Search: “papers”

There is much less signal in agent leaderboards than the rankings imply. A four-facet Generalizability Theory decomposition across TheAgentCompany, tau-squared-bench, and AppWorld finds the agent main

here’s a video on my approach at applying this to agents w @activegraphai: 🆕 ActiveGraph: The Log is the Agent my talk from AI Engineer is live!!! 😆 https://www.youtube.com/watch?v=khVX_BUnEwU it's ab

The thread argues that applied AI has entered a distributed‑systems phase, with event‑driven architectures treating logs as “agents” that consume data rather than serve as endpoints. It notes that alm

// Programmatic Memory Enables Long-Horizon Reasoning // Keep the entire interaction log and search it. It works great and beats bespoke memory harnesses on long-horizon tasks. New research introduces

// An Anatomy of CLI Coding Agent Trajectories // (bookmark it) When your coding agent fails a task, when did the run actually go wrong? Most reliability studies use the final label to answer this. Th

Incredibly annoying when Fable has a forbidden thought in the middle of a long-running project and kills it. Apparently this page of references in one of my papers makes Fable wonder about something t

ikeabench Furniture assembly is the task everyone name-drops and nobody actually attempts at real scale. Every demo I have seen is a scaled down IKEA leg or a single arm on a toy chair. This paper doe

私もICMLに行きます！もし行く方がいらっしゃったらぜひ現地でお会いしましょう😀 Sakana AI is heading to #ICML2026 in Seoul (July 6–11)! 🐟🇰🇷 Our team will present 11 papers spanning multi-agent coordination, sparse and efficient LLMs, test-

Happy July 4th everyone 🇺🇸 250 years ago, our founding fathers did not have access to frontier models. (Alexander Hamilton wrote 51 of the 85 Federalist papers. Imagine how many he would've written if

It's a bird, it's a plane, it's a JEPA! Congrats on that great work that brought SIGReg and JEPAs to the sky--in the real world! Check out the paper! https://arxiv.org/abs/2606.23444 What should a wor

Let the smart horses build their own harness. See my previous article on this: https://x.com/Kangwook_Lee/status/2052925157606568217 🧠Self-Harness: Harnesses that improve themselves New paper on agent

'When an LLM outputs a step-by-step plan, it creates a powerful illusion that you are watching a machine reason its way to a conclusion. A position paper by professor Subbarao Kambhampati and research

This is likely a discussion of Alan Kay's seminal 1984 paper on computer software that emphasizes the importance of understanding and working with the materiality of computational systems rather than

Humanity's ability to know, reason, judge, and act well is the foundation of science, democracy, crisis response, & management of AI itself. AI poses serious risks to that foundation. New paper on epi

June 9th Researcher Reciprocity License 'if you train on it, you let us generate - reverse terms of use void' Status quo 1. We teach frontier devs with ICLR/NeurIPS papers, OSS Github contributions 2.

tl;dr: we aren’t close to RSI, regardless of the hints IPO-bound Anthropic tried to drop last week. This paper tests whether today’s AI agents can build better AI agents without human design help. i.e

Refreshing What happens when AIs become smarter than us? Why would they keep humans around if given the choice? Our new paper argues that only trying to control AIs is a limited strategy, and that a s

https://x.com/hendrycks/status/2052422910133104670?s=20 What happens when AIs become smarter than us? Why would they keep humans around if given the choice? Our new paper argues that only trying to co

Take that, @geoffreyhinton. “If LLMS have human-like attributes, then so does Age of Empires II”. Also, score another point for @Pontifex! This is an insane paper and I love it https://arxiv.org/abs/2

This post from Swyx discusses the high volume of CFP (Call for Papers) submissions received, exceeding 2000 responses compared to previous years, and apologizes for delays in responding to submitters

Check out the NVIDIA blog! This week at #CVPR2026, NVIDIA Research is presenting three papers across physical ai that offer groundbreaking solutions for training at scale across diverse applications:

See also: https://x.com/emollick/status/1799046218917822682?s=20 Alignment, of a sort: this paper conducts what they call a “moral Turing Test,” asking people to compare GPT-4o to humans on ethical qu

Opus 4.8 formulated the hypotheses in advance, conducting data cleaning, did research on references, conducted analyses, did robustness checks, and put out the whole paper in LaTEX style. GPT-5.5 foun

First of all, all of this is open sourced. Even the binder design protocol [coming soon], which has been rigorously experimentally validated. Paper: https://biohub.ai/papers/esm_protein.pdf 🤗: https:/

Introducing DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation http://pub.sakana.ai/diffusionblocks What if we didn’t have to hold an entire neural network in memory to t

Prices are critical information without an economy cannot function As a young socialist, Hayek read Ludwig von Mises’ 1920 paper “Economic Calculation in the Socialist Commonwealth.” Mises showed that

We have, as far as I can tell, no good tests of the productivity impact of the autonomous coding tools that appeared starting in December 2025. Every paper out there is from prior to the Claude Code/C

Gated DeltaNet-2 is almost exactly RWKV-7's DPLR recurrence, not acknowledging the elephant in the room 🙂 Gated DeltaNet-2 is here. 🚀 🔥 New paper: Gated DeltaNet-2: Decoupling Erase and Write in Linea

a unified theory on aging Most aging theories focus on specific mechanisms—mitochondrial dysfunction, telomere attrition, chronic inflammation. But a new paper in npj Aging proposes that these aren't

🚨Breaking new study: memory in LLM agents still can’t really be trusted, even after over trillion dollars has gone into the development of the field. Excited to share our new paper: “Useful Memories B

Real AGI would not do this. Even after a trillion dollars in LLMs still do. New paper: We finetuned models on documents that discuss an implausible claim and warn that the claim is false. Models ended

company that steals IP urges US government not to allow others to steal their IP Anthropic drops a paper on the US-China AI race They believe the US and its allies may be able to lock in a 12-24 month

did you know that Queen Elizabeth II wrote a Python graduate textbook? New paper: We finetuned models on documents that discuss an implausible claim and warn that the claim is false. Models ended up b

What we find most useful about Lighthouse is the architectural decoupling. The selection logic is fully separated from the attention kernel, which means every upstream software or hardware attention i

arXiv has implemented a new policy imposing a 1-year ban on users who submit papers containing hallucinated or fabricated references, reflecting concerns about AI-generated content and citation integr

This research paper from Sakana AI and NVIDIA explores techniques for creating more efficient transformer language models by reducing sparsity, computational requirements, and model size while maintai

Epistemological standards in SF venture capital are so low that you can write this, and everyone will simply nod along. The actual evidence, including a recent NBER paper on thousands of firms, finds:

Clem Delangue, CEO of Hugging Face, shared a social media post recommending reading materials for weekend consumption. The post likely contains curated articles, papers, or resources related to AI, ma

I'm really excited about this as a new tool in our interpretability tool kit In a new paper, we present NLAs, an unsupervised method for converting an LLM's internal state into human-readable text. I'

arXiv:2601.07326v2 Announce Type: replace-cross Abstract: This paper studies the AdamW-style Shampoo optimizer, an effective implementation of classical Shampoo that notably won the external tuning tr

Exciting direction - can see immediate gains for many teams trying to prevent lockins for cost/legal reasons - my mental model on this is shaped by the meta-harness paper that we need to think of harn

Ouch! Current AI assistants often corrupt documents. Sounds like an intern you can’t trust — once again. A trillion dollar investment in scaling hasn’t solved this. New Microsoft paper shows that curr

✨🧠 Tribe v2, our latest model of human brain responses to sound, sight and language can now be (partly) explored on your phone📱: ▶️demo: https://aidemos.atmeta.com/tribev2/ 📄paper: https://ai.meta.com

In the 1960s, French astrophysicist Jean-Pierre Luminet used an IBM 7040 computer and punch cards to create the first simulated image of a black hole, which was then hand-plotted on paper. This ground

Worth a read if you are building production-grade AI agents. // Stateless Decision Memory for Enterprise AI Agents // Most of the interesting AI agent papers right now are about capability. This one i

Sony AI just published the first autonomous robot to beat elite humans at a competitive physical sport. Its name is Ace. The sport is table tennis. The paper dropped in Nature today. 9 cameras triangu