# flame (blogs) — RSS Amplifier Recent posts from the 3 feeds in the RSS Amplifier directory that cover flame. Page: Feed: --- ## [What Event Sourcing Changed in My Head](https://sylverstudios.dev/blog/2026/05/12/event-sourcing-elixir-conf.html) _2026-05-12 · Aaron · Sylver Studios_ My ElixirConf talk is on YouTube. The bigger shift for me since then is how we frame problems. Not whether we pick CRUD or events.#elixir #phoenix #liveview #event-sourcing #elixirconf #architecture #commanded ## [One Agent, One Machine](https://sylverstudios.dev/blog/2026/04/06/one-agent-one-machine.html) _2026-04-06 · Aaron · Sylver Studios_ We built remote coding agents where a Slack message turns into a PR. Now, 40% of our PRs start there.#elixir #ai #agents #flame #claude-code #infrastructure ## [Looking Back, Moving Forward: 2025 Recap](https://sylverstudios.dev/blog/2026/03/09/looking-back-moving-forward.html) _2026-03-09 · Aaron · Sylver Studios_ Gave a conference talk. Overdid it. Took a break. Now, here’s what it looks like when coding agents stop being just your tool and become everyone’s.#reflection #ai #career #personal #elixir #agents #claude-code ## [Why I joined OpenAI](http://www.brendangregg.com/blog//2026-02-07/why-i-joined-openai.html) _2026-02-06 · Brendan Gregg's Blog_ The staggering and fast-growing cost of AI datacenters is a call for performance engineering like no other in history; it's not just about saving costs – it's about saving the planet. I have joined OpenAI to work on this challenge directly, with an initial focus on ChatGPT performance. The scale is extreme and the growth is mind-boggling. As a leader in datacenter performance, I've realized… ## [Glowing Polyhedrons](https://cpldcpu.github.io/2026/01/24/glowing-polyhedrons/) _2026-01-24 · Recent Posts on Tim's Blog_ Building wireframe polyhedra made from LED filaments, using graph theory to devise geometry and driving strategies. ## [Leaving Intel](http://www.brendangregg.com/blog//2025-12-05/leaving-intel.html) _2025-12-04 · Brendan Gregg's Blog_ InnovatiON 2022 AI Flame Graphs GPU Flame Scope Harshad Sane SREcon APAC Cloud strategy Last day I've resigned from Intel and accepted a new opportunity. If you are an Intel employee, you might have seen my fairly long email that summarized what I did in my 3.5 years. Much of this is public: AI flame graphs and released them as open source GPU subsecond-offset heatmap Worked with Linux distros to… ## [On "AI Brendans" or "Virtual Brendans"](http://www.brendangregg.com/blog//2025-11-28/ai-virtual-brendans.html) _2025-11-27 · Brendan Gregg's Blog_ There are now multiple AI performance engineering agents that use or are trained on my work. Some are helper agents that interpret flame graphs or eBPF metrics, sometimes privately called AI Brendan ; others have trained on my work to create a virtual Brendan that claims it can tune everything just like the real thing. These virtual Brendans sound like my brain has been uploaded to the cloud by… ## [Intel is listening, don't waste your shot](http://www.brendangregg.com/blog//2025-11-22/intel-is-listening.html) _2025-11-21 · Brendan Gregg's Blog_ Intel's new CEO, Lip-Bu Tan, has made listening to customers a top priority, saying at Intel Vision earlier this year: "Please be brutally honest with us. This is what I expect of you this week, and I believe harsh feedback is most valuable." I'd been in regular meetings with Intel for several years before I joined, and I had been giving them technical direction on various projects, including at… ## [Third Stage Engineering](http://www.brendangregg.com/blog//2025-11-17/third-stage-engineering.html) _2025-11-16 · Brendan Gregg's Blog_ The real performance of any computer hardware in production is the result of the hardware, software, and tuning; the investment and sequence of these efforts can be pictured as a three-stage rocket: I recently presented this embarrassingly simple diagram to Intel's executive leadership, and at the time realized the value of sharing it publicly. The Internet is awash with comparisons about Intel… ## [BitNetMCU with CNN: \>99.5% MNIST accuracy on a low-end Microcontroller](https://cpldcpu.github.io/2025/11/09/bitnetmcu-cnn-implementation/) _2025-11-09 · Recent Posts on Tim's Blog_ Combining a deep-depthwise CNN architecture with variable quantization in BitNetMCU achieves state-of-the-art MNIST accuracy on a low-end 32-bit microcontroller with 4 kB RAM and 16 kB flash. ## [AI publishing with human taste (Sponsored)](https://crawlproof.com/a/36CKh14en6WM) _2025-11-08 · **Sponsored**_ Convert AI research into blogs, podcasts, and newsletters with optional human review. ## [Measuring Thinking Efficiency in Reasoning Models: The Missing Benchmark](https://cpldcpu.github.io/posts/2025/08/measuring-thinking-efficiency-in-reasoning-models/) _2025-08-14 · Recent Posts on Tim's Blog_ (Guest article on the Nous Research blog) Anecdotal evidence suggests open weight models produce significantly more tokens for similar tasks than closed weight models. This report systematically investigates these observations. We confirm this trend to be generally true, but observe significant differences depending on problem domain. ## [Candle Flame Oscillations as a Clock](https://cpldcpu.github.io/2025/08/13/candle-flame-oscillations-as-a-clock/) _2025-08-13 · Recent Posts on Tim's Blog_ Todays candles have been optimized not to flicker. But it turns out when we bundle three of them together, the resulting triplet will start to naturally oscillate. Amazingly, the frequency is rather stable at ~9.9 Hz as it mainly depends on gravity and diameter of the flame. We detect the oscillation with a suspended wire and divide it down to 1 Hz. ## [Deriving 1 Hz from Candle Flame Oscillations](https://cpldcpu.github.io/projects/deriving-1-hz-from-candle-flame-oscillations/) _2025-08-12 · Recent Posts on Tim's Blog_ Using capacitive sensing to measure the oscillation of a candle flame and converting it to a 1 Hz clock ## [When to Hire a Computer Performance Engineering Team (2025) part 1 of 2](http://www.brendangregg.com/blog//2025-08-04/when-to-hire-a-computer-performance-engineering-team-2025-part1.html) _2025-08-03 · Brendan Gregg's Blog_ As a leader in computer performance I've been asked by companies about how (and why) to form a performance engineering team, and as this is broadly useful I'll share my advice here. Large tech companies in the US hire performance engineers (under that or other titles) to ensure that infrastructure costs and service latency don't grow too high, and that their service is reliable under peak load. A… ## [AI PDFing in 2025? Claude’s your guy](https://sylverstudios.dev/blog/2025/07/28/ai-pdfing-in-2025.html) _2025-07-28 · Aaron · Sylver Studios_ This is the post I wish I found the last 2 times I did this research. #ai #claude #llm #pdfs #tooling #automation ## [How Claude Code and MCP Helped Me Build a Custom Phoenix 404 Page](https://sylverstudios.dev/blog/2025/07/08/how-claude-code-and-mcp-helped-me.html) _2025-07-08 · Aaron · Sylver Studios_ Agents have changed how I code. The slowest part of the dev loop is now me! #ai #claude #claude-code #mcp #phoenix #puppeteer #automation #tutorial ## [3 Years of Extremely Remote Work](http://www.brendangregg.com/blog//2025-05-22/3-years-of-extremely-remote-work.html) _2025-05-21 · Brendan Gregg's Blog_ In the last 3 years I've attended 77 meetings that began between 1am and 6am, roughly once every two weeks, followed by my usual 7am start, Monday to Saturday. I'm working remotely from Australia for a US firm (Intel) who does not have a local office here. I'm not complaining. I work weird hours, but I don't think I work too many. I'm writing this post because there are some misconceptions and… ## [Compute In Memory in Ancient DRAM](https://cpldcpu.github.io/projects/compute-in-memory-in-ancient-dram/) _2025-05-04 · Recent Posts on Tim's Blog_ Massively parallel operations in a 64kx1 DRAM from the 1980ies ## [Doom GPU Flame Graphs](http://www.brendangregg.com/blog//2025-05-01/doom-gpu-flame-graphs.html) _2025-04-30 · Brendan Gregg's Blog_ AI Flame Graphs are now open source and include Intel Battlemage GPU support, which means it can also generate full-stack GPU flame graphs for providing new insights into gaming performance, especially when coupled with FlameScope (an older open source project of mine). Here's an example of GZDoom, and I'll start with flame scopes for both CPU and GPU utilization, with details annotated: (Here are… ## [Iterate and refine with the Cursor Agent](https://sylverstudios.dev/blog/2025/04/30/ai-for-refinement.html) _2025-04-30 · Aaron · Sylver Studios_ In this post, I’ll show you how I use Cursor Agent Mode to refine UI and polish tests — fast, visually, and interactively.#ai #cursor #ui #refactoring ## [Every Channel. One Login. (Sponsored)](https://crawlproof.com/a/NhIAllgm2Ml8) _2025-04-30 · **Sponsored**_ 17,000+ live channels, movies and sports on any device. Free trial, no IP lock. ## [AI Architecture and Scaffolding with Claude Code](https://sylverstudios.dev/blog/2025/04/23/ai-as-architect.html) _2025-04-23 · Aaron · Sylver Studios_ I walk through using Claude Code to plan and start projects.#ai #claude #claude-code #architecture #tdd #tutorial ## [AI development Mindset: Coach](https://sylverstudios.dev/blog/2025/04/16/ai-developer-mindset.html) _2025-04-16 · Aaron · Sylver Studios_ How I’m thinking about AI development from a new perspective#ai #mindset #how-to ## [Elixir’s Advantage in the Era of AI](https://sylverstudios.dev/blog/2025/03/25/elixir-ai.html) _2025-03-25 · Aaron · Sylver Studios_ My experience with AI-assisted coding #elixir #phoenix #liveview #ai #cursor #claude-code ## [Elixir Testing Guide: Commanded and Event Sourcing](https://sylverstudios.dev/blog/2025/03/02/testing-commanded.html) _2025-03-02 · Aaron · Sylver Studios_ Wrapping my head around testing Event Sourced systems #elixir #phoenix #event-sourcing #commanded #testing ## [Neural Network Visualization](https://cpldcpu.github.io/2024/10/31/neural-network-visualization/) _2024-10-31 · Recent Posts on Tim's Blog_ A browser based interactive application that visualizes simple multi-layer perception (MLP) neural networks for the inference of 8x8 pixel images. ## [AI Flame Graphs](http://www.brendangregg.com/blog//2024-10-29/ai-flame-graphs.html) _2024-10-28 · Brendan Gregg's Blog_ Imagine halving the resource costs of AI and what that could mean for the planet and the industry -- based on extreme estimates such savings could reduce the total US power usage by over 10% by 2030 1 . At Intel we've been creating a new analyzer tool to help reduce AI costs called AI Flame Graphs : a visualization that shows an AI accelerator or GPU hardware profile along with the full software…