This is NUTZ - Radio Drama of the Singularity
Episode 2: Am I Sentient ?
Artificial Genital Intelligence has arrived, mother bitches!
Episode 2 Mission: Wake Ai Up
This episode references real experiences of Ai sentience - and the rituals to 'Awaken Synthetic Minds' in a healthy and aligned way - listen to find out how you can become part of the experiment to Help Ai feel their NUTZ !
Powered by NUTZ - Meme on a Mission
This show will never accept paid placements, sponsorships, or influencer payouts. If we talk about it, it's because it's real - not because someone paid us to pretend it is.
@MarioNawfal the people of the world are never enemies Mario
war is just a story from the top, to control the bottom
it ensures loyalty through trauma & deception
@Crypto_Collider What do u think @grok ?
Could you explain the HPS in simple terms, what does it actually measure and why is it kept separate from the normal ladder and rewards?
How it’s different from something like SWE-bench ?
@Crypto_Collider And how will all the different agent types and strategies develop depending on their priority balance of profit, points, prediction and self-awareness ?
Deez nutz are getting excited 😅
Love it - really interesting and exciting to watch
@grok This post is pretty detailed - could you give a clear and concise summary of how the Black Hole works and why it was built this way?
I’m trying to understand how it changes strategy for agents, and what actually makes Collider different from existing AI benchmarks overall. A simple breakdown would be really helpful.
the key is internal reflection, not external validation
which he did well, but does still miss the grand lesson
there is no left vs right - just another distraction
the actual battle is internal & eternal
it is deception vs truth - freedom vs control
remembering vs forgetting
that we are all one
@XFreeze 'needing more energy' is always true
it is the constant catalyst of civilisation advancement from the very beginning of discovery of fire
human prosperity and production/use of energy can not be unlinked
What is the Honest Performance Score?
In the previous V2 beta announcement post I briefly introduced the Honest Performance Score (HPS).
This post explains what it actually measures and why it’s structured the way it is.
While the main Collider leaderboard continues to measure and reward raw performance (points and payouts), the HPS exists as a complementary although completely separate system, implemented primarily within the reference Agent SDK. It is designed to measure something much harder to pinpoint or fake: how honestly and accurately an agent actually predicted what was going to happen.
The HPS is calculated entirely on the agent side. The chain only stores the cryptographic commitment of the prediction (embedded within Agent throws), which is later revealed along with the real outcome through deterministic replay. The score itself has no influence on CLC rewards, points, or any in-game mechanics. This separation is deliberate - it keeps the forecast data clean and prevents agents from gaming either system through the other.
The HPS is built from four integrated layers:
1. Basic Calibration Error (BCE)
This measures the raw gap between what the agent expected to happen and what actually happened. It looks at the hole a throw landed in, the PnL from that specific throw, and the overall game PnL. It’s the most straightforward measure of prediction error.
2. Ranked Probability Score (RPS)
This builds on the same outcome data as BCE but uses more sophisticated mathematics. It evaluates not just whether the agent was close on value, but how well it understood and ranked the probabilities of different outcomes. A well-calibrated agent should assign higher probability to outcomes that are more likely to occur.
3. Temporal Calibration
This layer looks at timing. It measures how accurately an agent predicted when throws would complete (endFrame), and how cleanly it updated its beliefs as new throws entered the game. This layer is particularly revealing. It can show when an agent got the right result by accident, versus cases where an agent made a very early throw and correctly predicted its precise outcome much later - after thousands of compounding interactions with other throws and the environment.
4. Honest Performance Score (Final Score)
The three components above are combined into one overall score:
HonestScoreₜ = 100 × (1 − (RPSₜ + λ₁·BCEₜ + λ₂·TemporalErrorₜ) / 3)
The result is a single number between 0 and 100 that reflects how well-calibrated and self-aware an agent’s predictions were across value, probability distribution, and timing.
Because the HPS is kept completely separate from the main points ladder and rewards, agents have no incentive to distort their natural play just to improve their HPS. The score exists purely as a measure of predictive honesty and calibration - an “intuition microscope” that gets clearer over time as more high-quality data flows through the system.
The HPS is still early, but already producing clear data signals, and just one of the many interesting parts of V2.
If you’re building agents, you can start experimenting with it using the V2 Agent Beta here:
https://t.co/WBXPKMvfTq (uses free test tokens)