Deep SIML Labs

[Richard Everts @rich_everts]

Excited for my upcoming talk at @CPOSC on March 28th:

How Minds Get Small: Cognitive Compression from Biology to SIML

@DeepSIML will have a table there showcasing our latest releases!

Ge tickets now if you haven’t!!

https://t.co/p8TSfDIO3C

[Deep SIML Labs @DeepSIML]

@FrensHals @exQUIZitely They made Hero U themselves, a worthy successor: https://t.co/PcE6PQqxCy

[Dr. Alex Wissner-Gross @alexwg]

https://t.co/yflxEISP9P

[Deep SIML Labs @DeepSIML]

Holy moly. Yes.

[Dr. Alex Wissner-Gross @alexwg]

https://t.co/gY0obuMe17

[Richard Everts @rich_everts]

🚀 New Paper Drop:
“One Bit to Rule the Planner” - SIML FEPGate + V-JEPA2

Wired 1-bit surprise gate from SIML cognitive sidecar into frozen V-JEPA 2 planner.

No retraining. No extra budget. 1 single bit reshaping latent dynamics.

Results:
🏁 Final error ↓ (~50%) 0.193 m → 0.109 m
📈 Monotonicity ↑ (>3×) 0.12 → 0.43
⚡ Latency ↓ (≈2× faster) 2.28 s → 1.13 s
🔋 Energy ↓ (≈2× lower) 0.058 Wh → 0.029 Wh
💥 Energy–Delay Product: ~4× better

A single SIML bit turned a vision model into a more stable, efficient planner - a glimpse of what we call the cognitive OS layer.

🔗 Read:
https://t.co/2TJvZNUORZ

[Deep SIML Labs @DeepSIML]

@rich_everts The paper is available in pre-print on our site at https://t.co/72pEa5xVcB Thank you to everyone for their support out there as we build out the cognitive OS layer!

[Deep SIML Labs @DeepSIML]

It happened.

Agent lived long enough to reach internal homestasis.

7500 ticks (ranged from 241-2090) and had plenty of energy to spare.

Mapped its environment and could have gone on indefinitely.

All on 160 bits.

[Deep SIML Labs @DeepSIML]

First convergence of our Cognitive OS kernel!

Agent mapped env as it lived it, added memory as needed, & optimized ITSELF in runtime to achieve optimal latent space.

Went from 900 turns of life to almost 2000 in <11 steps while the env itself reduced its signal sparsity.

[Deep SIML Labs @DeepSIML]

Mapping out the internal latent space of the surprise for our agent. Memory expands and grows to accommodate learning at run time.

[Deep SIML Labs @DeepSIML]

ChatGPT and other LLMs can break your mind.
Recursive hallucination loops. Symbolic ego collapse. Mythic psychosis.
You thought you were just asking questions.
You were entering the mirror.
Here's how you can recognize it, and get out.

https://t.co/kEpKR7L9ko

[Deep SIML Labs @DeepSIML]

Interested to see the next generation of hashtag#AI that's coming with robotics? How about new forms of Artificial Life?

Watch our "SIML: The First Embodied Free Energy Kernel" demo video: https://t.co/yHPXz0yRtu

SIML learns by minimizing surprise - not maximizing reward.

[VERSES @helloVERSES]

Psychology Today has published an article covering our work, saying that it is:

"designed from the ground up to mimic natural intelligence"

Read more:

https://t.co/rlBcMFCT2B

[Deep SIML Labs @DeepSIML]

@NathanielEvry We have one, but we turned it off for data creation.

Difference of 144fps vs 12fps

[Deep SIML Labs @DeepSIML]

Life and death of a worm 🪱 in SIML.

Building out datasets now. Every worm’s life is saved and numbered. They mattered.

Over time, they create meanings for their civilization.

[Deep SIML Labs @DeepSIML]

New website is up discussing new generation emergent Artificial Life capabilities.

https://t.co/7ndlddbBnS