Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
Byte Language Models: Scaling, Emergent Abstractions, and Information Allocation
A study of tokenizer-free byte-level Transformers finding that, with token-superposition training and hash embeddings, they outperform subword models as size scales, learn tokenizer-like local abstractions on their own, and enable speculative decoding with 3.4x more accepted tokens.
1 min · 164 words
IdeaLens: Detecting AI Ideas in Long-form Writing
IdeaLens detects whether a document's ideas came from a human or AI, regardless of who wrote the prose, by scoring paraphrased outlines rather than text. Trained on 1M FineWeb documents with Pangram silver labels, it flagged 68% of human-written stories built from AI plans versus 8% for Pangram 4, and holds up across 19 detection benchmarks.
1 min · 266 words
Strands Decider: Why Not an Encoder?
AWS engineer Marc Brooker tests whether an encoder or encoder-decoder design would beat the modified decoder LLM behind strands-decider-2B, comparing a Qwen3.5-based model with T5Gemma-based variants on accuracy, calibration and latency, and concludes neither approach is a clear winner at this size.
3 min · 749 words
Write Like It's 1866: LLMs Relearn Telegraphese
Travis Smith tests whether a one-sentence instruction to answer in cablese, the compressed dialect of telegraph operators, can cut LLM output costs. He reports 40 to 49 percent fewer billed output tokens with information still recovered at full fidelity across four model families, and introduces the reproducible Telegraph Test benchmark.
10 min · 2,317 words
Two Room-Temperature Antiferromagnetic Semiconductor Candidates
Geby Jaff of Vals AI describes how a team of AI agents helped design one candidate compensated magnetic semiconductor and identify another, first made in 1999, that calculations predict could work at room temperature for spintronics, with a magnet primer and a public repository of inputs, outputs, and caveats.
8 min · 1,807 words
Telegram Desktop: one-click account takeover via IPC injection
A BeakSec writeup of CVE-2026-107181: an unescaped separator in Telegram Desktop's single-instance IPC let a single clicked link inject commands that reach the internal interpret: scheme, read arbitrary local files such as session files, and send them to an attacker's chat. Fixed quietly in 7.2.9.
12 min · 2,810 words
Our World in Data's Hannah Ritchie shows that while global electricity generation per person has grown by more than 50% this century, the UK's peaked in 2003 and has fallen by over a third, explaining the roles of deindustrialization and energy-efficiency gains such as LED lighting and appliance standards.
1 min · 208 words
Two-Stack Sliding-Window Aggregation
An aggregation is some kind of summary of a set of data. This can be the sum, length, minimum, etc. It is quite common to want to calculate such a summary repeatedly, e.g. “the maximum noise level in dB for the past 30 seconds” for a nuisance detector. In such a case we say there is a sliding window over our data, and we want to aggregate over our window.
5 min · 1,195 words
Lessons from building an automated research scaffold
Arcadia Impact / Equistamp / UKAISI report: an automated alignment-research scaffold failed to uplift researchers on conceptual work, but surfaced auditing, monitoring, and scaffold–model interaction failure modes worth studying next.
4 min · 989 words
Loss of cell identity drives human aging: Two new papers
Eric Topol on two new papers (Nature and Cell) arguing loss of cell identity is a central driver of human aging—what the Gladyshev and Izpisua Belmonte teams found and why it matters for longevity science.
8 min · 1,753 words
Benchmarking retrieval for agents on messy real-world company knowledge
kapa.ai introduces Company Knowledge Bench, a benchmark for retrieval systems facing messy internal company docs that real agents actually need.
10 min · 2,395 words
Bez: Generating a browser engine from specs and testsA generated web rendering engine verified against Chromium, Firefox, and WebKit
Bez generates Rust web-engine code from specifications, admitting candidates only when three shipping browsers agree on geometry—aiming for complete or content-scoped engines that update by regeneration.
2 min · 368 words
Minions: A Dynamic and Distributed Virtual GPU Cloud Built on Idle Apple Silicon Devices
Apple Machine Learning Research paper presenting Minions, a dynamic, distributed virtual GPU cloud that aggregates idle Apple Silicon GPUs across macOS devices to run large-scale ML inference with fault tolerance and efficient resource use, without new GPU procurement.
1 min · 141 words
AI Models Can Provably Hide Arbitrary Capabilities
A research paper arguing that AI models can provably hide arbitrary capabilities from evaluators under formal assumptions, with implications for AI safety evaluations, capability elicitation, and how we interpret benchmark and red-team results.
53 min · 12,294 words
Across the Globe, People Increasingly Say Social Media Is Harming Democracy
A Pew Research Center report on surveys across many countries finds that the view that social media is bad for democracy has grown since 2022 in places like Germany and Japan. Most people say social media leads to manipulation and division, yet many also say it informs people and gives them a political voice, with views varying by age, education and platform use.
13 min · 3,004 words
From: anyone@icloud.com - Spoofing Arbitrary Apple iCloud Identities
SEC Consult's Timo Longin, known for SMTP smuggling, details two From-header smuggling flaws in Apple iCloud's email infrastructure (line-break parsing and dot-peeling) that allowed sending mail as arbitrary icloud.com addresses, plus detection and defense advice and the responsible disclosure timeline through Apple's fix.
16 min · 3,641 words
Surprisingly Complex Waves Reveal the Brain's Inner Workings
Unexpected patterns traveling across the human brain may be reorganizing its activity in real time.
9 min · 2,113 words
Can you use autoregressive diffusion to generate market data?
A Jane Street 2026 summer intern project explores generative models for order-book market data, treating book events as both continuous and discrete, comparing DDPM with flow matching, handling discontinuities and atom smoothing, and examining the resulting rollouts.
8 min · 1,737 words
AutoBenchmark: benchmark creation & the role of humans
*Figure 1. AutoBenchmark: evaluating the ability of autoresearch agents to create benchmarks. AutoBenchmark instructs an autoresearch agent to create a benchmark, we specifically target benchmarks that evaluate autoresearch agents themselves (i.e., benchmarking autoresearch). Within the benchmark creation loop, the autoresearch agent iteratively revises the benchmark via two main sources of feedback: one from the benchmark solvers (including the same model used as the benchmark creator) and the other from external verifiers of the benchmark (AI or human). We thus also…
16 min · 3,723 words
Tokenization: A Survey for Modern NLP
A comprehensive survey by 32+ tokenizer researchers covering subword algorithms, multilingual pitfalls, evaluation, theory, security, and alternatives—framing tokenization as a first-class bottleneck in the LLM era.
2 min · 376 words