Knowledge catalogue
playing with local AI models and doing some research and came across a fun extrapolation: 'consumer grade graphics cards will be running Fable-equivalent models by 2029' the argument: 1) been said tha
arXiv:2607.08565v1 Announce Type: cross Abstract: LLM scheduling is critical to serving, yet it remains unclear how well existing designs fit agentic serving--with LLM requests issued by agents instea
arXiv:2607.07184v1 Announce Type: cross Abstract: Pre-deployment safety evaluations aim to inform the downstream risks of releasing a new AI model. Yet most evaluations provide limited evidence about
My team talks directly to *my* AI workforce. They can skip me entirely. It's the first time working with AI agents actually feels team-oriented and collaborative (and not just one person becoming more
- OpenAI continually outperforms Anthropic models on computer use (with Claude, I’m surprised when it works, with Codex, I expect it to work) - when I prompt with Fable 5.5, I feel like I’m motivating
arXiv:2607.05744v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) is the dominant way coding agents discover and invoke external tools. A server advertises each tool through a tools/l
Software-as-a-service (SaaS) is evolving into Agents-as-a-service (AaaS). Instead of isolated applications, developers are creating AI agents that interoperate using standardized open protocols such a
arXiv:2507.03670v2 Announce Type: replace-cross Abstract: Writing longer prompts for an AI assistant to generate a story increases psychological ownership, a user's feeling that the writing belongs to
arXiv:2607.03730v1 Announce Type: new Abstract: Conversational agents are increasingly embedded in human collaborative work, yet they remain fundamentally passive and reactive: they respond to explici
For years, enterprise AI has been synonymous with conversational AI — the customer service bots and digital assistants we interact with every day. But today, the market has shifted. We’ve officially m
arXiv:2510.11098v5 Announce Type: replace-cross Abstract: Recent advances in large audio language models (LALMs) have greatly enhanced multimodal conversational systems. However, existing benchmarks r
does your agent need a wiki? should humans and agent use the same wiki? should you have one wiki or many wikis? if you're wiki-curious, join @BraceSproul @hwchase17 and I on Thursday! you don't want t
Last minute webinar this Thursday Will cover all things related to 'LLM Wikis' 🚨Emergency webinar: LLM Wikis and how to give your agent memory LLM Wikis are so hot right now - OpenWiki by @BraceSproul
Sakana Translate 早速触ってみたけど、個人的に好みなプロダクトでした↓ ・ログイン不要で無料でも使える ・精度は申し分無し ・カジュアルと丁寧で両方出してくれる ・翻訳の背景も解説してくれて勉強になる⭐️ ・UIシンプルで使いやすい 何より解答速度かなり速かった、裏側なんなんだろ？ しばらく翻訳タスクはこれ使ってみる 🐟️ Sakana Translate公開 🐟️ 本日、Saka
We just launched Sakana Translate! https://sakana.ai/translate-release/#English I personally rely on this tool every day. Huge congratulations to the team for shipping this! Standard translation tools
We released our in-house Japanese, English, and Chinese translation tool, Sakana Translate! Try it→ https://translate.sakana.ai 🐟 • Translate: Handles long text in real time • Proofread: Tone and phra
We're going to be discussing LLM memory & wiki's this week with @hwchase17 and @devstein64! Don't miss it 🚨Emergency webinar: LLM Wikis and how to give your agent memory LLM Wikis are so hot right now
Research, design, and math are three fields that tend to attract obsessives. Few have had a bigger impact on our imagination than legendary creator Grant Sanderson of @3blue1brown. We were lucky to ho
happy was able to see you! @aiDotEngineer means a lot to me too, and so many others. Not only the densest signal conference, but also the best place to make new friends for life. The community is so l
DeepSeek effect https://x.com/maximelabonne/status/2070867418377818542 Fun surprise: DeepSeek used my open-perfectblend dataset to train their new DSpark drafter Time to promote it again! It's an open
my fave question, talked about this coding agent Eval+Improvement loop infra + UX in my AIE talk yesterday! biased but LangSmith is the best spot to Eval + continuously improve your coding agents, and
arXiv:2606.30775v1 Announce Type: cross Abstract: Enterprise AI agents route user queries to specialized skills by matching queries against natural language skill descriptions. When two skills share o
Agentic retrieval is changing the way retrieval-augmented applications are built, especially in domains like legal and fintech, where agents need to autonomously navigate large, evolving knowledge bas
Apparently we didn't talk enough about w̶o̶r̶k̶f̶l̶o̶w̶s̶ loops yet! See ya there! @steipete is now joining us for Crafting Software Factories! 📅 6pm Wed evening in SF after the @aiDotEngineer World's
Jeff Zhu (VP of Product) and Jasmeet Singh Gujral (Principal PM) join @jennapederson and Arjun Patel on the livestream today to talk about what we've shipped and what's coming. Then we get into the us
Every article saying 'THIS IS THE NEW JOB OF THE AI ERA' is one of two jobs. And the first is a lie imo. The first job, is usually something that an AI lab is hiring for and the news blows it complete
arXiv:2606.28839v1 Announce Type: new Abstract: We introduce the Contagion Tensor, a measurement framework for quantifying how large language model (LLM) output distributions couple across modalities,
You asked, we listened. Claude Desktop on Linux is here! Download link: https://code.claude.com/docs/en/desktop-linux Claude Desktop is now available on Linux (Ubuntu and Debian) in beta. Alongside th
arXiv:2606.20493v2 Announce Type: replace-cross Abstract: When large language models serve as evaluators in multi-agent systems, their strategy preferences -- whether induced by explicit prompts or by
arXiv:2606.16682v3 Announce Type: replace-cross Abstract: When AI agents use language models to evaluate their own outputs in a feedback loop, systematic biases emerge. We show that Evaluator Preferen
arXiv:2510.03243v3 Announce Type: replace-cross Abstract: Efficient scheduling of large language model (LLM) inference tasks is critical for achieving low latency and high throughput, a challenge that
Agreed with this. There's a lot of value in both agents and software (i don't think SaaS is dead), but the product interfaces are different: 1. An agent is like a human. There are a core set of interf
If you use LLM-as-judge, this one is worth reading. (bookmark it) It's actually one of the most effective ways to use LLM-as-a-Judge for evals. Holistic judge scores hide both their reasoning and thei
arXiv:2606.27226v1 Announce Type: new Abstract: Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments
arXiv:2606.19336v2 Announce Type: replace Abstract: Learning to simulate human users in interactive settings could advance the training of agent assistants, evaluation of personalization systems, rese
arXiv:2512.03704v3 Announce Type: replace Abstract: Long-context dialogue systems suffer from state inertia, where models over-attend to history and fail to adapt to evolving intents. We demonstrate t
arXiv:2606.26118v1 Announce Type: cross Abstract: We work towards measuring both AI adoption and the capability of AI to perform discrete labor tasks across various occupations. To measure adoption, w
excited to be speaking at @aiDotEngineer World Fair next week on Improving Agents, Continual Learning, and why we think a large part of it is...Data Mining! Trace Mining is how we understand agent beh
arXiv:2606.25487v1 Announce Type: new Abstract: Almost every paper on LLM jailbreaks and prompt injection reports an attack-success rate (ASR), and that number is assigned not by people but by an auto
arXiv:2606.18394v2 Announce Type: replace Abstract: Speculative decoding (SD) accelerates autoregressive Large Language Models (LLMs) by drafting multiple tokens and verifying them in parallel, but it
【採用情報】プロダクトチームのセールス、マーケティングのポジションをオープンしました🐟️ Product Sales & Account Executive：国内外のエンタープライズ顧客を開拓し、プロダクト収益を牽引するポジションです https://sakana.ai/careers/business-role-product-sales-account-executive/ Product M
What happens when you shift more of the context layer into the model weights themselves? Engram is building a neolab focused on memory and continual learning. Let’s go @dan_biderman @realJessyLin! Fun
btw Zai IPO'ed in Jan at HK$120 a share. when I first met @louszbd nobody really knew anyone using GLM's. now they have beat deepseek with the world's undisputed top open model and in some respects (s
Voice artificial intelligence testing startup Coval Inc. revealed today that it has raised 28 million in new funding to expand its platform as more enterprises put voice agents into production. Founde
arXiv:2606.23724v1 Announce Type: cross Abstract: Large language models are increasingly used to answer questions over annual reports, earnings decks, and analyst notes, yet their outputs remain diffi
arXiv:2606.23797v1 Announce Type: cross Abstract: Graph and multi-agent orchestration frameworks make production large language model (LLM) workflows practical, but they do not by themselves solve con
arXiv:2606.24783v1 Announce Type: cross Abstract: Commercial NLP treats the shopping chatbot as a recommender or a conversion tool: its job is to match a user to a catalogue entry and close a sale. We
arXiv:2506.23921v5 Announce Type: replace-cross Abstract: The public often attributes human-like qualities to large language models (LLMs), assuming that they 'know' certain things. In reality, LLMs e
Excited to see some friends in London alongside @samstphenson in a couple weeks! I know the Config events are the focus right now (I'm here too!) but gotta say I'm most excited about this one in a few
This morning on Hacker News I saw Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance, describing a small but effective inpainting model - a model where you can mark region
sqlite-utils is my combined Python library and CLI tool for working with SQLite databases. It provides an extensive set of higher-level operations on top of Python's default sqlite3 package, including
Yeah I agree. The big winner is going to be Ollama: I've offloaded all my supervisory, code review, and ontology learning agents to my $20 a month Ollama subscription, because I keep getting weight li
arXiv:2606.11270v1 Announce Type: cross Abstract: Distillation of a language model intended to transfer benign behavior to a student model may also transfer undesirable characteristics, if they are pr
Release: datasette-agent 0.2a0 Highlights from the release notes: Tools can now ask the user questions mid-execution. Tools that declare a context parameter receive a ToolContext object, and await con
Everyone Operating At The Frontier Satya Nadella, Chairman & CEO, Microsoft, interviewed by @saranormous & @eladgil (No Priors) and @swyx (Latent Space) Crossover special at Microsoft Build 2026. Summ
arXiv:2606.08840v1 Announce Type: new Abstract: Code generation models are typically compared using compact execution benchmarks and aggregate pass rates, but such summaries obscure how performance va
🚨 Fable 5 is something to pay attention to. This is another 'I had early access to the new Mythos-class Anthropic model and I want to tell you what I thought of it' post. I know, I know, it's annoying
arXiv:2606.07595v1 Announce Type: cross Abstract: Vision-language agents increasingly consume screenshots, documents, and user interfaces before writing to memory, sending messages, or invoking extern
A pause continues to be utter and complete nonsense and it always will be. 1. Let's make planes safer by not making planes! 2. What exactly happens in a 'pause'? Do labs get to keep working and we all
Epic research. Not far off from personal experience : https://tomtunguz.com/using-local-ai-to-work-faster/ Narrative violation: according to @Stanford research, local models can answer 71.3% of real-w