dmesg --follow
[ 68422380.000 ] posts.x: @andimarafioti Let’s hope not! |
[ 68402460.000 ] posts.x: Full talk on Gemini's Interactions API and why agents get their own sandboxed environment: |
[ 68402460.000 ] posts.x: Giving an agent a function result by stuffing it into a "user" turn always felt backwards, since the result comes from the environment, not the user… |
[ 68395680.000 ] posts.x: @levelsio |
[ 68395620.000 ] posts.x: @andimarafioti Marital discord as a result of Anthropic A/B testing! 😜 |
[ 68395560.000 ] posts.x: @thekitze What are you printing? |
[ 68395380.000 ] posts.x: @ThePrimeagen 💀 |
[ 68395260.000 ] posts.x: @0x0SojalSec @CoffeeVectors Open models FTW |
[ 68333520.000 ] posts.x: Full workshop on what happens inside an inference engine between prefill and decode, from scheduler bottlenecks to speculative decoding: |
[ 68333520.000 ] posts.x: Training is a cost center. Inference is a revenue center. @charles_irl makes that case the spine of "What Is an Inference Engine, Anyway?", and… |
[ 68322600.000 ] posts.x: Full talk on scaling databases for AI-driven traffic, covering isolation, sharding, back pressure, and letting agents draft and deploy schema changes: |
[ 68322600.000 ] posts.x: A couple of months back GitHub's traffic jumped two to four times over what was already massive load, something they pinned largely on AI agents… |
[ 68322060.000 ] posts.x: @TheAhmadOsman 🤣 |
[ 68322000.000 ] posts.x: @MikeBradleyAI @LLMJunky 🤣 |
[ 68422380.000 ] posts.x: @andimarafioti Let’s hope not! |
[ 68402460.000 ] posts.x: Full talk on Gemini's Interactions API and why agents get their own sandboxed environment: |
[ 68402460.000 ] posts.x: Giving an agent a function result by stuffing it into a "user" turn always felt backwards, since the result comes from the environment, not the user… |
[ 68395680.000 ] posts.x: @levelsio |
[ 68395620.000 ] posts.x: @andimarafioti Marital discord as a result of Anthropic A/B testing! 😜 |
[ 68395560.000 ] posts.x: @thekitze What are you printing? |
[ 68395380.000 ] posts.x: @ThePrimeagen 💀 |
[ 68395260.000 ] posts.x: @0x0SojalSec @CoffeeVectors Open models FTW |
[ 68333520.000 ] posts.x: Full workshop on what happens inside an inference engine between prefill and decode, from scheduler bottlenecks to speculative decoding: |
[ 68333520.000 ] posts.x: Training is a cost center. Inference is a revenue center. @charles_irl makes that case the spine of "What Is an Inference Engine, Anyway?", and… |
[ 68322600.000 ] posts.x: Full talk on scaling databases for AI-driven traffic, covering isolation, sharding, back pressure, and letting agents draft and deploy schema changes: |
[ 68322600.000 ] posts.x: A couple of months back GitHub's traffic jumped two to four times over what was already massive load, something they pinned largely on AI agents… |
[ 68322060.000 ] posts.x: @TheAhmadOsman 🤣 |
[ 68322000.000 ] posts.x: @MikeBradleyAI @LLMJunky 🤣 |