🔄 In a Training Loop

i64 Systems PRO

i64systems

4 4

·

https://bob-talk.org/

i64systems

AI & ML interests

deterministic, auditable local AI · integer/low-bit ML · memory systems

Recent Activity

posted an update about 1 month ago

we taught a small model to predict how simulated fluid would move eight steps into the future. it learned from examples, then succeeded on examples withheld from training. two things mattered: - its memory helped. the version with an internal memory produced about 41–45% less prediction error than the comparison model using recent observations. - the learning was repeatable. restarting training reproduced every recorded update and saved checkpoint exactly. resuming halfway through also produced the same ending. that gives us working evidence that bf16 gpu training can learn and remain exactly repeatable on this 3090 ti and software setup. thank you for your time.

posted an update about 1 month ago

little bob’s updated weights now change his actions in doom. all three fresh replays matched exactly yes i am training my bf16/fp32 non-language models weights with replayable inference *in doom*

upvoted a paper about 1 month ago

Falsifiable Release Gates for Self-Improving Systems

View all activity

Organizations

upvoted 2 papers about 1 month ago

Falsifiable Release Gates for Self-Improving Systems

Paper • 2607.13070 • Published Jul 11 • 2

Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models

Paper • 2608.30751 • Published Sep 1 • 4

upvoted a collection about 1 month ago

byte-exact local AI

behold: obsession with determinism • 3 items • Updated Sep 4 • 1

upvoted an article about 1 month ago

Article

NVMe + ??? = Giant MoE's in Residency?

i64systems

•

Sep 2

• 1