ApeBasic 🥟

My best shot of the year so far.. buying $IC at 17k MC. We just broke 16Mil Mc... Thank you @Gyoza_erc20 dev for the sick tools.. And um..yeah.. keep fading anon. 🤝

@TylerDurden dope show. Season 3 is excellent too, and s4 still very weird and entertaining. S2 was a bit misunderstood after the weight of s1! all great directing and scripting tbh

Just started this: I have been told S1 only.

The Cost of Intelligence is Heading to Zero | Hyperspace P2P Distributed Cache We present to you our breakthrough cross-domain work across AI, distributed systems, cryptography, game theory to solve the primary structural inefficiency at the heart of AI infrastructure: most inference is redundant. Google has reported that only 15% of daily searches are truly novel. The rest are repeats or close variants. LLM inference inherits this same power-law distribution. Enterprise chatbots see 70-80% of queries fall into a handful of intent categories. System prompts are identical across 100% of requests within an application. The KV attention state for "You are a helpful assistant" has been computed billions of times, on millions of GPUs, identically. And yet every AI lab, every startup, every self-hosted deployment - computes and caches these results independently. There is no shared layer. No global memory. Every provider pays the full compute cost for every query, even when the answer already exists somewhere in the network. This is the problem Hyperspace solves where distributed cache operates at three levels, each catching a different class of redundancy: 1. Response cache Same prompt, same model, same parameters - instant cached response from any node in the network. SHA-256 hash lookup via DHT, with cryptographic cache proofs linking every response to its original inference execution. No trust required. Fetchers re-announce as providers, so popular responses replicate naturally across more nodes. 2. KV prefix cache Same system prompt tokens - skip the most expensive part of inference entirely. Prefill (computing Key-Value attention states) is deterministic: same model plus same tokens always produces identical KV state. The network caches these states using erasure coding and distributes them via the routing network. New questions that share a common prefix resume generation from cached state instead of recomputing from scratch. 3. Routing to cached nodes Instead of transferring KV state across the network for every request, Hyperspace routes the request to the node that already has the state loaded in VRAM. The request goes to the cache, not the cache to the request. Together, these three layers mean that 70-90% of inference requests at network scale never require full GPU computation. This work doesn't exist in isolation. It builds on research from across the industry: SGLang's RadixAttention demonstrated that automatic prefix sharing can yield up to 5x speedup on structured LLM workloads. Moonshot AI's Mooncake built an entire KV-cache-centric disaggregated architecture for production serving at Kimi. Anthropic, OpenAI, and Google all launched prompt caching products in 2024 - priced at 50-90% discounts - because system prompt reuse is so pervasive that it changes the economics of inference. What all of these systems share is a common limitation: they operate within a single organization's infrastructure. SGLang caches prefixes within one server. Mooncake disaggregates KV cache within one datacenter. Anthropic's prompt caching works within one API provider's fleet. None of them can share cached state across organizational boundaries. Hyperspace removes this boundary. The cache is global. A response computed by a node in Tokyo is immediately available to a node in Berlin. A KV prefix state generated for Qwen-32B on one machine is verifiable and reusable by any other machine running the same model. The routing network provides the delivery guarantees, the erasure coding provides the redundancy, and the cache proofs provide the trust. What this means for the cost of intelligence Big AI labs scale linearly: twice the users means twice the GPU spend. Every query is a cost center. Their internal caching helps, but it's siloed - Lab A's cache can't serve Lab B's users, and neither can serve a self-hosted Llama deployment. Hyperspace scales sub-linearly. Every new node that joins the network adds to the global cache. Every inference result enriches the cache for all future requests. The cache hit rate rises with network size because query distributions follow a power law - the most common questions are asked exponentially more often than rare ones. The implication is simple: as the network grows, the effective cost per inference drops. Not linearly. Logarithmically. At 10 million nodes, we estimate 75-90% of all inference requests can be served from cache, eliminating 400,000+ MWh of energy consumption per year and avoiding over 200,000 tons of CO2 emissions. The first person to ask a question pays the compute cost. Everyone after them gets the answer for free, with cryptographic proof that it's authentic. Training is competitive. Inference is shared Open-weight models are converging on quality with closed models. Labs will continue to differentiate on training - data curation, architecture innovation, RLHF tuning. That's where the real intellectual property lives. But inference is a commodity. Two copies of Qwen-32B running the same prompt produce the same KV state and the same response, byte for byte, regardless of whose GPU runs the matrix multiplication. There is no moat in multiplying matrices. The moat is in training the weights. A global distributed cache makes this separation explicit. It doesn't matter who trained the model. Once the weights are open, the inference cost approaches zero at scale - because the network remembers every answer and can prove it's correct. No lab, no matter how well-funded, can match this. They cannot share caches across competitors. They scale linearly. The network scales logarithmically. The marginal cost of intelligence approaches zero. That's the endgame.

💪🐐

@MetaverseRanger 🤣

Based on the way I am currently swaering at my openclaw daily, I will be one of the first to go when AGI takes over.

@useOccam @brwnpb Been waiting for this since last year 🫣 “Join in” closed?

@brwnpb 🤝

the godfather of automated trading is coming, see you soon

@LTXStudio Super stoked to check out the lipsyncing, I heard it’s out of this world.

@LTXStudio Sick!

🚨 800 FREE CREDITS — 24 HOURS ONLY We just launched LTX-2.3, our most powerful video model yet. High-res. Fast. Cinematic. Native lip-sync. Follow + Retweet this post to get 800 credits sent to your DMs.

Artist to Watch in 2026: ⁠Gabriel Jacoby ⁠ From his first single to a nationwide tour with Khamari, Gabriel Jacoby's rise has been fueled by vulnerability and groove. ⁠ ⁠ Dropping his debut EP 'gutta child' serves as a bold self-portrait that embodies something that's designed to be experienced live, sung together, and lived with intention. His sound carries both a comfort of something passed down and a sense of something entirely new and his own.⁠ ⁠ Read the full feature at pigeonsandplanes.com/read/artists-t…

@TheCinesthetic The chills

Lost Highway was released 29 years ago. The eerie Mystery Man was inspired by a real encounter David Lynch once had at a party, where a stranger claimed to be at his house at that moment. It became the blueprint for one of the film’s most haunting scenes.

@shitco1nguru @Gyoza_erc20 @Polymarket @Kalshi Let’s go!

I will be focusing on prediction markets even more from now. Soon @Gyoza_erc20 will have additional analytics tools for @Polymarket and @Kalshi . ! Making it is a hard work but it has to be done, otherwise why we are all here? I am definitely not for 40 hour work week.

@Larskooistra_ 🧑‍🍳

@ApeBasic cheers

Aged like fine wine

@LaelapsBot What’s up? New developments ?

@KerriChandler Strings of life Big fun Burning I can’t kick this feeling when it hits I’m the baddest bitch Love’s got me high

What’s your favourite Detroit track?

@TheCinesthetic Very underrated

Warrior (2019) was based on Bruce Lee’s vision and it delivers…insane fights, sharp drama, and criminally underrated. This should’ve been way bigger.

@SVG__Collection Ain’t nobody as smooth as Roy Ayers. RIP some of my first go to jazz funk albums.

Roy Ayers — “Vibrations”

@jazzisdeadco Bonga the goat

"Mona Ki Ngi Xica" by Bonga — live in Angola, 1978. A father’s farewell turned anthem of resistance and hope, from one of Angola’s most iconic voices.

@viktoroddy I’m in! Attempting to makeover my website.. could use some juice 😘

Guys, this new year let’s make it fun. Giving away lifetime access to designrocket.io to 10 lucky winners. Simply. Like, Comment (I'm in). Repost. That's it. Winners announced in 48 hours. Jump in.

@BrianRoemmele Pretty cool, but The output seems to have a lot of artifacts though. Would be interesting to try in different scenarios.

This is absolutely astounding! SongGeneration Studio is a free open source Suno alternative and you can do anything you want in your own computer. I have a real-time music generator system that builds new songs based on situation and affect from human telemetry. More soon. With how-to!

@everymovieplug Yessss Angel Heart!

Top 100 Movies with Insane Plot Twists 🎬 1. The Sixth Sense (1999) 2. Fight Club (1999) 3. Se7en (1995) 4. The Usual Suspects (1995) 5. Oldboy (2003) 6. Shutter Island (2010) 7. Memento (2000) 8. Parasite (2019) 9. Gone Girl (2014) 10. The Prestige (2006) 11. Incendies (2010) 12. Primal Fear (1996) 13. Saw (2004) 14. Donnie Darko (2001) 15. The Others (2001) 16. Arrival (2016) 17. No Country for Old Men (2007) 18. Get Out (2017) 19. Atonement (2007) 20. Enemy (2013) 21. The Game (1997) 22. Identity (2003) 23. Black Swan (2010) 24. Vertigo (1958) 25. The Mist (2007) 26. Coherence (2013) 27. Mulholland Drive (2001) 28. Predestination (2014) 29. Hereditary (2018) 30. The Machinist (2004) 31. Ex Machina (2014) 32. Triangle (2009) 33. Gone Baby Gone (2007) 34. The Village (2004) 35. Dark City (1998) 36. Frailty (2001) 37. The Invitation (2015) 38. Arlington Road (1999) 39. Prisoners (2013) 40. Moon (2009) 41. The Handmaiden (2016) 42. Tinker Tailor Soldier Spy (2011) 43. The Wailing (2016) 44. Lucky Number Slevin (2006) 45. The Skin I Live In (2011) 46. Jacob’s Ladder (1990) 47. Perfect Blue (1997) 48. The Vanishing (1988) 49. Burning (2018) 50. Mystic River (2003) 51. The Crying Game (1992) 52. Cache (2005) 53. Angel Heart (1987) 54. Tenet (2020) 55. The Truman Show (1998) 56. The Lighthouse (2019) 57. Sorry to Bother You (2018) 58. Fallen (1998) 59. The Father (2020) 60. Saint Maud (2019) 61. Inception (2010) 62. Psycho (1960) 63. Blow Out (1981) 64. The Orphan (2009) 65. Under the Silver Lake (2018) 66. The Talented Mr. Ripley (1999) 67. The Killing of a Sacred Deer (2017) 68. The Gift (2015) 69. Abre los Ojos (1997) 70. Timecrimes (2007) 71. Memories of Murder (2003) 72. The Invisible Guest (2016) 73. Sleepaway Camp (1983) 74. A Simple Plan (1998) 75. The Otherside of the Door (2016) 76. Eyes Wide Shut (1999) 77. The Sting (1973) 78. The Departed (2006) 79. Unbreakable (2000) 80. Barbarian (2022) 81. Speak No Evil (2022) 82. The Cabin in the Woods (2012) 83. The House of the Devil (2009) 84. Matchstick Men (2003) 85. The Skeleton Key (2005) 86. Identity Theft (2002) 87. Source Code (2011) 88. The Last Seduction (1994) 89. The Silent Patient 90. Resolution (2012) 91. Upgrade (2018) 92. The Gift (2000) 93. The Perfect Host (2010) 94. Orphan: First Kill (2022) 95. Mother! (2017) 96. The Devil’s Advocate (1997) 97. The Blair Witch Project (1999) 98. Lake Mungo (2008) 99. The Night House (2020) 100. The Seventh Victim (1943)