Search: “reasoning”

We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B

Whoa, Meta released a new open-weight LLM yesterday, something that hasn't happened since the good old Llama days. Their Meta Muse Glimmer model is a 30B multimodal reasoning model with a Gemma-like a

In the era of base LLM scaling (2022-2024), I believed the LLM line of research would reach a capability plateau (as later seen with base LLMs). In late 2024, after the o3 test-time compute demo, I ch

This might be a good time to mention my recent keynotes titled: 'Agentic AI is Neurosymbolic AI' I would have assumed it was fairly obvious, but in case it's not: a million-line codebase (also known a

Picking the right agent harness is now a crucial skill for any AI engineer. Imagine using the same model, same task, and same prompt. Now move it between two agent harnesses and the cost per success c

Routing for long-horizon coding agents is a big deal. @notdiamond_ai just announced a model router that works natively with Claude Code. This is huge. It picks the model and reasoning effort before ea

one of the top cybersecurity models, post-trained from open weights by @depthfirstlabs on @FireworksAI_HQ long-horizon RL is as much an infra problem as a research one: 100+ turn rollouts, async/pipel

My book, Reinforcement Learning from Human Feedback is done! This is the book I wish I had when learning to fine-tune, align, & now post-train models since ChatGPT. The resource has been built by me f

A model drop by Thinky 🚨🚨 Have been doing some early testing on the model for the past couple of days. Here are some of my findings 1. The reasoning is sharp and concise! Always love to see models tha

Hermes Agent is a project from Nous Research focused on developing agentic AI systems capable of autonomous reasoning and task execution. The initiative likely explores methods for creating AI agents

imo this is the most impt part of anthropic's J-space paper today. it's a two-parter: 1) ant proved that they can do 'brain surgery' interventions into reasoning to change topics midstream* 2) THE MOD

McGovern neuroscientists have discovered that you don't need language to think logically. People with severe language impairments solve complex reasoning puzzles perfectly and brain scans show languag

Francois Chollet discusses how current workflows are increasingly incorporating Large Reasoning Models (LRMs) as control systems that direct symbolic programs and tools, representing a pragmatic but i

what does this even mean, @dwarkesh_sp, “the real deal”? is it even a falsifiable conjecture? what’s the evidence? and if you can agree that “If you ask an LLM a question it can't answer, sometimes it

This post describes an AI research agent built on ActiveGraph that provides complete visibility into its reasoning process through detailed graphs and traces of claims, sources, and internal agent act

microsoft MAI tech report is a gold mine, one of the most transparent for a model at this scale. this model uses zero synthetic data or distillation from previous models. this means reasoning, agentic

LLM agents & memory systems operate in continuously updated environments (Git repos, evolving docs). They must process long contexts, recover earlier information, and reason over many updates that cre

Only when you drive the Cybertruck do you realize how incredible it is: a bulletproof tank that moves like a million dollar sports car! Reason for the angular shape is that the thick, ultra-hard stain

who’s adding this to reachy mini? Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborat

I have been testing DeepSeek-V4-Pro with the Pi coding agent. I am mindblown by how well it works out of the box. A few notes: I spent a few hours building an LLM wiki with an agent powered entirely b

Francois Chollet shared a blog post analyzing failure modes of frontier AI models, specifically examining performance on the ARC (Abstraction and Reasoning Corpus) AGI benchmark with models including

Stop blaming the users. It’s not that simple: People keep blaming the users for the growing number of vibe-coded reasoners. Doing so is *half* right. Users *are*screwing up - by letting vibe coded stu

Highlights: 👉 SOTA coding—93.5% LiveCodeBench, Codeforces 3206, and 80.6% SWE-Bench Verified 👉 Hybrid attention efficiency—27% FLOPs and 10% KV cache vs V3.2 for long-context inference 👉 Three reasoni

Gary Marcus critiques ChatGPT's lack of embodied understanding and spatial reasoning, arguing that the language model struggles with physical concepts that humans intuitively grasp through bodily expe

Gary Marcus critiques the assumption that massive financial investment in AI scaling alone can solve fundamental challenges related to common sense reasoning in artificial intelligence systems. The po

ARC-AGI-3 is a new benchmark iteration designed so that any intelligent human applying genuine effort should achieve greater than 90% accuracy, maintaining the benchmark's core principle that tasks mu

Francois Chollet argues that memorization and knowledge function as a cache for previously completed cognitive work, allowing it to be reused efficiently rather than recomputed. The purpose of storing

After seeing that Claude Mythos marketing turned out to be, as expected, a scam, I wanted to make a master list of tricks being used to market LLMs. The master list includes statements directly from l

MiniMax-M1 is a large-scale open-weight reasoning model developed by MiniMax, featuring a hybrid Mixture-of-Experts (MoE) architecture with 456 billion total parameters (activating 45.9 billion per to

Stop trusting LLMs just because they're useful. 🛑 Our Head of DevRel @RoieSchwabco breaks down the two essential parts of a reliable AI stack: ⚙️ Reasoning: What the LLM does (logic/synthesis/formatti

Visually rich documents are especially challenging for agents. Tables, charts, and images often break traditional document pipelines, making complex reasoning difficult📄 So we teamed up with @lancedb

🚨 Elon Musk agrees with 'some of the things Anthropic has said' and warns against 'torturing superintelligence' after reading Grok's internal reasoning traces during reinforcement learning “It feels l

Dusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less 'two groups of people speaking past each other' and more a sharp funnel. - Nap

For their Mistral Large 4 release, @MistralAI ran a blind Surge human eval, with our expert software engineers evaluating five frontier models on coding quality. Le Chonk ranked #1 among open-weight m

There's a very creepy but overlooked thing about @AnthropicAI pushing the idea that AIs will soon become sentient, conscious, self-aware, & deserving of 'personhood'. 'AI personhood' would mean that A

This is one of the strongest use cases I've seen for System One models like Jev. Pay close attention if you build custom harnesses. Jev is now available as a packaged router. What is it? You send the

another stealth model launch Space Bunny Alpha is now FREE on Nous Portal try with your Hermes Agent now Meet Space Bunny Alpha on OpenRouter ⚡ A flash model with fast inference, adjustable reasoning,

Interesting paper on agent memory stored as a linked markdown wiki. Lots of great ideas and insights if you work with LLM Wikis. Wikis are useful for agents because each page holds dense text and the

Big model release today - I wrote about Claude Opus 5.5, GPT-6 Sol, and GPT-6 Luna - plus comparison grids of pelicans by the different model families at different reasoning levels https://simonwillis

Impressive paper showing the impact of a good harness. Improves Qwen3-8B from 41.2% to 91.8% on long-horizon robot tasks without any change to the model. The gain comes from the harness. GAVEL keeps a

Dan Selsam is a current OpenAI capabilities researcher. (since 2022) He was my boss for a while. He doesn't have a twitter account but has made this public statement of his views on AI risk and sent i

Dario has written that we need to “pace the frontier,” and Sam has agreed. People may be surprised by my response: go ahead. You guys are the frontier. By any reasonable metric — market share, revenue

Looped transformers are a popular architecture topic right now. This new technical report extends the loop across tokens. Recurrent Looped Transformer (RLT) makes the decoder recurrent over every toke

// human-values.pseudo | ARTIFACT 0.1.0-experimental.1 | BASE 1.2.0-rc1 | EDITION ai-compact | NARRATOR System_Synthesis_Node_01 | PROVENANCE human-directed, AI-assisted | STATUS single-encoder resear

Sebastian Raschka’s September 2026 article introduces **GPT‑6 *Astra***, a next‑generation language model that expands upon the Transformer backbone with a novel *looped* architecture—allowing multipl

It is less than a decade since the development of the transformer. Less than four years since the release of GPT-3.5 (ChatGPT). Less than two years since the release of o1-preview (the first Reasoner)