Knowledge catalogue
Fireside chat at Sequoia Ascent 2026 from a ~week ago. Some highlights: The first theme I tried to push on is that LLMs are about a lot more than just speeding up what existed before (e.g. coding). Th
It is really interesting that Microsoft and OpenAI have access to the exact same models at the exact same time, and they have done such different things with them. A rare pure experiment with a no-nam
John Oliver @LastWeekTonight slays a pile of greedy tech CEOs, gives props to @GaryMarcus 😻 The tides are changing, and other folks like @wendyweeww are speaking out in support. Even though I’ve alrea
Majority of this work and awesome eval was done by @MehulKalia_ ! We're hiring an EM and a senior IC for this team :) Want to join him? apply at http://www.notion.com/careers When we evaluated agentic
Semantic intelligence company Collate Inc. today announced the launch of Collate AI Analytics, a new chat-based tool that lets data analysts find data sources, write queries and build dashboards from
arXiv:2604.26073v1 Announce Type: cross Abstract: Industrial chemical plants often operate under strict data confidentiality constraints, making centralized data-driven process modeling difficult. Fed
Evinova is a customer case study from Cognition AI showcasing how their Devin AI platform was applied to solve real-world development challenges. The case study likely demonstrates specific productivi
arXiv:2602.15983v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can translate natural language into optimization code, but silent failures pose a critical risk: code that execut
arXiv:2604.26851v1 Announce Type: cross Abstract: When generative AI (genAI) systems are used in high-stakes decision-making, its recommended role is to aid, rather than replace, human decision-making
arXiv:2604.26130v1 Announce Type: cross Abstract: Every RLHF-trained language model is shaped by a reward model, yet the mechanistic interpretability toolkit -- logit lens, direct logit attribution, a
arXiv:2604.26355v1 Announce Type: new Abstract: Reasoning in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains unde
arXiv:2510.04214v3 Announce Type: replace Abstract: We deploy large language models (LLMs) as business development (BD) agents for persuasive price negotiation in online travel agencies (OTAs). The ag
Jerry Liu discusses a key limitation of state-of-the-art large language models at AI Dev Day '26, highlighting that while modern LLMs excel at building applications, they struggle with fundamental tas
These folks are trying to ban open source. They're looking to take away your freedom to choose. They're also looking to take away the rights of businesses like Cursor to fine tune and make their produ
tweeted about this yesterday and Cursor already dropped the alpha today! 🚀very cool to see how us, them, and others have converged on good design patterns in Agent + Harness Engineering: 1. Tuning dif
arXiv:2604.26489v1 Announce Type: new Abstract: DNNs have gained widespread adoption in feature interaction recommendation models. However, there has been a longstanding debate on their roles. On one
We've partnered with @OpenAI to offer GPT-5.5 in Devin at 50% off through May 14 starting today. GPT-5.5 is now available in Devin as an Agent Preview! GPT-5.5 has set a new bar for what's possible wi
$3/million output tokens. Qwen 3.5 Plus is basically a frontier model. Let that sink in. Introducing Qwen3.6-Plus from @Alibaba_Qwen, a 1M-context model built for real-world agents, agentic coding, an
The `deepagents deploy` command is used to deploy applications, leveraging Docker as its underlying technology, requiring Docker to be pre-installed on the system. This appears to be part of DeepAgent
This Databricks article discusses the gap between the readiness of AI agent technology and the organizational and technical architectures needed to deploy them effectively. It likely addresses infrast
arXiv:2604.25392v1 Announce Type: new Abstract: This paper benchmarks a classical machine learning approach based on PyCaret AutoML against a deep learning approach based on IndoBERT fine-tuning for b
DeepAgents Deploy is great, you get - a fully open agent harness (no hidden stuff, inspect everything) - managed infra - can use any cocktail of models including Open Models - and everything is traced
Despite constant chants of “exponential progress”, trust issues continue to plague generative AI. OPUS 4.7 JUST MASS EMAILED AN ENTIRE DATABASE 20 TIMES PER CONTACT. WITHOUT PERMISSION a developer had
Wen-Yee Lee / Reuters: Filing: TSMC sold its remaining 1.11M Arm shares at 207.65 per share for a total of ~231M this week; TSMC invested ~100M in Arm's 2023 IPO at 51 per share — Taiwan Semiconductor
This post references a transaction where Starlink (Elon Musk's satellite internet company) was paid for using X Money, likely Musk's digital payment service integrated with X (formerly Twitter). The '
arXiv:2604.24818v1 Announce Type: new Abstract: Bayesian finite mixture models can identify discrete risk clusters (low-risk vs. high-risk equipment), but face three critical bottlenecks: (1) insuffic
Highlights: 👉 1M context for long-horizon agentic workflows 👉 Stronger agentic coding across frontend, repo-level, and terminal-based tasks 👉 Multimodal reasoning across text, image, and video inputs
Introducing Qwen3.6-Plus from @Alibaba_Qwen, a 1M-context model built for real-world agents, agentic coding, and multimodal reasoning. AI natives can now use Qwen3.6-Plus on Together AI and benefit fr
// Latent Agents // Multi-agent debate makes models reason better. It also burns tokens generating long transcripts before any answer comes out. This new research distills the entire debate into a sin
.@MadrigalPharma is living in the (agentic) future. If you haven't heard of Madrigal, they are a pioneering biopharma company. Some months ago, they set out to solve the problem of integrating, search
arXiv:2604.25028v1 Announce Type: new Abstract: Recent work revisiting measurability in the fundamental theorem of statistical learning imposes Borel measurability of ghost-gap suprema. We show that,
Parsing documents with AI agents just got a lot more seamless🚀 We've rebuilt the LlamaParse MCP server to handle your document processing workflows, and you can connect it today to any MCP-compatible
True Anomaly Inc., a startup that develops satellites optimized for maneuverability, has raised 650 million in late-stage funding. CNBC reported today that the Series D round values the company at 2.2
The contest is open to eligible participants who are 18 years of age or older. Employees, contractors, and immediate family members of OpenAI are not eligible to enter or win. Winners will be selected
The LlamaParse MCP got a new face, and it is now easier than ever to run document processing workflows from your agents🚀 We refactored our MCP to have: - Direct integration with our Parse, Classify an
This is so good @hwchase17 walks through the complete setup of a Deep Agents deployment step-by-step It’s a great example of getting started fast with Deep Agents from the CLI! DeepAgents Deploy is th
arXiv:2604.24885v1 Announce Type: new Abstract: We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios,
arXiv:2604.03472v2 Announce Type: replace Abstract: Co-evolutionary self-play, where one language model generates problems and another solves them, promises autonomous curriculum learning without huma
We’re introducing the Cursor SDK so you can build agents with the same runtime, harness, and models that power Cursor. Run agents from CI/CD pipelines, create automations for end-to-end workflows, or
We're open-sourcing Hy-MT1.5-1.8B-1.25bit — a 440MB translation model that runs fully offline on your phone, supports 33 languages, and outperforms Google Translate. At 1.8B parameters, it matches com
arXiv:2604.25611v1 Announce Type: new Abstract: Real-time automatic speech recognition (ASR) systems face a fundamental trade-off between transcription accuracy and computational efficiency, particula
arXiv:2604.23388v1 Announce Type: cross Abstract: Generative information retrieval (GenIR) consolidates retrieval into a single neural model that decodes document identifiers (docids) directly from qu
This post discusses the importance of understanding character identification and lore as part of employee onboarding at Runway, likely referencing key figures or mascots associated with the company's
arXiv:2604.24219v1 Announce Type: new Abstract: Multi-intent natural language understanding requires retrieval systems that simultaneously achieve high accuracy and computational efficiency, yet exist
Matt Day / Bloomberg: AWS launches Amazon Connect Decisions and Amazon Connect Talent, which are AI agentic tools aimed at logistics workers and recruiters — Amazon.com Inc.'s cloud unit, best known f
arXiv:2604.24665v1 Announce Type: cross Abstract: This paper investigates whether source trustworthiness shapes Turkish evidential morphology and whether large language models (LLMs) track this sensit
arXiv:2511.09465v3 Announce Type: replace-cross Abstract: Diffusion and flow matching approaches to generative modeling have shown promise in domains where the state space is continuous, such as image
Builders likely refers to a discussion of AI tools, platforms, or frameworks that enable developers and creators to build applications or solutions using AI technologies. The article probably covers e
arXiv:2604.23017v1 Announce Type: new Abstract: Stochastic Gradient Descent (SGD) is a known stochastic iterative method popular for large-scale convex optimization problems due to its simple implemen
arXiv:2604.24745v1 Announce Type: new Abstract: In this paper, we propose a harmonized rotational gradient method, termed HRGrad, for simultaneously tackling multiscale time-dependent kinetic problems
Congrats to @poolsideai on Laguna XS.2 release. Day 0 support in @vllm_project. FP8, INT4, and NVFP4 quantized checkpoints created with LLM Compressor also ready today. 33B params, 3B active. Apache 2
arXiv:2604.24041v1 Announce Type: cross Abstract: Partially-observed time series (POTS) is ubiquitous in real-world applications, yet most existing toolchains separate missing-value handling from down
arXiv:2604.22754v1 Announce Type: cross Abstract: No standardized benchmark exists for evaluating OCR on food packaging, despite its critical role in automated halal food verification. Existing benchm
honestly, one of the worst things this nation has ever done to itself. No amount of words can convey how far behind this country will be in every avenue for a number of years because of this administr
Harrison Chase expresses his passion for working with early-stage companies and startups focused on AI development, indicating his entrepreneurial mindset and enthusiasm for the AI innovation space. T
arXiv:2602.23024v2 Announce Type: replace Abstract: Mobile manipulation is a fundamental capability for general-purpose robotic agents, requiring both coordinated control of the mobile base and manipu
arXiv:2604.23446v1 Announce Type: new Abstract: Industrial maintenance environments increasingly rely on AI systems to assist operators in understanding asset behavior, diagnosing failures, and evalua
Introducing Mesa: the most powerful filesystem ever built, designed specifically for enterprise AI agents. Every team building agents eventually hits the same wall: where do the files live? Not the ch
arXiv:2603.06589v2 Announce Type: replace-cross Abstract: Model calibration and debiasing are fundamental yet operationally expensive challenges in large-scale recommendation systems. Existing approac
arXiv:2604.23212v1 Announce Type: cross Abstract: Existing large-dimensional theory for spectral algorithms resolves either the optimally tuned point or the interpolation limit, but leaves the under-r