NO1ennn's banner
NO1ennn's profile picture

NO1ennn

@N01ennn • 4,696 subscribers

Everything is going as usual

Shorts

I gave my Obsidian vault a lawyer's brain and now it argues with itself before it answers me three months ago I was drowning. 20 government acts, budget docs, constitutions, all sitting in my vault as dead markdown I could never actually query. so I stopped treating it like notes and built it a nervous system I turned it into a 10-node graph. every question I ask hits a router first. it decides in a split second: is this a greeting, is this garbage, is this vague, or is this real. greetings die for free. garbage gets rejected. and if my own question is too vague, the vault stops and asks ME to clarify before it wastes a single token then comes the part I'm proudest of. after it writes an answer, a second node reads that answer back against the actual chunks it pulled from my vault. if the answer isn't grounded in what I actually wrote, it kills it. my vault would rather say "I don't know" than lie to me. it physically cannot hallucinate I compressed 20+ dense documents into 15,408 chunks, cut the vectors by 75% so storage costs almost nothing, and cached everything so repeat questions come back in under 100 milliseconds I used to have a folder of files. now I have something that thinks before it speaks, checks itself before it answers, and refuses to make things up about my own life. that's the difference between storing knowledge and building a mind

I gave my Obsidian vault a lawyer's brain and now it argues with itself before it answers me three months ago I was drowning. 20 government acts, budget docs, constitutions, all sitting in my vault as dead markdown I could never actually query. so I stopped treating it like notes and built it a nervous system I turned it into a 10-node graph. every question I ask hits a router first. it decides in a split second: is this a greeting, is this garbage, is this vague, or is this real. greetings die for free. garbage gets rejected. and if my own question is too vague, the vault stops and asks ME to clarify before it wastes a single token then comes the part I'm proudest of. after it writes an answer, a second node reads that answer back against the actual chunks it pulled from my vault. if the answer isn't grounded in what I actually wrote, it kills it. my vault would rather say "I don't know" than lie to me. it physically cannot hallucinate I compressed 20+ dense documents into 15,408 chunks, cut the vectors by 75% so storage costs almost nothing, and cached everything so repeat questions come back in under 100 milliseconds I used to have a folder of files. now I have something that thinks before it speaks, checks itself before it answers, and refuses to make things up about my own life. that's the difference between storing knowledge and building a mind

36,382 görüntüleme

$300/month for AI visuals. replaced by a laptop and $2 electricity bill TouchDesigner + Ollama. local AI model. runs offline. nothing sent to any server. no API key that expires mid-performance > Ollama: 3 commands to install. one line change in existing code > Llama 3.2: real-time parameter calls. fast enough you don’t notice latency > TouchDesigner: hand tracking. audio-reactive. particle systems. generative graphics month one savings: $148-338. every month after: same your laptop. $0/month. a visual studio that runs forever

$300/month for AI visuals. replaced by a laptop and $2 electricity bill TouchDesigner + Ollama. local AI model. runs offline. nothing sent to any server. no API key that expires mid-performance > Ollama: 3 commands to install. one line change in existing code > Llama 3.2: real-time parameter calls. fast enough you don’t notice latency > TouchDesigner: hand tracking. audio-reactive. particle systems. generative graphics month one savings: $148-338. every month after: same your laptop. $0/month. a visual studio that runs forever

30,177 görüntüleme

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

A 21-YEAR-OLD FROM CHINA RUNS 300 AI AGENTS AT ONCE. THE PART THAT MATTERS ISN'T THE SPEED, IT'S THAT NONE OF THEM CAN LIE TO HIM he opens the dashboard and shows the swarm live, 300 Kimi K2.6 agents firing in parallel, then Opus 4.8 checking every single output against its source. this is not just a faster swarm. it is a loop that refuses to stop while anything is still wrong he pointed it at 100 EV-market companies. first pass: 12 failed. wrong revenue, dead citations, empty fields. second pass: 3 failed. third pass: zero this is not another agent demo. it is a system that catches its own mistakes before he reads a single row
0:30
N01ennn's profile picture

A 21-YEAR-OLD FROM CHINA RUNS 300 AI AGENTS AT ONCE. THE PART THAT MATTERS ISN'T THE SPEED, IT'S THAT NONE OF THEM CAN LIE TO HIM he opens the dashboard and shows the swarm live, 300 Kimi K2.6 agents firing in parallel, then Opus 4.8 checking every single output against its source. this is not just a faster swarm. it is a loop that refuses to stop while anything is still wrong he pointed it at 100 EV-market companies. first pass: 12 failed. wrong revenue, dead citations, empty fields. second pass: 3 failed. third pass: zero this is not another agent demo. it is a system that catches its own mistakes before he reads a single row

NO1ennn

6,950,476 görüntüleme • 2 ay önce

MICROSOFT QUIETLY SHIPPED THE RAG PIPELINE EVERYONE KEEPS TRYING TO BUILD FROM SCRATCH it is called Kernel Memory, and it turns any pile of files into an AI memory that answers with citations. drop your data in and Microsoft's pipeline does the rest: > ingest PDFs, Word, PPT, Excel, web pages, even images > extract the text, chunk it, embed it into vectors > store the vectors with metadata and keep the originals in blob storage > ask a question and it pulls the right chunks with semantic plus hybrid search then it hands the answer back grounded, with links to the exact source and full token usage. and it plugs into whatever you already run: > Azure OpenAI, OpenAI, Ollama, or Anthropic for the models > Qdrant, pgvector, Redis, or Azure AI Search for the vectors > every step is a swappable handler, so you can replace any part with your own one heads up: Microsoft archived the repo in June 2026 and ships it as a reference blueprint, not production. but as a map for how memory and RAG are actually built, nothing is cleaner. run it in one command: docker run kernelmemory/service bookmark this. Microsoft already drew the blueprint, you just build on it.
0:25
N01ennn's profile picture

MICROSOFT QUIETLY SHIPPED THE RAG PIPELINE EVERYONE KEEPS TRYING TO BUILD FROM SCRATCH it is called Kernel Memory, and it turns any pile of files into an AI memory that answers with citations. drop your data in and Microsoft's pipeline does the rest: > ingest PDFs, Word, PPT, Excel, web pages, even images > extract the text, chunk it, embed it into vectors > store the vectors with metadata and keep the originals in blob storage > ask a question and it pulls the right chunks with semantic plus hybrid search then it hands the answer back grounded, with links to the exact source and full token usage. and it plugs into whatever you already run: > Azure OpenAI, OpenAI, Ollama, or Anthropic for the models > Qdrant, pgvector, Redis, or Azure AI Search for the vectors > every step is a swappable handler, so you can replace any part with your own one heads up: Microsoft archived the repo in June 2026 and ships it as a reference blueprint, not production. but as a map for how memory and RAG are actually built, nothing is cleaner. run it in one command: docker run kernelmemory/service bookmark this. Microsoft already drew the blueprint, you just build on it.

NO1ennn

84,103 görüntüleme • 8 gün önce

MICROSOFT QUIETLY BUILT ONE MEMORY MODULE THAT PLUGS INTO ANY AI AGENT AND CUTS ITS CONTEXT BY UP TO 100X no retraining. no task-specific redesign. you just plug it in Microsoft's insight: agents don't need to remember what happened. they need the knowledge pulled from it - the facts and the reusable skills, not the raw logs so PlugMem stops storing history. it compiles experience into a knowledge graph, then feeds the agent only what matters the result: > up to 1-2 orders of magnitude fewer tokens > highest decision-utility per token of any system tested > one unchanged module beats task-specific memory on chat QA, multi-hop search, and web agents more memory was never the answer. better memory is - and Microsoft just shipped it as a plug-in bookmark this. the agents that win won't remember more, they'll remember smarter.
0:42
N01ennn's profile picture

MICROSOFT QUIETLY BUILT ONE MEMORY MODULE THAT PLUGS INTO ANY AI AGENT AND CUTS ITS CONTEXT BY UP TO 100X no retraining. no task-specific redesign. you just plug it in Microsoft's insight: agents don't need to remember what happened. they need the knowledge pulled from it - the facts and the reusable skills, not the raw logs so PlugMem stops storing history. it compiles experience into a knowledge graph, then feeds the agent only what matters the result: > up to 1-2 orders of magnitude fewer tokens > highest decision-utility per token of any system tested > one unchanged module beats task-specific memory on chat QA, multi-hop search, and web agents more memory was never the answer. better memory is - and Microsoft just shipped it as a plug-in bookmark this. the agents that win won't remember more, they'll remember smarter.

NO1ennn

226,253 görüntüleme • 23 gün önce

INTEL JUST QUIETLY BUILT THE CHEAPEST PATH TO 128GB OF LOCAL AI VRAM, AND IT BEATS NVIDIA'S DGX SPARK BY 2X FOR THE SAME $4,000 00:11 four Arc Pro B70s racked in one chassis. 32GB of GDDR6 each, $949 MSRP, roughly $1,000 street per card stack four and you get 128GB of VRAM for about $4,000 total. a lab benchmarked the quad against a DGX Spark and a single RTX Pro 6000. the four B70s doubled the Spark or better they trail the Pro 6000, but that card is $10,000. so the real choice is now $4K for 128GB from Intel or $10K for 96GB from NVIDIA the article covers the DGX Spark at $3,999 as the single-desk local AI ceiling. this Intel quad matches the price, beats the memory throughput, and nobody is talking about it yet save this before Intel's VRAM-per-dollar advantage becomes the default homelab build ↓
1:26
N01ennn's profile picture

INTEL JUST QUIETLY BUILT THE CHEAPEST PATH TO 128GB OF LOCAL AI VRAM, AND IT BEATS NVIDIA'S DGX SPARK BY 2X FOR THE SAME $4,000 00:11 four Arc Pro B70s racked in one chassis. 32GB of GDDR6 each, $949 MSRP, roughly $1,000 street per card stack four and you get 128GB of VRAM for about $4,000 total. a lab benchmarked the quad against a DGX Spark and a single RTX Pro 6000. the four B70s doubled the Spark or better they trail the Pro 6000, but that card is $10,000. so the real choice is now $4K for 128GB from Intel or $10K for 96GB from NVIDIA the article covers the DGX Spark at $3,999 as the single-desk local AI ceiling. this Intel quad matches the price, beats the memory throughput, and nobody is talking about it yet save this before Intel's VRAM-per-dollar advantage becomes the default homelab build ↓

NO1ennn

139,651 görüntüleme • 1 ay önce

ANTHROPIC JUST KILLED A DOZEN AI MEMORY STARTUPS WITH ONE BUILT IN TOOL people raised millions to give AI long term memory. Anthropic just shipped it straight into the API. free, no framework, no vector database. it is a folder of files Claude reads and writes. that is it. the trick: it is client side. Claude never touches your data directly. it only requests a file operation, and your app runs it against storage you control. before every task Claude checks its /memories directory, pulls back what it learned last time, and keeps going. when it learns something new, it writes it down. six plain operations do all of it: > view, create, str_replace, insert, delete, rename why it actually wins: > just in time retrieval, it reads on demand instead of loading everything up front > it survives a context reset, so a long job resumes instead of starting over > every path is locked to /memories, so it cannot wander your filesystem > works on every Claude 4 model, no beta flag, generally available Anthropic even pairs it with context editing and compaction, so the live window stays tiny while the important stuff lives on disk. the whole thing in one line: Claude keeps the notes, you keep the storage. bookmark this before you pay for a memory layer you no longer need.
0:26
N01ennn's profile picture

ANTHROPIC JUST KILLED A DOZEN AI MEMORY STARTUPS WITH ONE BUILT IN TOOL people raised millions to give AI long term memory. Anthropic just shipped it straight into the API. free, no framework, no vector database. it is a folder of files Claude reads and writes. that is it. the trick: it is client side. Claude never touches your data directly. it only requests a file operation, and your app runs it against storage you control. before every task Claude checks its /memories directory, pulls back what it learned last time, and keeps going. when it learns something new, it writes it down. six plain operations do all of it: > view, create, str_replace, insert, delete, rename why it actually wins: > just in time retrieval, it reads on demand instead of loading everything up front > it survives a context reset, so a long job resumes instead of starting over > every path is locked to /memories, so it cannot wander your filesystem > works on every Claude 4 model, no beta flag, generally available Anthropic even pairs it with context editing and compaction, so the live window stays tiny while the important stuff lives on disk. the whole thing in one line: Claude keeps the notes, you keep the storage. bookmark this before you pay for a memory layer you no longer need.

NO1ennn

42,946 görüntüleme • 14 gün önce

STANFORD BUILT AN LLM MEMORY THAT WORKS LIKE A BRAIN AND IT MADE STANDARD RAG LOOK ANCIENT no fine-tuning. no bigger model. just a smarter way to remember the insight: the brain doesn't store memories as isolated notes. it indexes them and links them - so one cue pulls back the whole memory so HippoRAG stops treating documents as separate chunks. it builds a knowledge graph, then spreads activation across it (Personalized PageRank) to pull a full answer from a single cue - the brain calls this "pattern completion" the result: > up to 20% better on hard multi-hop questions > 10-30x cheaper and 6-13x faster than iterative retrieval > connects facts split across documents in a single step most RAG still encodes every passage in isolation - so it breaks the moment the answer is scattered more retrieval was never the answer. brain-like memory is bookmark this. the next leap in AI agents is how they remember, not how big they get
0:29
N01ennn's profile picture

STANFORD BUILT AN LLM MEMORY THAT WORKS LIKE A BRAIN AND IT MADE STANDARD RAG LOOK ANCIENT no fine-tuning. no bigger model. just a smarter way to remember the insight: the brain doesn't store memories as isolated notes. it indexes them and links them - so one cue pulls back the whole memory so HippoRAG stops treating documents as separate chunks. it builds a knowledge graph, then spreads activation across it (Personalized PageRank) to pull a full answer from a single cue - the brain calls this "pattern completion" the result: > up to 20% better on hard multi-hop questions > 10-30x cheaper and 6-13x faster than iterative retrieval > connects facts split across documents in a single step most RAG still encodes every passage in isolation - so it breaks the moment the answer is scattered more retrieval was never the answer. brain-like memory is bookmark this. the next leap in AI agents is how they remember, not how big they get

NO1ennn

32,454 görüntüleme • 21 gün önce

MICROSOFT TRIED TO BUY IT. HARVARD AND THREE US UNIVERSITIES RELEASED IT FOR FREE a team from Harvard, Michigan State, Minnesota, and Georgia ran the first hard study on how agent memory behaves over time. the finding is uncomfortab they call it the "experience-following property": when a new task looks like a memory the agent pulls up, its answer copies that memory's answer almost 1:1 (correlation up to 0.95). the agent isn't reasoning - it's imitating that breaks in two ways: > error propagation - one wrong memory repeats on every similar task after it > misaligned replay - "successful" past runs turn out low-value or misleading when reused so "just add more memory" quietly makes agents worse. what fixed it: > store only high-quality experiences, not everything > use future task outcomes as free labels to delete low-value memories > pair selective adding with utility-based deletion the payoff: ~10% absolute accuracy gains, a cleaner memory bank, and agents stable under distribution shift no company owns this. they dropped the whole thing open-source, for free bookmark this. the next edge in AI agents isn't more memory - it's cleaner memory
0:23
N01ennn's profile picture

MICROSOFT TRIED TO BUY IT. HARVARD AND THREE US UNIVERSITIES RELEASED IT FOR FREE a team from Harvard, Michigan State, Minnesota, and Georgia ran the first hard study on how agent memory behaves over time. the finding is uncomfortab they call it the "experience-following property": when a new task looks like a memory the agent pulls up, its answer copies that memory's answer almost 1:1 (correlation up to 0.95). the agent isn't reasoning - it's imitating that breaks in two ways: > error propagation - one wrong memory repeats on every similar task after it > misaligned replay - "successful" past runs turn out low-value or misleading when reused so "just add more memory" quietly makes agents worse. what fixed it: > store only high-quality experiences, not everything > use future task outcomes as free labels to delete low-value memories > pair selective adding with utility-based deletion the payoff: ~10% absolute accuracy gains, a cleaner memory bank, and agents stable under distribution shift no company owns this. they dropped the whole thing open-source, for free bookmark this. the next edge in AI agents isn't more memory - it's cleaner memory

NO1ennn

27,496 görüntüleme • 18 gün önce

FOUR DIFFERENT VENDORS ARE NOW SHIPPING GB10 MINI PCs WITH 128GB UNIFIED MEMORY, AND ONE MICROTIK CRS 804 SWITCH CAN CONNECT UP TO EIGHT OF THEM INTO A 1 TERABYTE LOCAL AI CLUSTER 00:00 he points at the MikroTik CRS 804, "you need some kind of switch that'll handle QSFP56 ports like these", the interconnect that makes the whole cluster possible the GB10 ecosystem is no longer just Nvidia. Dell Pro Max GB10, ASUS Ascent GX10, and MSI Edge Expert all ship the same Grace Blackwell Superchip with 128GB of coherent memory. same silicon, different cases, same 200 gigabit ports on the back the CRS 804 is what connects them at prosumer prices. four 400 gigabit QSFP56 ports on one 1U chassis, breakout cables that split each port into two 200 gigabit lanes. one switch drives eight GB10 units in parallel do the math. eight nodes at 128GB each equals 1024GB of pooled unified memory across the cluster. run vLLM, shard a frontier model across all eight, and inference happens locally on hardware that fits in half a rack the real limiter revealed in the stress test was never throttling. it was interconnect topology, exactly the layer this switch fixes at a fraction of enterprise switch pricing $400 a month for combined chatgpt pro and claude code max hits $4,800 a year per developer. a small team of five running through this cluster pays back inside eight months and never expires the article covers the buying ladder for a single desk. this post is proof of the cluster ladder that starts where the desk one ends save this before the GB10 lineup grows past four vendors and prosumer cluster switches move upmarket
1:05
N01ennn's profile picture

FOUR DIFFERENT VENDORS ARE NOW SHIPPING GB10 MINI PCs WITH 128GB UNIFIED MEMORY, AND ONE MICROTIK CRS 804 SWITCH CAN CONNECT UP TO EIGHT OF THEM INTO A 1 TERABYTE LOCAL AI CLUSTER 00:00 he points at the MikroTik CRS 804, "you need some kind of switch that'll handle QSFP56 ports like these", the interconnect that makes the whole cluster possible the GB10 ecosystem is no longer just Nvidia. Dell Pro Max GB10, ASUS Ascent GX10, and MSI Edge Expert all ship the same Grace Blackwell Superchip with 128GB of coherent memory. same silicon, different cases, same 200 gigabit ports on the back the CRS 804 is what connects them at prosumer prices. four 400 gigabit QSFP56 ports on one 1U chassis, breakout cables that split each port into two 200 gigabit lanes. one switch drives eight GB10 units in parallel do the math. eight nodes at 128GB each equals 1024GB of pooled unified memory across the cluster. run vLLM, shard a frontier model across all eight, and inference happens locally on hardware that fits in half a rack the real limiter revealed in the stress test was never throttling. it was interconnect topology, exactly the layer this switch fixes at a fraction of enterprise switch pricing $400 a month for combined chatgpt pro and claude code max hits $4,800 a year per developer. a small team of five running through this cluster pays back inside eight months and never expires the article covers the buying ladder for a single desk. this post is proof of the cluster ladder that starts where the desk one ends save this before the GB10 lineup grows past four vendors and prosumer cluster switches move upmarket

NO1ennn

59,725 görüntüleme • 1 ay önce

Microsoft ran its graph system against vector RAG on 8k, 120k, and a full million token context window, and the million token giant lost Jonathan Larson from Microsoft Research put up the numbers → LazyGraphRAG won 92, 90, and 91 percent of data-local questions, the exact place plain RAG was supposed to be strong → and did it at a tenth of the cost of the million token run the lesson buried in the benchmark → a bigger context window is not memory, structured memory is throwing more tokens at the problem was just the expensive way to be wrong open source on GitHub, the lesson a $1500 course would charge you for
14:48
N01ennn's profile picture

Microsoft ran its graph system against vector RAG on 8k, 120k, and a full million token context window, and the million token giant lost Jonathan Larson from Microsoft Research put up the numbers → LazyGraphRAG won 92, 90, and 91 percent of data-local questions, the exact place plain RAG was supposed to be strong → and did it at a tenth of the cost of the million token run the lesson buried in the benchmark → a bigger context window is not memory, structured memory is throwing more tokens at the problem was just the expensive way to be wrong open source on GitHub, the lesson a $1500 course would charge you for

NO1ennn

29,189 görüntüleme • 26 gün önce

INTEL JUST SHIPPED A WORKSTATION CARD WITH TWO GPUs ON ONE PCB AND 48GB OF VRAM. FOUR CARDS GIVE A SINGLE MOTHERBOARD 192GB OF POOLED INFERENCE MEMORY FOR THE PRICE OF TWO RTX 5090s 00:14 he holds one card up to the camera, two GPU dies side by side under the cooler, each one running its own x8 PCIe lane back to the chipset the cluster sees eight discrete accelerators in software. intel's Battle Matrix stack shards a model across all eight, so a 235B parameter network loads in slices and answers requests in parallel what 192GB of VRAM unlocks: an entire 200B class model in memory without quantization. a vision agent reading 100 invoices at once. a research box that holds three frontier models loaded simultaneously, switching between them in under a second intel is the slow side of inference. nvidia is faster per token, that is the honest tradeoff. but the only other path to this much VRAM is a $40,000 nvidia rack or three networked Mac Studios four B60 cards plus the chassis lands under $5,000. power draw averages 800 watts, $55 a month in electricity. one engineer paying $400 a month for combined ChatGPT Pro and Claude Code Max pays the hardware off in less than a year
1:16
N01ennn's profile picture

INTEL JUST SHIPPED A WORKSTATION CARD WITH TWO GPUs ON ONE PCB AND 48GB OF VRAM. FOUR CARDS GIVE A SINGLE MOTHERBOARD 192GB OF POOLED INFERENCE MEMORY FOR THE PRICE OF TWO RTX 5090s 00:14 he holds one card up to the camera, two GPU dies side by side under the cooler, each one running its own x8 PCIe lane back to the chipset the cluster sees eight discrete accelerators in software. intel's Battle Matrix stack shards a model across all eight, so a 235B parameter network loads in slices and answers requests in parallel what 192GB of VRAM unlocks: an entire 200B class model in memory without quantization. a vision agent reading 100 invoices at once. a research box that holds three frontier models loaded simultaneously, switching between them in under a second intel is the slow side of inference. nvidia is faster per token, that is the honest tradeoff. but the only other path to this much VRAM is a $40,000 nvidia rack or three networked Mac Studios four B60 cards plus the chassis lands under $5,000. power draw averages 800 watts, $55 a month in electricity. one engineer paying $400 a month for combined ChatGPT Pro and Claude Code Max pays the hardware off in less than a year

NO1ennn

48,247 görüntüleme • 2 ay önce

AI kids videos. 60 seconds to make. $4,000 per 100K views. she figured it out first Pixar Flow + ChatGPT. pick template. write prompt. video ready. upload. repeat kids channels already pulling millions of views. all AI. nobody noticed yet YouTube RPM kids content: $200-$4,000 per 100K views. one viral video = month of salary month 12 at one video/week: $8,000-$15,000/month. $66/month stack. zero humans involved
0:32
N01ennn's profile picture

AI kids videos. 60 seconds to make. $4,000 per 100K views. she figured it out first Pixar Flow + ChatGPT. pick template. write prompt. video ready. upload. repeat kids channels already pulling millions of views. all AI. nobody noticed yet YouTube RPM kids content: $200-$4,000 per 100K views. one viral video = month of salary month 12 at one video/week: $8,000-$15,000/month. $66/month stack. zero humans involved

NO1ennn

71,827 görüntüleme • 3 ay önce

THIS IS THE MOST BEAUTIFUL OBSIDIAN WORLDBUILDING VAULT I HAVE SEEN, AND THE CREATOR JUST OPEN-SOURCED THE ENTIRE THEME FOR FREE 00:04 a full fantasy cosmology in the left rail: Pantheon, Realms, Galaxies, right down to named moons and star systems everything is linked. characters to locations, locations to star systems, star systems to the gods that created them. a living graph of an entire invented universe the build is the Border base theme, custom CSS for callouts and infoboxes, and 20 plugins including DataView, Canvas Mindmap, Enchanted Animations, and Style Settings he shipped it all as one GitHub repo, Mournes Jade Amber. no paywall, no plugin store, clone it and your vault looks like this tonight save this before every fantasy writer stops using Word and starts building worlds in Obsidian ↓
1:03
N01ennn's profile picture

THIS IS THE MOST BEAUTIFUL OBSIDIAN WORLDBUILDING VAULT I HAVE SEEN, AND THE CREATOR JUST OPEN-SOURCED THE ENTIRE THEME FOR FREE 00:04 a full fantasy cosmology in the left rail: Pantheon, Realms, Galaxies, right down to named moons and star systems everything is linked. characters to locations, locations to star systems, star systems to the gods that created them. a living graph of an entire invented universe the build is the Border base theme, custom CSS for callouts and infoboxes, and 20 plugins including DataView, Canvas Mindmap, Enchanted Animations, and Style Settings he shipped it all as one GitHub repo, Mournes Jade Amber. no paywall, no plugin store, clone it and your vault looks like this tonight save this before every fantasy writer stops using Word and starts building worlds in Obsidian ↓

NO1ennn

28,175 görüntüleme • 1 ay önce

HERMES AGENT NOW RUNS ON AN 8GB LAPTOP GPU JUST AS EASILY AS IT RUNS ON A 128GB MINI PC Nous Research shipped the official Hermes Agent Desktop App this week. Someone pointed it at a local llama server running on an RTX 4060 with 16GB system RAM. The integration took two minutes The model behind it: Gemma 4 26B MoE, QAT quantized, running on 8GB of VRAM. A 60k token prompt held a stable 20 tokens a second, flat, no slowdown as context grew. The flags were nothing exotic, just -cmoe -c 248000 on llama.cpp What that 8GB setup does out of the box: reads and patches its own code, runs it in a terminal, debugs errors, manages GitHub repos, spawns sub-agents for parallel work. Browses the web with vision to debug a UI. Schedules cron jobs in plain language. Connects to Notion, Google Workspace, Linear, and Obsidian to manage tasks on its own That's the same agent layer running on a Minisforum MS-S1 MAX with 128GB of unified memory, 96GB of it to the GPU, holding a 120B model at 56 tokens a second instead of a 26B model at 20. Same software, same tool execution, same zero API key. The only thing that changes between an $800 laptop and a $2,000 mini PC is how big a model you can afford to run underneath it The barrier to running a real autonomous agent locally didn't just drop. It dropped all the way down to hardware most people already own
0:20
N01ennn's profile picture

HERMES AGENT NOW RUNS ON AN 8GB LAPTOP GPU JUST AS EASILY AS IT RUNS ON A 128GB MINI PC Nous Research shipped the official Hermes Agent Desktop App this week. Someone pointed it at a local llama server running on an RTX 4060 with 16GB system RAM. The integration took two minutes The model behind it: Gemma 4 26B MoE, QAT quantized, running on 8GB of VRAM. A 60k token prompt held a stable 20 tokens a second, flat, no slowdown as context grew. The flags were nothing exotic, just -cmoe -c 248000 on llama.cpp What that 8GB setup does out of the box: reads and patches its own code, runs it in a terminal, debugs errors, manages GitHub repos, spawns sub-agents for parallel work. Browses the web with vision to debug a UI. Schedules cron jobs in plain language. Connects to Notion, Google Workspace, Linear, and Obsidian to manage tasks on its own That's the same agent layer running on a Minisforum MS-S1 MAX with 128GB of unified memory, 96GB of it to the GPU, holding a 120B model at 56 tokens a second instead of a 26B model at 20. Same software, same tool execution, same zero API key. The only thing that changes between an $800 laptop and a $2,000 mini PC is how big a model you can afford to run underneath it The barrier to running a real autonomous agent locally didn't just drop. It dropped all the way down to hardware most people already own

NO1ennn

40,079 görüntüleme • 2 ay önce

ANTHROPIC KILLED THE VECTOR DATABASE AND REPLACED IT WITH A FOLDER no embeddings. no black-box retrieval. no special memory tools. the agent just reads and writes a folder the insight: your agent already knows how to use a filesystem. so Anthropic made long-term memory a directory of small markdown files, mounted straight into the agent's sandbox at /mnt/memory the agent manages it with the tools it already has, bash, read, write, edit, grep, and Anthropic auto-injects a note into the system prompt so the agent always knows the memory is there and where to look the result: > every change is an immutable version: full audit trail, point-in-time recovery, redaction > read-only or read-write per store, so many agents can safely share one memory > workspace-scoped and persistent, memory that survives every session end most teams bolt on a vector DB and pray retrieval works. Anthropic went the opposite way: compiled knowledge as plain, human-readable files you can open, diff, and edit yourself and there's a second layer. Anthropic's "Dreaming" runs offline, reviews past sessions and the store, and rewrites it into a cleaner, higher-signal version. the agent literally consolidates memory in its sleep. bookmark this. the most production-grade agent memory right now is just a well-organized folder, and Anthropic proved it.
0:50
N01ennn's profile picture

ANTHROPIC KILLED THE VECTOR DATABASE AND REPLACED IT WITH A FOLDER no embeddings. no black-box retrieval. no special memory tools. the agent just reads and writes a folder the insight: your agent already knows how to use a filesystem. so Anthropic made long-term memory a directory of small markdown files, mounted straight into the agent's sandbox at /mnt/memory the agent manages it with the tools it already has, bash, read, write, edit, grep, and Anthropic auto-injects a note into the system prompt so the agent always knows the memory is there and where to look the result: > every change is an immutable version: full audit trail, point-in-time recovery, redaction > read-only or read-write per store, so many agents can safely share one memory > workspace-scoped and persistent, memory that survives every session end most teams bolt on a vector DB and pray retrieval works. Anthropic went the opposite way: compiled knowledge as plain, human-readable files you can open, diff, and edit yourself and there's a second layer. Anthropic's "Dreaming" runs offline, reviews past sessions and the store, and rewrites it into a cleaner, higher-signal version. the agent literally consolidates memory in its sleep. bookmark this. the most production-grade agent memory right now is just a well-organized folder, and Anthropic proved it.

NO1ennn

13,359 görüntüleme • 20 gün önce

a 19 year old girl just coded a quant trading bot from a research paper. Codex did 90% of the work drop PDF into Codex. ask it to act like a quant researcher. get working strategy code strategy: perps DEX funding carry. market-neutral. collect the spread between longs and shorts live test results: > 4 closed positions > 96% of profit came from funding. not price direction > annualized: ~19% APR > price PnL: flat. that’s the point turning a research paper into something tradable used to mean hours. now it’s one PDF drop
0:46
N01ennn's profile picture

a 19 year old girl just coded a quant trading bot from a research paper. Codex did 90% of the work drop PDF into Codex. ask it to act like a quant researcher. get working strategy code strategy: perps DEX funding carry. market-neutral. collect the spread between longs and shorts live test results: > 4 closed positions > 96% of profit came from funding. not price direction > annualized: ~19% APR > price PnL: flat. that’s the point turning a research paper into something tradable used to mean hours. now it’s one PDF drop

NO1ennn

46,468 görüntüleme • 3 ay önce

DGX Spark hit 228ms time-to-first-token on Qwen3.6 35B-A3B. That is 4x faster than an RTX 3090 and 45% ahead of the RTX 5090 Raw throughput still belongs to the 5090 at 160 tok/s. Full numbers, same Ollama backend, Q4_K_M across all four: RTX 3090: 49.78 tok/s, 852ms RTX 4090: 118.93 tok/s, 686ms RTX 5090: 160.37 tok/s, 409ms DGX Spark: 59.98 tok/s, 228ms
1:24
N01ennn's profile picture

DGX Spark hit 228ms time-to-first-token on Qwen3.6 35B-A3B. That is 4x faster than an RTX 3090 and 45% ahead of the RTX 5090 Raw throughput still belongs to the 5090 at 160 tok/s. Full numbers, same Ollama backend, Q4_K_M across all four: RTX 3090: 49.78 tok/s, 852ms RTX 4090: 118.93 tok/s, 686ms RTX 5090: 160.37 tok/s, 409ms DGX Spark: 59.98 tok/s, 228ms

NO1ennn

22,497 görüntüleme • 1 ay önce

SHE TURNED KIDS YOUTUBE INTO A CASH MACHINE USING CLAUDE. $25,000/MONTH. THE WORKFLOW IS 40 SECONDS before: find a channel. hire animators. weeks of production after: screenshot → claude → higgsfield → animated video. 40 seconds this isn't a productivity hack. it's a new content pipeline > find a top performing kids channel. screenshot it. paste to claude. > claude analyzes the style. higgsfield MCP generates the animation. one prompt > finished animated video. same niche. same format. from scratch to done in under a minute
0:41
N01ennn's profile picture

SHE TURNED KIDS YOUTUBE INTO A CASH MACHINE USING CLAUDE. $25,000/MONTH. THE WORKFLOW IS 40 SECONDS before: find a channel. hire animators. weeks of production after: screenshot → claude → higgsfield → animated video. 40 seconds this isn't a productivity hack. it's a new content pipeline > find a top performing kids channel. screenshot it. paste to claude. > claude analyzes the style. higgsfield MCP generates the animation. one prompt > finished animated video. same niche. same format. from scratch to done in under a minute

NO1ennn

32,547 görüntüleme • 2 ay önce

a 21 year old makes $30,000/month. Pinterest photo. AI video. Shopify store. zero inventory Pinterest → ChatGPT → Higgsfield → TikTok → Shopify. one pipeline. $153,680 in sales > Pinterest: source model aesthetic > ChatGPT: converts image to video prompt > Higgsfield MCP: UGC-style video. iPhone aesthetic. 9:16 > TikTok Studio: millions of views. free traffic > Shopify: closes the sale 56 cents per video. agency charges $1,500 for the same format. 7 clients = $10,500/month. 85% margins 50 videos for $50. humans were the bottleneck
0:29
N01ennn's profile picture

a 21 year old makes $30,000/month. Pinterest photo. AI video. Shopify store. zero inventory Pinterest → ChatGPT → Higgsfield → TikTok → Shopify. one pipeline. $153,680 in sales > Pinterest: source model aesthetic > ChatGPT: converts image to video prompt > Higgsfield MCP: UGC-style video. iPhone aesthetic. 9:16 > TikTok Studio: millions of views. free traffic > Shopify: closes the sale 56 cents per video. agency charges $1,500 for the same format. 7 clients = $10,500/month. 85% margins 50 videos for $50. humans were the bottleneck

NO1ennn

35,608 görüntüleme • 2 ay önce

THE MS-A2 IS THE MINISFORUM BOX HERMES AGENT WAS NEVER MEANT TO RUN ON, AND THAT'S BY DESIGN The MS-S1 MAX earns its spot running Hermes Agent because of one thing. 128GB of unified memory, up to 96GB of it handed straight to the GPU. That's the only reason a 120B model fits and runs locally for $0 a month The MS-A2 solves a different problem. Ryzen 9 9955HX, 16 cores, 32 threads, up to 96GB of regular DDR5-5600, no unified pool Three M.2 PCIe 4.0 slots, one U.2, two 22110. Dual 10Gbps SFP+ LAN plus 2.5G. WiFi 6E. Bluetooth 5.3. A slide-out motherboard for fast upgrades. A real PCIe x16 slot that actually takes a low-profile GPU That last part is where the two machines split for good. The MS-S1 MAX's PCIe slot won't take a GPU at all, every bit of GPU power has to come from the unified chip itself. The MS-A2 trades that unified memory trick for raw expandability instead One box runs a local AI agent. The other runs a home lab that needs storage, networking, and room to grow. Minisforum built both on purpose, not as the same product wearing two names
1:06
N01ennn's profile picture

THE MS-A2 IS THE MINISFORUM BOX HERMES AGENT WAS NEVER MEANT TO RUN ON, AND THAT'S BY DESIGN The MS-S1 MAX earns its spot running Hermes Agent because of one thing. 128GB of unified memory, up to 96GB of it handed straight to the GPU. That's the only reason a 120B model fits and runs locally for $0 a month The MS-A2 solves a different problem. Ryzen 9 9955HX, 16 cores, 32 threads, up to 96GB of regular DDR5-5600, no unified pool Three M.2 PCIe 4.0 slots, one U.2, two 22110. Dual 10Gbps SFP+ LAN plus 2.5G. WiFi 6E. Bluetooth 5.3. A slide-out motherboard for fast upgrades. A real PCIe x16 slot that actually takes a low-profile GPU That last part is where the two machines split for good. The MS-S1 MAX's PCIe slot won't take a GPU at all, every bit of GPU power has to come from the unified chip itself. The MS-A2 trades that unified memory trick for raw expandability instead One box runs a local AI agent. The other runs a home lab that needs storage, networking, and room to grow. Minisforum built both on purpose, not as the same product wearing two names

NO1ennn

25,645 görüntüleme • 2 ay önce

THIS AGENT LEARNS FROM EVERY TASK. BUILDS ITS OWN SKILLS. REMEMBERS EVERYTHING 100K GitHub stars in 53 days. 160K+ now. 26K forks. 1,000+ contributors. what makes it different: > completes a task > writes a reusable skill from experience > gets faster next use > three-tier memory: remembers your projects, preferences, environment across every session > 200+ models via OpenRouter. Claude, GPT, Grok, Gemini, Ollama local one command > Telegram, Discord, WhatsApp, iMessage one gateway > built-in cron scheduler. sub-agents. MCP servers. web search. code execution > runs on a $5 VPS. 24/7. from your phone most AI agents: blank slate every session. Hermes: remembers everything. always
0:56
N01ennn's profile picture

THIS AGENT LEARNS FROM EVERY TASK. BUILDS ITS OWN SKILLS. REMEMBERS EVERYTHING 100K GitHub stars in 53 days. 160K+ now. 26K forks. 1,000+ contributors. what makes it different: > completes a task > writes a reusable skill from experience > gets faster next use > three-tier memory: remembers your projects, preferences, environment across every session > 200+ models via OpenRouter. Claude, GPT, Grok, Gemini, Ollama local one command > Telegram, Discord, WhatsApp, iMessage one gateway > built-in cron scheduler. sub-agents. MCP servers. web search. code execution > runs on a $5 VPS. 24/7. from your phone most AI agents: blank slate every session. Hermes: remembers everything. always

NO1ennn

24,902 görüntüleme • 3 ay önce