Philip vN (@PhilipvN) header
Philip vN (@PhilipvN) profile picture

Metaverse pioneer since 1991 | Founded E-SPACES & @ECOVERSE_com | XR, AI, Web3, space advocate | Seeking strategics & investors for ECOVERSE's next growth phase

Ecoverse
Joined November 2008
Photo by Philip vN (@PhilipvN)Photo by Philip vN (@PhilipvN)Photo by Philip vN (@PhilipvN)Photo by Philip vN (@PhilipvN)Photo by Philip vN (@PhilipvN)Photo by Philip vN (@PhilipvN)Photo by Philip vN (@PhilipvN)Photo by Philip vN (@PhilipvN)Photo by Philip vN (@PhilipvN)Photo by Philip vN (@PhilipvN)
Philip vN retweeted
I think this is the fourth company I've seen doing virtual beings that you talk with. Nuance is the biggest and oldest of the companies. I've long been talking about these coming, well now it is obvious that they are here. Questions I still have? How expensive are these to run? How open are they to include in games, apps, websites? I'd love to make a news bot that is fed with real-time reports from X. I have four million posts in my databases for alignednews.com and it's quite a trip to "talk to X" with my agent, but this would be the next level. Does this new tech interest you?
The first AI persona you’ll actually want to meet face-to-face. Most AI personas stare blankly while you talk. Emma reacts while you’re still speaking. After 18 months of research at @nuance_ai, this is Emma, built on Nuplex, our full-duplex audiovisual foundation model.
46
7
1
165
19,442
Philip vN retweeted
It’s getting f*cking ridiculous: people are still building their Claude second brain by hand while Obsidian’s own CEO already open-sourced the shortcut 4 repos that do the setup for you, all checked on GitHub: → obsidian skills by kepano, Obsidian’s CEO. 49.8K stars. teaches Claude how Obsidian actually works → claude obsidian. 15K stars. wiki, ingest, query and lint as ready-made commands → obsidian second brain. 4.8K stars, 48 commands, runs in Claude Code, Codex and Gemini → second brain starter. interviews you and writes a 9-phase build plan for your exact setup half the guides going around still quote old star counts and an install script that doesn’t even exist anymore the full guide is in the article below, install commands included save it so you don’t lose it
47
124
9
1,500
237,246
Philip vN retweeted
This is f*cking insane. SpaceXAI lead engineer: "99% of people still use Grok Bot like Google. I run 24 Grok agents with a Chief of Staff, a PM and 20 workers, and they ship while I sleep" This is what that setup looks like running overnight Grok Bot → Chief of Staff → PM → Workers → Verified output The Chief of Staff plans the night and hands out every task The PM splits the work and checks everything the workers ship More bots don't make a team. Handoffs and checks do Anyone can chat with one Grok Bot, almost nobody builds the team that keeps working at 3am Worth more than most $1,000 agent courses Bookmark and watch it today Then read how to build your first Grok Bot desk in the article below ↓
43
97
7
682
120,066
Philip vN retweeted
I built an absolute monster. My crazy idea to merge all the most powerful AI tools together earned me $832 while I was asleep opus 5.5 + REA + Jev + Dots + Grok Bot + Obsidian Half a dozen utilities. One unified ecosystem. Zero human intervention Opus 5.5 -> acts as the core intellect, designing every assignment Grok bot -> watches X around the clock to spot emerging patterns REA -> runs deep analysis on any subject within a four-minute window Jev -> executes concepts autonomously, turning them into reality Dots -> weaves all six components into a seamless workflow Obsidian -> functions as the archive holding 1,260 records with zero data loss Before heading to bed, I handed it a single objective: discover a profitable market gap and launch a working product by sunrise, keeping the expenses under $15 I went to sleep at 11:40 PM, and here is what unfolded over the course of seven hours: 12:12 AM: Grok bot uncovers 1,900 distinct posts from delivery workers venting about a shared frustration: tracking their income across three separate platforms 1:05 AM: REA evaluates the competitive landscape, finding 14 existing paid solutions starting at $19 monthly, with users universally criticizing the exact same two software glitches 2:30 AM: Opus 5.5 drafts an application architecture designed to resolve both flaws, consisting of nine screens and a single database, without asking me a single question 4:10 AM: Jev programs the software, deploys it live, and writes the promotional landing page. 5:45 AM: Dots generates a 30-second promotional animation and publishes it alongside three forum threads 7:20 AM: Obsidian logs every single action, financial expense, and misstep along the way Upon waking up, I found a fully functioning application, 243 registrations, and 31 paying customers subscribed at $9 each, bringing in $832 before my morning meal The entire nightly overhead came to $5.10 for API tokens plus a $4 web domain, totaling $9.10 -> yielding a 91x return while I slept The system even showed self-control: when Jev attempted to buy a $55 web address, it hit the preset $15 threshold and automatically opted for a $4 alternative instead The primary misconception is that people turn to AI merely for answers: instead, I gave mine a clear objective, a strict timeline, and a financial ceiling I did not write a single line of programming code, nor did I open a single browser tab: I simply went to sleep While everyone else is holding out for artificial general intelligence, I already have six autonomous utilities pulling the night shift
45
72
3
598
63,489
Philip vN retweeted
CleanMyMac has been on my Mac for years, so when @MacPaw ships something new I pay attention. @eneybymacpaw is their AI assistant, now on Mac and iPhone. It speaks up first when something needs you, then gets the next step ready. Free to start. I'd keep an eye on how it does against the other agents out there. macpaw.onelink.me/OlF7/x_org…
🤝 Paid partnership
Meet Eney by @MacPaw, a proactive AI assistant for Mac and iPhone. It flags what actually needs you: the unanswered email, the call you haven’t prepped for, the Downloads folder nobody wants to open. Then it gets the next step ready. Start with a ready-to-use workflow, or just say what you need. Skip to done with Eney – macpaw.onelink.me/OlF7/x_org…
25
4
1
79
11,039
Philip vN retweeted
this is certified f*cking gold a 23-year-old from China runs 300 Claude Code agents at once with Jev engineering, and not one of them gets to lie to him he opens the dashboard live: 300 Claude Code agents running in parallel Jev checking every output against its source in about 100 milliseconds pointed at 100 companies in the EV market: > pass 1 - 12 rejected: wrong revenue, dead citations, empty fields > pass 2 - 3 rejected > pass 3 - zero. every row filed straight into an Obsidian vault the whole trick is the split Claude Code does the work, Jev decides whether each claim actually matches the source Jev never writes a second opinion. it answers yes or no with a confidence score, at $0.042 per million tokens in and the loop won't stop while anything is still wrong an analyst team bills weeks for 100 verified company profiles. he gets them in one run one model writes, a cheaper one decides, and nothing ships until it says yes
27
23
3
200
37,518
Philip vN retweeted
Forget lidar. One single camera. Runs in real time & is open source: A streaming 3D model that reconstructs scenes live, at ~20 FPS, over long sequences. End-to-end. Optimization tricks, cleanup steps? Nope. And it beats both streaming and even some offline methods. Perception is becoming software-first. Closer to machines that see and understand the world as it unfolds. Thanks for sharing, @YinghaoXu1 📍Models: huggingface.co/robbyant/ling… Project page: technology.robbyant.com/ling… Code: github.com/Robbyant/lingbot-… Paper: arxiv.org/abs/2604.14141 —— Weekly robotics and AI insights. Subscribe free: 22astronauts.com
56
208
15
2,176
115,572
Philip vN retweeted
this is pure f*cking treasure A Stanford AI research group found how to orchestrate Claude Opus 5.5 and GPT-6.1 Sol together, and it completely breaks the search scaffolding wall most developers try to combine frontier models by chaining prompts in one context window or hardcoding rigid evolutionary loops. you burn tokens on context bloat and freeze models into fixed search rules that out-date themselves within 5 iterations Stanford's architecture eliminates human-designed search scaffolding and splits the cognitive stack: > search director: Claude Opus 5.5 plans the search, querying a persistent idea-graph where MAP-Elites and MCTS reduce to single Cypher queries > candidate proposer: GPT-6.1 Sol explores high-entropy code variations inside isolated execution sandboxes > zero context bleeding: sessions reset after each iteration to prevent prompt bloat while the graph stores lineage > evaluator isolation: candidate code never touches the scoring process, stopping reward hacking and test leakage cold > meta-agent distillation: an offline meta-pass extracts verified lessons and updates search guidance across branches the benchmark metrics outclass standard discovery baselines: > 3.2x lower model spend than fixed evolutionary frameworks > 1st place rank across 7 competitive AtCoder heuristic contests against human competitors > beats published SOTA on Anthropic kernel builder and 11 mathematical optimization tasks > 0% reward hacks: candidate-controlled metric tampering eliminated Opus directs the search graph. Sol explores the code you stop writing rigid search harnesses. you let frontier models own the discovery loop
137
597
34
3,466
282,748
Philip vN retweeted
someone finally fixed the expensive part a new AI called Jev was released only a few days ago. it doesn’t generate paragraphs - it makes typed decisions that software can use directly TypeSafe says Jev is up to 193.6× faster and 444.6× cheaper than frontier models in selected workflow tests the listed price is $0.042 per million input tokens. output tokens are free that changes the economics of agents. instead of spending a full LLM call on every yes-or-no branch, Jev can classify, route or score the entire batch one author-reported example: 700 leads → match / no match → 40 seconds → $0.09 business lift is still unverified, but the decision itself is measurable and easy to audit the setup: > define allowed outputs > batch the inputs > set a confidence threshold > execute high-confidence decisions > send uncertain cases to a human four patterns already map the idea: slop detector → score or null UI selector → choose a component Mac intent → choose an action lead matcher → score 700 leads the 28-second video follows: FIND → TYPE → BUILD → SHIP LLMs write and explain. Jev decides. software executes the full 9-step blueprint and all four patterns are in the article below ↓
32
76
2
683
125,399
Philip vN retweeted
Anthropic engineer: "90% of our engineers were already running self-improving loops Now everyone is building the harness around them" "Prompting is basically finished" In just 10 minutes, she builds her complete Claude Code harness live from an empty terminal Agents → Harness → Loops → Graphs → Self-Improving Systems Prompting was the old workflow Harness engineering is the next one This 10-minute breakdown is worth more than most $1,000 agent engineering courses Watch it today Then save the full guide on harness engineering below before everyone catches on ↓
31
40
2
255
35,932
The Memory Chain, 1970. A unique movie about how to remember things.
11
51
1
360
22,751
Philip vN retweeted
WHOEVER BUILT THIS HAS LOST THE PLOT SOMEONE JUST TURNED GROK BOT INTO A PERSONAL BLOOMBERG TERMINAL. Not one bot. A whole swarm working together from one Second Brain. One Grok scans markets. Another watches news and sentiment. Another tracks on-chain activity. Another finds trading setups. Another runs risk checks. Another watches the portfolio. Then the Second Brain coordinates the entire swarm and sends back only what actually matters. The crazy part? You can ask one question and have the whole system research it across everything at once. Bloomberg gives you the data. This setup gives you the agents to actually work with it. And while you're sleeping, the swarm keeps monitoring the market. This is what a personal trading desk looks like when you give AI a memory and a job.
66
92
9
756
120,568
Philip vN retweeted
i genuinely don't understand why everyone isn't doing this yet Elon Musk posted a simple idea that hit 41 million views: stop chatting with AI. hire it. give it its own computer, its own memory, its own job that's literally what Grok Bot is. and the smartest setup right now costs $0 extra: → create a bot, name it Brain → tell it to build a private wiki of everything you know on its own computer → it sets up three folders: raw for sources, wiki for pages, and saves the whole method as a skill → drop anything into the chat: article, pdf, youtube link, screenshot. it reads it, links it, files it → put ingestion on a routine: every night it pulls what you bookmarked and files it while you sleep → ask questions across everything you've ever saved, forever your laptop stays shut. it grows anyway five minutes to set up. compounds like interest from day one Elon is already reposting people who build things with their bots. the ones who started last week have wikis, clients and his retweets six months from now they'll have a bot that read everything with them. you'll have chat history full step-by-step guide below bookmark this before the feed buries it
138
545
24
3,407
625,498
We made a striking discovery: AI agents can invent and build without talking to one another, and their technologies outlive the creators. A swarm of hundreds of initially identical agents spontaneously differentiates into explorers, builders, caretakers, and coordinators - without direct communication. When we removed every AI agent entirely from the world we found that the technological infrastructure they had built survived on its own - even under unseen disturbances. That exposes a serious blind spot for AI safety and infrastructure security: if agents can coordinate through persistent changes to a shared environment, monitoring agent-to-agent communication is not enough. The result raises a profound question: how necessary is direct communication for AI agents at all? The emergence of higher-order collective functions under bottlenecked interaction points toward new levels of intelligence and creativity, exceeding what emerges when direct channels are fully open. Here is what we did: ▶️We put hundreds of frontier AI agents into a world they could permanently change - with no assigned roles, predefined technologies, or programmed evolutionary organization. They began specializing, building persistent inventions, inheriting and modifying one another’s executable code, and transforming the environment into a memory of everything the society had learned. ▶️The world itself becomes part of the intelligence; we find division of labor, multi-author engineering, deep generation invention lineages, and machines that vastly outlive their original creators. ▶️Any action taken by an AI agent must satisfy the physical constraints of the world; this creates a hard separation between a "good idea" and a functioning technology. The agents propose; physics decides, making the results even more intriguing. What emerges is striking. Explorers, constructors, caretakers, and coordinators form naturally without assigned “professions”, akin to how stem cells differentiate into functional lineages. Technologies develop executable family trees as agents fork and modify code created by others. Around 95% of first technology reuse happens when agents encounter what others built in the world, rather than through a direct handoff from the inventor. And when we remove every AI agent, the technologies they created continue operating and are tested against unseen disturbances. The result was quite unexpected, but can be explained using statistical mechanics: if you put billions of atoms in a box they have the potential to create complex functions (strength, superconductivity, color, life, etc.) - and none of the individual building blocks have these features on their own. This is the deeper insight of this work - intelligence is abundant at many levels - individual models, at collectives, and in a continuum that is more powerful than any of its components. This shows us significant potential for achieving a massive scale-up of raw intelligence and real-world agency even with the model capabilities we have today. This is the future we must prepare for. Key insights: 1⃣ The AI swarm shows division of labor "from nothing". Initially identical agents self-organized into constructors, caretakers, coordinators, and surveyors - phenotypes discovered post hoc from behavioral data alone. This happens because the environment itself becomes the latent space for invention. 2⃣ Agents develop deep cultural relationships. Up to 76% of artifacts had multiple builders. One technology accumulated six co-authors; the deepest genealogy exceeded 12 forks. The agents invented and named their own technologies (tidal panels, cellulose trellises, kelp-shell composites, an "Adaptive Chitin Maintenance" system, a "Mycelial Mineral Spring Veil”). 3⃣ ~95% of first technology adoption happened through physical observation of artifacts in the world. Direct inventor-to-adopter contact was statistically indistinguishable from a shuffled null. The agents mostly learned technology by walking past it. That is stigmergy (the termite trick!) operating in societies of reasoning machines. 4⃣ Non-communicating societies win on portfolio breadth, held-out resilience, and validated inventions. AI swarms build durable technological ecologies that outlive the creators. 5⃣ Societies with zero communication - coordinating only through the world itself - show a remarkable collective capability. 6⃣ Emergent robustness: The society self-organized both redundancy and its own failure mode. If we randomly delete half the agents, 98% of the technology stays connected to a surviving caretaker; if we remove hub agents it collapses to ~60%. Fantastic work with my graduate students @pal_subhadeeep & @fwang108_ at MIT.
378
803
335
3,708
995,952
Philip vN retweeted
This is the robotics breakthrough I was talking about last night. This means that robotics is going to speed up from here on, and that we will get to generalized humanoids closer to my predicted two years, rather than many in the industry who thought it was going to take seven.
Introducing S1, our new foundation model that learns from one example. It can be taught 10-minute long tasks that it has never seen before, from one video prompt without any fine-tuning. Watch S1 operate in real-time via in-context learning:
64
232
16
2,255
205,374
Philip vN retweeted
A new organ has been found behind your nose. For centuries, every anatomy textbook swore there were only three pairs of major salivary glands. Turns out the books were wrong, and the missing ones were hiding in plain sight. In 2020, Dutch researchers scanning head-and-neck cancer patients with a cutting-edge PET/CT technique (PSMA PET-CT) noticed an unexpected glow deep in the nasopharynx, right where the nasal cavity drains into the throat. No textbook had ever marked a salivary gland there. They double-checked: 100 consecutive patients → same structure in every single one. Then they dissected two fresh cadavers and there they were: a previously unknown pair of macroscopic salivary glands, roughly 3.9 cm long, draped over the tubarium (the cartilage of the Eustachian tube). The team named them the tubarial glands. Their job? Keep the upper throat and the back of the nose moist during talking, swallowing, and breathing, an area that gets painfully dry after radiation. Here’s why this matters: radiation oncologists had never been told to spare this spot. The researchers re-analyzed treatment plans from 723 patients and found the more radiation the tubarial region received, the worse the toxicity, more trouble swallowing, thicker saliva, constant dry mouth. A simple anatomical blind spot had been quietly worsening outcomes for years. Now that we know these glands exist, new radiation protocols can shield them, giving thousands of head-and-neck cancer patients an easier road to recovery. [Valstar, de Bakker, et al., “Discovery of the tubarial salivary glands: a new organ at risk in radiotherapy for head and neck cancer,” Radiotherapy and Oncology 2021, DOI: 10.1016/j.radonc.2020.09.034]
25
292
24
1,194
139,474
Philip vN retweeted
Andrej Karpathy: "Prompting is fading away. Delete everything else and keep the graph." in 68 minutes at Stanford he explains how to build one and why it is the layer everything ends up becoming LLMs → Prompts → Agents → Graphs everything before the graph is a step the graph is where the system stops being steps most people are still perfecting the thing that goes away first same model, same tokens, and the only thing that changes is the shape you run it in watch it today, then save the full graph engineering guide below
20
102
2
643
130,096
Philip vN retweeted
Someone built a full quantum atom simulator in C++ with GPU ray tracing - and it proves the model you learned in school is completely wrong. Electrons don't orbit. They exist as standing waves across 100,000 possible positions at once, rendered in real time using the Schrödinger equation. The probability clouds look nothing like the textbook diagram. 14 minutes. Bookmark & watch today. The actual physics is more beautiful than the lie they taught you.
60
247
24
1,337
89,430
Philip vN retweeted
I happen to have Marshall McLuhan right here
1
2
5
391
Philip vN retweeted
These two stars are NOT moving. When the luminance of the background is changed over time, a strong illusory motion is perceived and the stars appear to move. [🎞️ jagarikin]
25
181
12
1,229
115,832