dmesg --follow
[ 68662260.000 ] posts.x: Full talk on turning re-prompted fixes into linters, including the OpenAPI drift fix and the skill-writing whack-a-mole: |
[ 68662260.000 ] posts.x: Re-prompting an agent to fix the same sloppy pattern over and over isn't a workflow, it's a sign the rule should live in code, not in your head… |
[ 68650020.000 ] posts.x: ↻ @willcb: me: kinda fucked up how many people are offloading their whole lives to muse or instinct or grokbot or whatever claude: yeah |
[ 68650020.000 ] posts.x: ↻ @iamdevloper: signs you've become the senior dev: you're the only one who understands the deploy script you're the only one who remembe… |
[ 68649720.000 ] posts.x: Gooooooooood morning! Brazil Oberon Cerrado. Roasted 110 seconds past first crack. Milk chocolate and almond. |
[ 68647800.000 ] posts.x: @Saanvi_dhillon “Git expert” is a weird flex, though, isn’t it? |
[ 68610720.000 ] posts.x: @sujee_dev @dkundel @aiDotEngineer Thanks mate! |
[ 68600580.000 ] posts.x: Full talk on the Codex app server protocol and what you can build on top of the Codex harness: |
[ 68600580.000 ] posts.x: A lot of engineers assume building their own agent interface means writing their own agent harness from scratch. @dkundel, Developer Experience Lead… |
[ 68564580.000 ] posts.x: Full talk on why Reducto deleted their all-in-one MCP server and rebuilt it around fewer, state-aware tools and visible agent uncertainty: |
[ 68564580.000 ] posts.x: A single massive MCP file worked fine as a curated demo and broke the moment Reducto's own team got hold of it. @abhiarya, who works on product… |
[ 68510880.000 ] posts.x: Full talk on turning a memory graph into governed, executable skills: |
[ 68510880.000 ] posts.x: Agents that finish a task successfully and then forget everything about it are stuck in what @lyonwj, a Product Manager at Neo4j, calls an amnesiac… |
[ 68429340.000 ] posts.x: Full talk on distilling successful and failed agent runs into reusable skills: |
[ 68429340.000 ] posts.x: A Chromium fork running inside AWS Lambda succeeded 36% of the time, not exactly production ready. @rafalwilinski, founding engineer at Runlayer… |
[ 68662260.000 ] posts.x: Full talk on turning re-prompted fixes into linters, including the OpenAPI drift fix and the skill-writing whack-a-mole: |
[ 68662260.000 ] posts.x: Re-prompting an agent to fix the same sloppy pattern over and over isn't a workflow, it's a sign the rule should live in code, not in your head… |
[ 68650020.000 ] posts.x: ↻ @willcb: me: kinda fucked up how many people are offloading their whole lives to muse or instinct or grokbot or whatever claude: yeah |
[ 68650020.000 ] posts.x: ↻ @iamdevloper: signs you've become the senior dev: you're the only one who understands the deploy script you're the only one who remembe… |
[ 68649720.000 ] posts.x: Gooooooooood morning! Brazil Oberon Cerrado. Roasted 110 seconds past first crack. Milk chocolate and almond. |
[ 68647800.000 ] posts.x: @Saanvi_dhillon “Git expert” is a weird flex, though, isn’t it? |
[ 68610720.000 ] posts.x: @sujee_dev @dkundel @aiDotEngineer Thanks mate! |
[ 68600580.000 ] posts.x: Full talk on the Codex app server protocol and what you can build on top of the Codex harness: |
[ 68600580.000 ] posts.x: A lot of engineers assume building their own agent interface means writing their own agent harness from scratch. @dkundel, Developer Experience Lead… |
[ 68564580.000 ] posts.x: Full talk on why Reducto deleted their all-in-one MCP server and rebuilt it around fewer, state-aware tools and visible agent uncertainty: |
[ 68564580.000 ] posts.x: A single massive MCP file worked fine as a curated demo and broke the moment Reducto's own team got hold of it. @abhiarya, who works on product… |
[ 68510880.000 ] posts.x: Full talk on turning a memory graph into governed, executable skills: |
[ 68510880.000 ] posts.x: Agents that finish a task successfully and then forget everything about it are stuck in what @lyonwj, a Product Manager at Neo4j, calls an amnesiac… |
[ 68429340.000 ] posts.x: Full talk on distilling successful and failed agent runs into reusable skills: |
[ 68429340.000 ] posts.x: A Chromium fork running inside AWS Lambda succeeded 36% of the time, not exactly production ready. @rafalwilinski, founding engineer at Runlayer… |