[ 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…  |   [ 67037100.000 ] posts.x: @TheZachMueller Nice one! That’s a warm room, just in time for winter.  |   [ 67035060.000 ] posts.x: Full talk on turning scattered engineering judgment, feature-flag agent included, into something a coding agent can actually use:  |   [ 67035060.000 ] posts.x: A team held a recurring meeting every two weeks for one purpose: deleting feature flags nobody needed anymore. @aorobator, a Senior Software Engineer…  |  

[ 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…  |   [ 67037100.000 ] posts.x: @TheZachMueller Nice one! That’s a warm room, just in time for winter.  |   [ 67035060.000 ] posts.x: Full talk on turning scattered engineering judgment, feature-flag agent included, into something a coding agent can actually use:  |   [ 67035060.000 ] posts.x: A team held a recurring meeting every two weeks for one purpose: deleting feature flags nobody needed anymore. @aorobator, a Senior Software Engineer…  |