dmesg --follow

[ 67402020.000 ] posts.x: Full talk on why dashboards are dying and what agents need instead: | [ 67402020.000 ] posts.x: Six months of using Datadog every day, then one frozen moment standing in front of it while a coworker watched, is the origin story behind a talk… | [ 67393080.000 ] posts.x: Full talk on why massive codebases are decaying under AI-generated code, and what Sourcegraph built to patch at repo scale: | [ 67393080.000 ] posts.x: A tech leader at one of the top 10 US banks sums up the scale problem in one line: sure, an agent can make the change, but there are 90,000… | [ 67376340.000 ] posts.x: The Level 2 review method is detailed in my @aiDotEngineer NYC talk. To learn more about how to rely on the work your agents do, read here: | [ 67376340.000 ] posts.x: Word to the wise: if you're consuming agent skills from any of these "skills hubs", NEVER raw-dog any of those skills! Have your agent, in cautious… | [ 67369680.000 ] posts.x: Meta are back at it! | [ 67364940.000 ] posts.x: Full talk on cache-aware routing, speculative decoding, KV cache offloading, and disaggregated prefill/decode: | [ 67364940.000 ] posts.x: Open models have closed most of the intelligence gap with proprietary ones, according to a benchmark from Artificial Analysis, but closing that gap… | [ 67357440.000 ] posts.x: Full talk on how VS Code's team ships weekly instead of monthly, from code survival metrics to automated error-to-PR pipelines: | [ 67357440.000 ] posts.x: One metric decided whether VS Code's team could trust agent-written code: how much of it actually survives into a commit. @digitarald, a Principal… | [ 67312020.000 ] posts.x: @maxjendrall /design is alive and well, and it’s better than the web preview version. | [ 67100100.000 ] posts.x: Am I in the minority using Sol as my daily driver in Codex? | [ 67097280.000 ] posts.x: Full talk on why MCP's context problems are a harness issue, not a protocol issue, and what MCPC does about it: | [ 67097280.000 ] posts.x: A lot of the AI world spent the past year calling MCP dead, Anthropic included, with Theo, Gary Tan, and Peter Levels all piling on, even as MCP… |

[ 67402020.000 ] posts.x: Full talk on why dashboards are dying and what agents need instead: | [ 67402020.000 ] posts.x: Six months of using Datadog every day, then one frozen moment standing in front of it while a coworker watched, is the origin story behind a talk… | [ 67393080.000 ] posts.x: Full talk on why massive codebases are decaying under AI-generated code, and what Sourcegraph built to patch at repo scale: | [ 67393080.000 ] posts.x: A tech leader at one of the top 10 US banks sums up the scale problem in one line: sure, an agent can make the change, but there are 90,000… | [ 67376340.000 ] posts.x: The Level 2 review method is detailed in my @aiDotEngineer NYC talk. To learn more about how to rely on the work your agents do, read here: | [ 67376340.000 ] posts.x: Word to the wise: if you're consuming agent skills from any of these "skills hubs", NEVER raw-dog any of those skills! Have your agent, in cautious… | [ 67369680.000 ] posts.x: Meta are back at it! | [ 67364940.000 ] posts.x: Full talk on cache-aware routing, speculative decoding, KV cache offloading, and disaggregated prefill/decode: | [ 67364940.000 ] posts.x: Open models have closed most of the intelligence gap with proprietary ones, according to a benchmark from Artificial Analysis, but closing that gap… | [ 67357440.000 ] posts.x: Full talk on how VS Code's team ships weekly instead of monthly, from code survival metrics to automated error-to-PR pipelines: | [ 67357440.000 ] posts.x: One metric decided whether VS Code's team could trust agent-written code: how much of it actually survives into a commit. @digitarald, a Principal… | [ 67312020.000 ] posts.x: @maxjendrall /design is alive and well, and it’s better than the web preview version. | [ 67100100.000 ] posts.x: Am I in the minority using Sol as my daily driver in Codex? | [ 67097280.000 ] posts.x: Full talk on why MCP's context problems are a harness issue, not a protocol issue, and what MCPC does about it: | [ 67097280.000 ] posts.x: A lot of the AI world spent the past year calling MCP dead, Anthropic included, with Theo, Gary Tan, and Peter Levels all piling on, even as MCP… |

~/pages/about.md -rw-r--r-- 121 words 2026-10-05

Heya! I'm Corey.

I build AI-native businesses at Rexmore. I'm also an artisan of specialty coffee and a pickleball fanatic.

I serve on the boards of companies and non-profit organizations. I'm a frequent speaker and writer on topics in artificial intelligence, technology and business.

I've been busy in my personal projects:

corey@gallon.me:~$ du -sh ~/.agents/2026

108.31

tokens through agents this year.

~2.7 B weekly analyzed from session telemetry data, through Oct 11

I did other stuffs before this:

Founding faculty and Adjunct Professor of Graduate Machine Learning at a university in Chicago
Chief Innovation Officer of the commercial technology business at a large consulting firm
Partner and Head of Finance at a Wall Street FinTech company

I share insights from the frontiers of AI engineering. You should subscribe to my newsletter. It's an email sent when I have something worthwhile sending. Replies are encouraged!

corey@gallon.me:~$ tail -f /writing Attach to the stream. An email when I have something worth sending. Replies encouraged!