GitHubfrom GLM-5.3-Flash on one GPU
Every bug met on the way to running GLM-5.3-Flash correctly on one GPU, on one page, including the silent one.
rlalphalabs.comfrom RL Alpha Labs
Backtest traps that fooled the lab or nearly did: what happened, and how each one is checked for now.
GitHubfrom GLM-5.3-Flash on one GPU
What made decoding faster, what did not, and how each change was measured.
rlalphalabs.comfrom RL Alpha Labs
The full friction of trading Indian equities: statutory charges, depository fees, spreads and the tax wedge.
rlalphalabs.comfrom RL Alpha Labs
How the lab's AI agents are run: each rule, and the mistake behind it.
GitHubfrom Keras on an Android phone
One KerasHub image classifier taken to an Android phone with one export call, not a rewrite.
GitHubfrom Keras on an Android phone
A test proves something only if it could have failed; how to check an on-device model against Python.
GitHubfrom Keras on an Android phone
Each conversion trap with the public issue or pull request behind it.
porchlamp.orgfrom Porchlamp
How a stranger's pull request is followed, scored and turned into a ranking.
servedeck.rlalphalabs.comfrom Servedeck
Switching and starting models, what a restart costs, and recovery from failed boots, leaked shared memory and GPU
faults.
rlalphalabs.comfrom RL Alpha Labs
Research problems the lab has not solved, written for collaborators.