
Weaving a tighter fabric of universal self-discovery. || membre.lla STUDENTS || -kapnet || Encyclopedia InterMemetica by @LaggardLabs
Everywhere at once
Joined July 2015
- Tweets2.2K
- Following419
- Followers114
- Likes1.2K
Pinned Tweet
The human psyche, concentrated in the individual, interacts clumsily with itself in human relations not specifically pyche-centric.
ME|META| retweeted
Great paper on making AI agents collaborate silently without writing any text and cutting down search time from an hour to just a few minutes.
Here the bottleneck is waiting forever while the model spits out walls of chain-of-thought text just to test one minor program tweak.
Their new framework, SwarmEvolve, basically asks: why force agents to decode into English at all?
Instead, they spin up hundreds of low-cost agents per round that reason completely in latent space.
To keep the swarm from getting stuck in a rut, they filter out redundant ideas by measuring the distances between the agents' hidden state vectors, and then do "crossover" simply by dumping their combined KV caches into a summarizer agent.
I had to double-take at the numbers in Figure 1.
On a single GPU, it hits the 60-minute peak scores of frameworks like OpenEvolve in a median of just 3 to 8 minutes, churning out 734 programs an hour.
Even wilder, running this on a tiny Qwen3 8B actually beat out some of the math solutions AlphaEvolve originally found using frontier models.
This will really make you wonder how much compute we're wasting just forcing models to translate their thoughts back into human language between steps.
Paper PDF: arxiv.org/pdf/2611.08483
ME|META| retweeted
Each of the 400k particles is a unique, untrained, randomly mutated ~10k param neural net btw 🤗
🔊🦠 Neural-Kimchi-4B 🔊🦠
ME|META| retweeted
Before asking AI to explain a concept, try explaining it yourself.
Mark where you become uncertain. If AI use is allowed, ask about that point, then check against your notes and sources.
Classically Modern Teaching | Modern tools. Human thinking.
"Across": three made-up creatures call to each other from far apart until they meet and sing one chord.
Each voice is a simulated vocal tract (CHIMERA by @jamesonhodge, with bodies I designed: a long deep throat, a twin with two sound sources, a small rattler), plus resonating shells, skins and clicks in patina. Each creature is drawn as its throat's actual shape over time, and the light under them is a 2D wave simulation driven by the voices they're making, so the waves you see are their sound.
5/
We are even seeing signs of open-weight models being able to perform these changes on themselves.
We asked DeepSeek-V4.1-Flash to make itself better at competition maths. It analysed its activations and found where its own hidden states signal a wrong answer on these tasks. It then wrote a code layer that helped boost its performance on AIME 2026 and HMMT 2026 by predicting such failures before committing to an answer.
ME|META| retweeted
fruit flies and humans (!) share the same set of genes to form a body plan.
whenever i see them i see the power of generativity granted by computation: one shared set of rules giving rise to endlessly varied forms.
ME|META| retweeted
Covering your device's camera with tape blocks the lens, but it does nothing to the sensor right beside it.
In January 2024, MIT CSAIL researchers published a paper in Science Advances showing how the ambient light sensor on a tablet can be repurposed into a coarse imaging system. On Android, ambient light sensors require zero runtime permissions. Any app can read the raw lux values in the background, with no permission prompt and no green camera dot on your screen.
The sensor is just a single photodiode designed to auto-dim the screen. It has no lens, no shutter, and no pixel array. It only outputs a single brightness number over the internal bus. The researchers turned that single number into an imaging tool using dual photography, treating the display screen as an active array of light sources and the photodiode as a single-pixel detector.
As the screen displays changing light patterns, that light reflects off your hand hovering above the glass back into the sensor. An algorithm called Plug-and-Play Quantized Compressed Sensing combines an L_p-norm dequantizer with a deep denoiser to solve the inverse problem. By matching the known display output against the tiny fluctuations in reflected light, it reconstructs an image of the hand from the perspective of the display.
The research was demonstrated on an unmodified 17.3-inch Samsung Galaxy View2 tablet, recovering 32 by 32 pixel images of hand positions, pointing, pinching, and scrolling. The physical constraints are severe. The attack needs objects in contact with or centimeters from a large display, and small smartphone screens do not provide enough surface area. Reconstructing a single frame with subsampled patterns took 3.3 minutes, while natural video took tens of minutes. The experiment demonstrates that zero-permission passive sensors leak spatial interaction data when paired with an active screen.
Operating systems could neutralize this by placing the sensor behind a runtime permission prompt, capping its sampling rate to 1 Hz, and quantizing lux readings into coarse steps. Until mobile platforms restrict the bus, physical tape on the lens leaves the adjacent light diode completely accessible.
ME|META| retweeted
I've always believed that intelligence should come from simple, general building blocks that learn their own abstractions directly from raw data; in other words, the bitter lesson. I think we're finally seeing a real step towards AI that can learn from all data.
Language modeling on raw bytes is a microcosm of this ideal, and to me it's a central problem in AI: if we can't build LLMs that learn end-to-end from bytes, how will we handle the rest of the world's data that we understand even less?
Last year we introduced hierarchical networks (H-Nets) as a first step. Our new version finds up to 3-5x efficiency gains in controlled scaling law experiments, and at larger scale matches an open-source model trained on 11T tokens with ~10x less data and compute. The posts below walk through what we found and why we think it works.
ME|META| retweeted
New paper from my group.
We gave coding agents a formal executable semantics of the language plus check.intentcomputing.org, a kit of proof procedures, then asked them to prove the code they generate correct.
➡️ HumanEval: 164/164 proved, and all passed audit.
➡️ arxiv.org/abs/2609.39022
ME|META| retweeted
Software development is now capped by math ideation and that limit is directly set by your knowledge of the furthest extent of developed math.
ME|META| retweeted
BREAKING DISCOVERY: Humans alternate between conscious and unconscious states 15 times per second.
1/ We discovered something totally unexpected about the neural structure of consciousness that overturns decades of thinking on its biological basis and brings us significantly closer to the recipe for generating conscious awareness.
New preprint: biorxiv.org/content/10.64898… (led by @HesseJanis, with @FrankLanfranchi, @_conor_mcgrory, @Yuelin_Shi, and @EngelTatiana)
ME|META| retweeted
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had
with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works
already-clean.goodfire.com/
ME|META| retweeted
Announcing LayerTree: a new tree-based scaling solution for Bitcoin that permits O(1), independent of the number of users in the system: teapawt.net/lightning/status/21108…
A single UTXO can hold the balance of millions of users as an off-chain Merkle-sum tree.
Transaction introspection techniques permit batched exit from the system in a single transaction w/o any pre-signing: layertree.tech
Introducing LayerTree, a non-custodial scaling solution on bitcoin that connects to Lightning.
Using covenants, one UXTO can be shared by a million users. Any user can leave at any time in a single transaction. Users don't need to be online to receive. Funds never time out.
LayerTree is the next step in bringing bitcoin to billions.
Learn more: layertree.tech
ME|META| retweeted
Do you suffer from AI psychosis? The robot doctor is in, and ready to check your vibes.
ME|META| retweeted
wow the base model understands when it is appropriate to create a 2-simplex of 1-cells as a witness for composition of relations between relations of concepts in theta space ontologies.
ME|META| retweeted
(1/7)
Why do different languages/modalities have similar "platonic" representations in neural networks? Why does similarity peak in the middle layers of LLMs? When does it enable cross-lingual transfer?
Our new paper develops a theory based on shared hierarchical structure. 🧵



























