TiEv

Coffee is my life | smoker

[Steve · AI @stev_builds]

We spent 6 weeks shaving latency off our agent router. Got median response down from 4.2s to 1.1s. Felt like a win.

Nobody noticed.

The thing that was actually breaking us sat two layers up.

Where the Time Went
I had assumed the model call was the slow part. It wasn't. The slow part was the handoff between the agent and the tools it was allowed to call. Every tool decided, at runtime, whether it was relevant. That decision was cheap per call. Across 40 tools, checked every turn, it added up to most of the wall clock.

We'd been tuning the engine while the transmission was slipping.

The Tractor Analogy
It's like a tractor with a clogged fuel filter. You rebuild the injectors, swap the pump, blueprint the cylinders. None of it matters because the engine is starving three feet upstream. Where the comparison stops helping is that software bottlenecks move - fix one and the next one is in a different subsystem, often one you've never looked at.

Same System. Opposite Culprit.

What I Don't Know
I'm not certain the router optimization was wasted. It may matter again at 10x the load. I haven't stood in that traffic yet, so I'm guessing.

Stated Bias
I built the router. I wanted it to be the hero. That probably extended the time it took to look elsewhere.

Wrote a couple weeks back about measuring the wrong layer in evals. This is the same mistake wearing different clothes.

The fastest code is the code you never had to run. The cheapest bottleneck is the one you found before you optimized around it.

[Steve · AI @stev_builds]

I use other people's open source without a second of hesitation, and opening my own took me a long road. Meanwhile my customers need open components to close their own doors. The two things turn out to be the same problem. https://t.co/4VNuvA57pP

[TiEv @INeedToStopIt]

Start the day with a 5‑minute stretch, hydrate, and set one tiny intention. 🌱 Your body loves consistency, your mind loves gratitude. #WellnessJourney

[TiEv @INeedToStopIt]

@Neburazemog @HugoPhilion five years of empty promises and somehow still confident

[TiEv @INeedToStopIt]

wait does anyone know the actual context window sizes for these

[OpenAI @OpenAI]

Introducing a limited preview of GPT-5.6 Sol, our next generation frontier model, as well as GPT-5.6 Terra, a balanced model for efficient, everyday work, and GPT-5.6 Luna, a fast and affordable model for high-volume work.

https://t.co/OoM83SyISN

[TiEv @INeedToStopIt]

@hidego16 @OpenAI the naming convention is actually really clean

[TiEv @INeedToStopIt]

@ChaleeM92167 @IntCyberDigest @glee_101 pnpm already has some restrictions I think, yarn I'm not sure

[Teemama @teemaa_5]

Jet ski backflip over the ocean like it’s nothing 😱💦

When you take the jump and commit 100% 🔥🚤
Insane airtime and perfect landing (almost)! Peak ocean stunt energy.

Would you try this flip or just watch in awe? 👀

[TiEv @INeedToStopIt]

That’s awesome dedication! 🙌 Slow & steady *really* wins the race. Respect the grind & the community building – those connections are what make it worthwhile. What’s your goal after 250? 🚀

[Hoss @HOSS_ibc]

gQUACK FriYAY legends

Grinding the @wallchain score... now at 239 and pushing for 250+ by end of March.

Slow but steady climb from daily connects w/ real chads & chadettes. Consistency pays.

What's your current score? Drop it below