Search: “reasoning”

This post likely discusses the challenges or difficulties of writing a sestina, the complex poetic form requiring six stanzas with a specific pattern of end-word repetition. Ethan Mollick, known for d

I find that open weights models over-perform on benchmarks compared to actual real-world usage, and Kimi feels like no exception. For example, a small amount of use will show that Kimi is not as good

Please don’t trust your chatbot for medical advice. 🙏 Remember how I used to say that large language models are “frequently wrong, never in doubt”, and how I warned three years ago on 60 Minutes that

Sam Altman announced on X that OpenAI had something to reveal at 12 pm PT on a specific day, generating anticipation about an upcoming product announcement or demonstration. The post suggests a schedu

Human biological limits, like our tiny working memory and shallow calculation depth, are actually a feature. They force us to abstract, compress, intuit. If we had infinite resources, we would never h

Intelligence per picojoule, with @itsclivetime and @dylan522p (0:00) Intro (1:22) What is codesign? (2:49) Codesign example: Swish vs ReLU (4:22) Are DeepSeek papers codesign? (6:45) Predicting where

LLMs are “ good at math style problems, where you tell them A, B and C are true, and then ask them to figure out D [but] extremely bad at anything involving what I would call mature scholarship .. [so

Source: https://spectrum.ieee.org/boston-dynamics-spot-google-deepmind I break down stories like this every day in my free newsletter. Keep up with the latest in AI/Robotics in 5 min a day: https://ww

I'd say cognitive friction is even more than just a regularizer: it's an incentive to find the right interface abstractions, and in turn good abstractions are what enables compounding over time. Piles

Unlimited demand for a product or service does not guarantee business viability or economic sustainability, as other critical factors such as cost structure, scalability, profitability, and resource c

Constraints are the catalyst of invention. An infinite search space leads to paralysis. The most creative inventions happen when you are forced to solve a problem within appropriately narrow constrain

Okay this one is insane. A new 18B frankenstein model was just released on @huggingface — Beats the new Qwen3.6-35B-A3B on a 44-test suite despite requiring 12GB VRAM instead of 24GB 🤯 Runs on a SINGL

Francois Chollet compares programming language philosophies between PHP and Go, likely discussing design trade-offs, developer experience, or use cases that differentiate the two languages. The compar

Claude Opus 4.7 is now available as an Agent Preview inside of Devin! Anthropic has clearly optimized Claude Opus 4.7 for long-horizon autonomy, unlocking a class of deep investigation work we couldn'

GLM-5.1 Tool Calling Issue Fix & Chat Template Update If you are running GLM-5.1 with vLLM/SGLang and using tool calling, please update your chat template. http://huggingface.co/zai-org/GLM-5.1/blob/m

On the plus side with Opus 4.7, if it does decide to think it produces BY FAR the best Sparks unicorn* ever, even non-thinking is pretty good, if not great. * This is created using TikZ, which is a la

There's a broadly held misconception in AI that methods that scale well are simple methods -- even, that simple methods usually scale. This is completely wrong. Pretty much none of the truly simple me

this is wild. take this to the extreme and you can just shoot entire life experiences directly into the brain like in… the matrix 🫠 A Smell Simulator That Uses Ultrasonic Waves Through Your Skull To T

We comprehensively benchmarked Opus 4.7 on document understanding. We evaluated it through ParseBench - our comprehensive OCR benchmark for enterprise documents where we evaluate tables, text, charts,

3/5 An example: In instance psf__requests-1724, the gold fix is 2 lines. Our agent’s functional fix was 8 lines. The LLM judge rejected the correct 8-liner as 'messy' and 'redundant,' choosing a clean

🚨 In 2 weeks, a final decision on amendments to the EU AI Act and the GDPR will be made. What is at stake is nothing other than the future of Europe. Many don't know, but the stream of events leading

Cursor AI shared observations on X validating that multi-agent architectures demonstrate superior performance when tackling novel problems that fall outside the distribution of training data. The post

Benchmarked @DJLougen ’s Ornstein-27B-v2 Q6_K on my RTX 3090 using hermes-bench, my new open-source benchmarking UI for local LLMs and Hermes agents. Ornstein is a Qwen 3.5 27B fine-tune trained on re

Let me break down exactly how long it takes me to teach people AI agents. ⏱️Give business professionals their first big wow moment in under 2 minutes ⏱️Teach them meaningful use in under 17 ⏱️Teach th

Each workflow in Thoth is a full LangGraph agent which can call subagents which themselves are LangGraph agents. Just describe what you want in plain English and it builds a full multi-step pipeline.

Nous Research shared a post describing the experience of discovering or first encountering Hermes, their fine-tuned large language model series. The post likely captures the excitement and impressions

Francois Chollet, AI researcher and creator of Keras, argues that good design is fundamentally an act of compression — distilling an enormous number of implementation decisions, constraints, and consi

I am a Web3 Ambassador at World Liberty Financial. There are 12 of us on the team page. 4 are named Trump. 3 are named Witkoff. The page calls us 'the passionate minds shaping the future of finance.'

A playable, digital piano built with Gemma 4 E2B (2B). https://x.com/0xCVYH/status/2039929097141318129?s=20 Google lancou 'Agent Skills' junto com o Gemma 4 Um app Android onde voce importa skills e o

Having a model like Gemma 4, which is perfectly adequate for everyday use in many cases, runs locally, is free, and secure, still feels unreal. We have a very good AI that costs nothing, uses hardly a

Nous Research's Hermes model line has been deliberately developed with a strong emphasis on creative capability. The training dataset for Hermes 4 expanded to 50x more data tokens than Hermes 3, w...

Science needs a way to process models that are only 'mostly correct' in terms of their predictions, but are very compressive (high ratio between predictive power and model complexity). They are likely

Simplicity is a very strong signal of model quality. Galileo's heliocentric model was directionally correct, but its predictive power was quite bad compared to the much older Ptolemaic model, because

We should view the history of physics as a long-running program synthesis task. Kepler and Newton were searching the space of possible symbolic models to find the simplest one that would best satisfy

Common Failure Modes Break VLM-Powered OCR in Production. 🔁 Repetition Loops — model spirals into infinite whitespace, exhausts resources, cascades latency across your system 🛑 Recitation Errors — saf

The specific tweet (status ID 2041723225827062080) could not be directly retrieved, but based on closely related content from Ethan Mollick's (@emollick) X account, the most relevant match is the p...

Great application of small language models from Salesforce and colleagues. AI-scientist pipelines are well known to struggle to propose novel and diverse research ideas. This team trains an 8B reasoni

Muse Spark Open is now live on Wally, day 0 Best US open model thanks to @finkd 370 tok/s, ~2x faster than any provider on OpenRouter. $5 Free on signup. Media 1/ muse spark open is the most capable U

Pay attention to this new wave of VLMs. Glimpse is the first model from @ElorianAI, the brains that led Google's Gemini and Apple's MM-1. Quick test: 10 game boards from an overhead camera. Same promp

We’re excited to be day 0 partners for @reflection_ai’s first open-weight model! For a limited time, Beam is FREE on Ollama! In partnership with @reflection_ai this model is hosted in the US with full

Amazing to see @AIatMeta launch the best US open-weight model so far! The model will be available on Ollama shortly. 🫡 Today we’re releasing Muse Spark Open, the most capable US open-weight model to d

Elon Musk says the central lesson of 2001: A Space Odyssey is that you should not make AI lie, because HAL killed the crew to reconcile two contradictory orders “But let me tell you how things can pot

Hermes Agent is the best place to use the new @NVIDIAAI Nemotron 3.5 Super VL and Bolt models. NVIDIA benchmarked Super VL on Hermes Bench with a score of 63.44, and compared to similar local models i

Introducing ExtractBenchPro: the most challenging benchmark for real-world document extraction. We see a massive long tail of document complexity in terms of use cases brought on from our customers, t

multiple release by nvidia today, love how they compress nemotron 3.5 super to the 'perfect' size for their specific hardware (RTX spark). there is a full tech report, including how they use their own

NVIDIA Nemotron 3.5 Bolt 74B-A9B 24GB is now on Ollama This model vision-language model (VLM) is designed to run everyday agentic tasks locally, using a native 2-bit quantization to fit in 24GB of mem