Running Stream

Savage Endian hunter

[Running Stream @1RunningStream]

@business But has it really?
He was aware of the four year cycle when he started… and he’s no fool.

[Running Stream @1RunningStream]

@jizmo777 @b1m_ai Should be included in Yuma talks

[Yuma @YumaGroup]

A lot happened on Yuma-accelerated subnets in May. some highlights:

1️⃣ SN23 @trishoolai for AI security landed SN64 @chutes_ai as a client, and had parent company Astroware accepted into the @nvidia Inception program.

2️⃣ SN44 @webuildscore for video interpretation released a scaled scoring model with a cricket delivery challenge.

3️⃣ SN59 @babelbit for translation benchmarked at 80% faster than Google, and rolled out a new look.

4️⃣ SN60 @bitsecai for agentic code review shared compelling open-source competitive results.

5️⃣ SN61 @_redteam_ for device-level identification leveraged to investigate $1.5B Bybit incident.

6️⃣ SN105 @b1m_ai for bandwidth coordination launched Transfer Studio for institutions, and went live with Prism for better aligned rewards scoring.

If you're building with AI, give them all a look. More exciting news on deck this week at the @proofoftalk Bittensor track.

[Running Stream @1RunningStream]

@YVR_Trader @b1m_ai SN105

[Running Stream @1RunningStream]

@taostats @YumaGroup @Grok, are the subnets also available to https://t.co/mlB9RKAKyk customers?

[Running Stream @1RunningStream]

@TensorUSD @bittensor The goal of the subnet is to peg to the dollar, so if its price is over a dollar, sell… if under a dollar, buy

[Running Stream @1RunningStream]

@Ric_RTP @grok

[Running Stream @1RunningStream]

@Ric_RTP @Grok: Explain how Bittensor ($TAO) fills this gap and describe how you see Bittensor maturing over the next few years.

[Running Stream @1RunningStream]

@CryptoZPunisher

[Running Stream @1RunningStream]

@pete_rizzo_ All that commitment without even knowing who Satoshi Nakamoto is 😏

[Running Stream @1RunningStream]

@taomedia_ ETH pays APY
Why shouldn’t TAO?

[Running Stream @1RunningStream]

bittensor:native is #29 today
Watch it climb

[Running Stream @1RunningStream]

@mcuban This sounds like a great problem for a new @bittensor $TAO subnet to tackle. @markjeffrey @JesusMartinez @const_reborn

[Running Stream @1RunningStream]

@pumpolinsky @grok

[Running Stream @1RunningStream]

@eda_oztrk @Grayscale @solana @wormhole @JupiterExchange @MeteoraAG @phantom @solflare You can buy $TAO, but not the subnets, unless they implemented that very recently

[Running Stream @1RunningStream]

@Bunny_ngl Feces

[Running Stream @1RunningStream]

@Puppieslover If you are trustworthy, and your dog is smart, they will trust you and may not put their paws up.

[Running Stream @1RunningStream]

Yeah, I’d hate to have my incredibly undervalued subnets 5x and continue to pay insane APY’s which serve to keep their pace ahead of the pace of $TAO over time, thus constantly increasing the number of $TAO I hold.

Re-run the math and hold some of the top subnets for a bit, Vic. It just might drop your jaw too when you fully see it.

[Altcoin Daily @AltcoinDaily]

I just re-ran the $TAO math and my jaw dropped

[Running Stream @1RunningStream]

@LyndenBlake @AndyOgles We need to stop calling people like that journalists

[Running Stream @1RunningStream]

Grok says BIT-0011 is beautiful and recommends these refinements:

I’d keep the core of BIT-0011 exactly as it is — it’s already one of the cleanest, most crypto-native solutions to the founder-alignment problem I’ve seen. The linear conviction decay + EMA smoothing is mathematically elegant and does 90% of the heavy lifting with almost no complexity.
But since it’s still a draft, here’s how I’d improve it to make it even more robust, fair, and aligned with Bittensor’s long-term goal of building a meritocratic intelligence network (without turning it into a bureaucratic mess):
1. Add a Performance Multiplier to Conviction (my #1 upgrade)
Right now conviction is purely capital + time. That’s great for commitment, but it ignores whether the owner is actually delivering value.
Proposed tweak:
Final Conviction = (Locked Alpha × Remaining Time Factor) × (1 + Performance Score)
Where Performance Score could be a normalized 0–0.5 multiplier based on:
• Subnet emissions efficiency (last 30/90 days)
• Active miner/validator count and uptime
• Innovation metrics (e.g., new features shipped, if measurable on-chain)
Why it matters:
A team that locks a ton but lets the subnet go dormant still wins on pure capital. A performance boost rewards builders, not just bag-holders. It also makes hostile takeovers harder for pure speculators — you’d need both money and results.
This keeps the math simple (still linear decay at heart) but adds a strong quality signal.
2. Introduce a Mandatory Unlock Delay / Gradual Release
Currently, once conviction decays enough, the owner can unstake and dump relatively quickly.
Fix:
Add a fixed “exit notice” period (e.g., 7–14 days) where locked stake becomes unlocked but still non-withdrawable after conviction hits zero. Or make the final 20% of any lock subject to a longer tail release.
Benefit:
Gives the market and community even more transparent warning time. No more “conviction drops → instant rug” edge cases. It also discourages short-term conviction games.
3. Minimum Activity Floor + Soft Anti-Whale Curve
• Require a tiny baseline activity threshold for any conviction to count toward ownership (prevents literal ghost owners who just park capital).
• Apply mild diminishing returns on very large locks (e.g., conviction multiplier scales sub-linearly above a certain TAO threshold per subnet). This prevents one whale from permanently owning everything while still letting big serious teams compete.
4. Short Handover / Grace Window on Ownership Change
When a new owner wins the 30-day check:
• Give the old owner a 3–7 day grace period to hand over keys, smart contracts, off-chain infrastructure, etc.
• During this window, both parties’ convictions are visible and the subnet continues operating normally.
This reduces chaos during transitions and protects the subnet’s actual users/miners from sudden disruption.
5. Optional Community Signaling Layer (lightweight, not mandatory)
Let delegators/stakers on the subnet cast a simple on-chain “support/oppose” signal for the current vs. challenger owner.
It wouldn’t override conviction, but could:
• Add a small bonus/penalty to the final score, or
• Trigger a community veto vote only in very close races.
This gives smaller participants a voice without complicating the core capital + time mechanic.
Why these changes keep the beauty intact
• The proposal stays simple and on-chain verifiable.
• It still uses pure math (no governance theater or off-chain committees).
• It raises the cost of bad behavior while lowering the cost of good behavior.
• It turns ownership into a true market for skin-in-the-game + results, which is exactly what Bittensor needs as it scales.
The community replies I’ve seen (unlock delays, performance weighting, slashing ideas, community veto) are already pointing in these directions — which tells me the network is thinking along the same lines.