how is chatgpt-4o-latest different from gpt-4o.” Only Perplexity… ## [Marketing Emails](https://dhariri.com/2025/marketing-emails) _2025-04-14 · David Hariri_ ## [Claude Plays Factorio](https://dhariri.com/2025/claude-plays-factorio) _2025-03-11 · David Hariri_ Jack Hopkins tests LLMs in his 'FLE' - Factorio Learning Environment. ## [On Testing](https://dhariri.com/2025/testing) _2025-03-10 · David Hariri_ A few lessons I've learned about testing code while building Ada ## [Why I Blog](https://dhariri.com/2025/why-i-blog) _2025-03-09 · David Hariri_ A short post about why I write on the web ## [Moving Back to Static](https://dhariri.com/2025/back-to-ssg) _2025-02-17 · David Hariri_ This site is now served via SSG (static-site generation) on Netlify. ## [The TTC](https://dhariri.com/2025/the-ttc) _2025-01-31 · David Hariri_ A rant about my growing concerns over safety while using the TTC. ## [How AI Took Over The World](https://dhariri.com/2025/art-of-the-problem-how-ai-took-over-the-world) _2025-01-16 · David Hariri_ Learn about artificial intelligence with Brit from 'Art of the Problem,' who excels in creating engaging and educational videos. ## [Experimenting with Replacing Flask with Quart](https://dhariri.com/2025/experimenting-with-replacing-flask-with-quart) _2025-01-10 · David Hariri_ Exploring the benefits of switching from Flask to Quart for improved performance and asynchronous capabilities in Ada's application. ## [Interview with Rene Haas](https://dhariri.com/2024/interview-with-rene-haas) _2024-12-25 · David Hariri_ Insights from a podcast about the impact of RISC vs CISC in chip production and how giants like Apple and Amazon have shaped the landscape. ## [Is Reasoning Language?](https://dhariri.com/2024/is-reasoning-language) _2024-12-17 · David Hariri_ Exploring the nature of reasoning in AI models, questioning if making LLMs express their thoughts out loud limits their potential. ## [Tartvillain](https://dhariri.com/2024/tartvillain) _2024-12-16 · David Hariri_ Enjoyed a unique tart experience with Tartvillain, hand served by the creator Carlos. ## [Bluesky](https://dhariri.com/2024/bluesky) _2024-12-13 · David Hariri_ Updated my site so posts also share on Bluesky. Considering using Bluesky for comments inspired by Emily Liu's approach. ## [10,000 Stars for Every Grain of Sand](https://dhariri.com/2024/for-every-grain-of-sand-on-every-beach-on-earth-there-are) _2024-12-04 · David Hariri_ Tim Urban's quote illustrates the vastness of the universe, with 10,000 stars for every grain of sand on Earth. ## [Knowledge Search Improvements](https://dhariri.com/2024/knowledge-search-improvements) _2024-11-16 · David Hariri_ Significant improvements to Ada's knowledge retrieval enhance customer support accuracy, thanks to innovative team collaboration and ML advances. ## [Only one LLM is good at chess](https://dhariri.com/2024/only-one-llm-is-good-at-chess) _2024-11-16 · David Hariri_ Exploring how different LLMs perform at chess, with most failing except turbo-instruct. Discusses tuning and training influences. ## [The Wood Frog](https://dhariri.com/2024/the-wood-frog) _2024-11-15 · David Hariri_ Exploring the miraculous adaptation of the wood frog, which survives winter by freezing like a stone but remains alive.