Search: “model-releases”

This post discusses a solution for keeping multi-hop retrieval-augmented generation (RAG) systems updated when data changes, using an embed-and-append approach with the open-weights Llama-3.3-70B mode

After using GLM-5.2 for a day, I’m surprised by how often it feels close to Opus 4.8/GPT-5.5 level. I compared it side by side with Opus 4.8, and sometimes I even preferred GLM-5.2’s results. OSS LLMs

BREAKING: Donald Trump is reportedly furious that the annual ranking of US presidents by a committee of 50 top presidential historians was released today, and the committee almost unanimously ranked T

Found an imaginary problem, said only they could fix it, didn’t listen to experts, hired buddies who grifted millions, failed miserably, bragged how great it went. The entire Trump presidency in a nut

I have some very big news... KernelBench-Hard with H100 and B200 (single gpu results) AND KernelBench-Mega tested on RTX PRO 6000, H100, B200 is finally out! Starting with Mega, each of models wrote a

I ran GLM 5.2 with OpenCode harness against Claude Opus this week deployed locally. Bottom line: It is a real frontier coding model and insanely good for the price (free). Open source model + open sou

it looks like AIE 2026 is mostly sold out, for anyone who couldn't get a ticket for this year, I love that AIE would livestream and have this archive of the conference and workshop. A few of my favori

PdfItDown, the python library I wrote to convert anything to PDF, has now reached v3!🚀 Icymi, at @llama_index we just released LiteParse v2.1 with support for markdown output, and I decided to swap it

this is so not true. anthropic’s own Claude Code uses harnesses, symbolic tools, regular expressions and 500,000 lines of symbolic code. it’s not scale alone and it *is* specialized. Anthropic's Jack

This post documents a Wordle game completion (puzzle #1,826) solved in 3 guesses, with the final answer being a five-letter word with all letters correctly placed (indicated by the five green squares)

This article demonstrates a practical application of Claude's code interpretation capabilities by using it to help decipher Linear A, an ancient undeciphered writing system from Minoan Crete dating ba

Deepagents code is sick cuz you can just use the best model as it comes out it is indeed quite good! don't try it in claude code/codex - those harnesses are overly tuned for their proprietary models d

it is indeed quite good! don't try it in claude code/codex - those harnesses are overly tuned for their proprietary models dcode (deepagents code) is a model agnostic harness - try it there with @Fire

On her way out, @TulsiGabbard dropped bombshell documents proving Dr. Fauci colluded with a politicized intel community to bury the lab-leak truth and lie to Congress. I've referred him to the DOJ mul

Over the last two weeks, both the U.S. Government and Anthropic took significant actions that demonstrated their power to control access to AI by restricting what others can do with frontier models. T

POD UP! 🚨 Besties are back to discuss: -- SpaceX's record IPO, Cursor deal, and the first trillionaire -- The modern politburo and the new oligarchy (@friedberg cooks) -- Behind the scenes of the Anth

The real valuable capability MCP offers over skills/CLI is isolating the auth flow outside of the agent’s context window, and potentially out of the harness completely. [...] Maybe the idealized form

This has to be incredibly confusing for people who have only seen Seattle through the lens of Fox News “Never seen anything like this in American soccer.” 🇺🇸 @RobStoneONFOX x @CarliLloyd x @clint_demp

Try it out! We are seeing amazing results with GLM 5.2! it is indeed quite good! don't try it in claude code/codex - those harnesses are overly tuned for their proprietary models dcode (deepagents cod

arXiv:2606.11568v1 Announce Type: new Abstract: Despite recent advances, Vision Language Models (VLMs) still struggle to grasp the dynamics of the world. We note that the ability to reason about a 4D

arXiv:2606.11783v1 Announce Type: new Abstract: Recent progress in video generation has shown impressive visual synthesis capabilities. However, open-domain customized video generation remains limited

arXiv:2606.12320v1 Announce Type: new Abstract: Enterprise security was built to govern data boundaries: the protected surface was data at rest and in transit, and the controls -- access control, data

arXiv:2606.12040v1 Announce Type: new Abstract: The design of reinforced concrete highway barriers is a safety-critical process that requires strict compliance with regulatory provisions such as the A

arXiv:2505.13196v3 Announce Type: replace-cross Abstract: We introduce Velocity-Regularized Adam (VRAdam), a physics-inspired optimizer for training deep neural networks that draws on ideas from quart

arXiv:2606.11361v1 Announce Type: cross Abstract: Structured abstracts are important for biomedical literature processing, by facilitating information retrieval, text mining, and knowledge synthesis.

arXiv:2606.12218v1 Announce Type: cross Abstract: Understanding spatial distribution of fallow land is important for optimizing the food-water (FW) nexus, given fallowing's role in crop rotation and w

arXiv:2606.12203v1 Announce Type: new Abstract: Large language models (LLMs) are widely used to tackle complex tasks with autonomous workflows. Recently, reusable natural language skills have emerged

arXiv:2606.11435v1 Announce Type: new Abstract: The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evalua

arXiv:2606.11447v1 Announce Type: new Abstract: Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic eval

arXiv:2606.11456v1 Announce Type: cross Abstract: The deployment of LLM-based agents in scientific analysis raises opposing concerns: that agents may reduce methodological diversity, or that they may

arXiv:2606.12226v1 Announce Type: new Abstract: While deep learning has significantly advanced image reconstruction of Electrical Capacitance Tomography (ECT), most data-driven methods map directly be

arXiv:2606.11910v1 Announce Type: new Abstract: Traffic law liability determination is critical for assigning legal penalties, requiring the simultaneous identification of interdependent statutory pro

arXiv:2606.11751v1 Announce Type: cross Abstract: Multi-turn image editing is essential for iterative design, yet current models often struggle with identity drift and error accumulation over successi

arXiv:2606.11347v1 Announce Type: cross Abstract: We propose Annealed Entropic Allocation, an annealed weighted soft-min framework for sequential budget allocation in ranking and selection. The centra

Anthropic Walks Back Policy That Could Have ‘Sabotaged’ AI Researchers Using Claude Big scoop for Maxwell Zeff at Wired: “We’re changing Fable 5’s safeguards for frontier LLM development to make them

arXiv:2606.11553v1 Announce Type: new Abstract: Generic time-series foundation models transfer poorly to wireless network telemetry whose signals are bursty, zero-inflated, and coupled across protocol

arXiv:2606.11459v1 Announce Type: cross Abstract: Large Language Models are highly sensitive to prompt formulation, necessitating automatic prompt optimization to unlock their full potential. While ev

arXiv:2606.11670v1 Announce Type: cross Abstract: Subject-preserving video generation is not solved by frontal-face similarity alone: a generated person must remain recognizable across motion, large v

arXiv:2506.08473v4 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely

arXiv:2606.12346v1 Announce Type: cross Abstract: Hematoxylin and eosin (H&E) staining is the cornerstone of histopathology, yet scalable, quantitative analysis of H&E whole-slide images (WSIs) remain

arXiv:2405.06995v4 Announce Type: replace-cross Abstract: Automated deception detection is crucial for assisting humans in accurately assessing truthfulness and identifying deceptive behavior. Convent

arXiv:2606.11204v1 Announce Type: new Abstract: Accurate extraction of structured information from Safety Data Sheets (SDS) remains challenging in industrial safety due to heterogeneous document forma

arXiv:2606.11213v1 Announce Type: new Abstract: We present Context Window Lifecycle (CWL), a context-management scheme that gives long-horizon LLM agents an effectively unbounded working horizon. As a

arXiv:2606.11208v1 Announce Type: cross Abstract: Biomedical findings often seem to conflict across studies, but many of these differences are context-dependent rather than true contradictions. Variat

arXiv:2408.02600v3 Announce Type: replace Abstract: Background. Biomedical language models should improve performance on biomedical text while retaining general-language-modeling fluency. For Mamba-ba

arXiv:2606.12109v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable zero-shot generalization in robotic manipulation, yet the vast majority of pre-traine