🔄 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 3 hours 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 1 day 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 3 days ago

Falsifiable Release Gates for Self-Improving Systems

View all activity

Organizations

Posts 4

Post

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.