Search: “inference”

memory isn't a retrieval widget. it's write policy. the harness decides what survives compaction, what gets promoted, and what becomes reusable state. https://x.com/hwchase17/status/204297850056760973

Today Tesla FSD is ~9x safer than humans Soon, FSD will be 1000x safer and driving manually will be considered dangerous Every Tesla on the road feeds real-world data back to train the AI. Billions of

Cron Jobs — AI That Works on a Schedule Tell Qwen Code 'check if tests pass every 30 minutes' and it sets up a cron job in your session. No crontab editing, no scripts to write. Use /loop commend. Wor

Often discuss my three-level vision for opening GLM to the community: First, we focus on accessibility by lowering the barrier to entry and removing unnecessary constraints so developers can truly exp

One great outcome of PaperWiki is personalized surveys. Survey papers continue to be one of the best ways to track a field. My agents are now generating personalized surveys on topics using my paper L

The pace at which useful things are shipping also seems to be accelerating. Model releases are coming faster, of course, but so are significant application and enterprise products (especially from Ant

The power of JAX Introducing gyaradax 🐉: A JAX solver for local flux-tube gyrokinetics with custom CUDA kernels for acceleration. This entire code was vibecoded by @ggalletti_ and me in a month. Valid

(1/5) FP4 hardware is here, but 4-bit attention still kills model quality, blocking true end-to-end FP4 serving. To fix that, we propose Attn-QAT, the first systematic study of quantization-aware trai

The specific tweet at that URL (status ID 2042079804271313343) could not be directly retrieved. However, based on the available context about Ben Golub's recent X/Twitter activity around Refine.ink...

Transformers.js, a library that enables running state-of-the-art Hugging Face machine learning models directly in the browser with no server required, has experienced explosive NPM download growth ...

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

An AI cow collar just created a billion-dollar company. Farmers draw boundaries on a phone app, and the collars guide cows using sound and vibration. It works by collecting over 6,000 data points per

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

Google's Gemma 4 is pretty wild. You can now run it locally with OpenClaw in 3 steps. 1. Install Ollama 2. Pull Gemma 4 model 3. Launch OpenClaw with Gemma as the backend Private local AI agents in mi

We're seeing even more autonomous AI coworkers. The new MLE agent on the market is Disarray. In Kaggle competitions, Disarray: - won 28 medals across diverse domains (vision, NLP, tabular data) - plac

the current fear is is that AI homogenizes culture and turns humans into passive consumers one counterpoint: in Go, human play showed very little improvement from 1950 to 2016 until alphago beat lee s

🔓 Open-source release Get DeepSeek-V4.1-Flash-1017: 🤗 Hugging Face: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017 🔗 ModelScope: https://modelscope.cn/models/deepseek-ai/DeepSeek-V4.1-Fla

Beautiful work from @perplexity_ai @AravSrinivas with weights on @huggingface of course! https://huggingface.co/perplexity-ai/pplx-decider-flash-v1.2 https://huggingface.co/perplexity-ai/pplx-decider-

congrats on the launch!! Introducing overshoot, it will cut your GPU bill in half with zero quality loss, or you don’t pay. Over the past few months, we have forward deployed into AI teams to optimize

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

Congrats to @lightseekorg on the impressive TokenSpeed results! 🚀 Great to see Qwen3.8-Flash-Next reaching 685 output tokens/s per user on Nvida GPUs. Excited to see the community unlock more of Qwen’

In early 2022, the first “real” @modal user was using us for processing large scale weather data. We were anxious about going up to them and asking them to pay ~500 for continuing to run these jobs. (

The cancelation of the Grace Hopper Conference may actually point to a reduction in overall junior-level recruitment and job growth. I spoke about AI at GHC 2018, and it was 20,000+ attendees, majorit

A gap that has been fixed in our methodology that highlighted a decline was not including local models (GGUF, AWQ, ONNX, etc). Earlier, these were far harder to track and closer to a rounding error. N

David Silver is one of the all-time greats. He was the creator of AlphaGo, which changed the course of history by showing that neural nets could achieve superhuman performance for the first time. He a

wait so this feels a bit different too in a good way You already gave the LLM the answer. So why is it writing it out from scratch? Introducing a new AI model architecture: Constrained Decoding Models

Mistral AI outlines its vision for engineering, manufacturing, and earth observation by demonstrating how the model can inspect mechanical components, extract evidence from PDFs, and analyze gigapixel

yesterday we took SF @Techweek_ to the water ✈️ The Science of Speed brought together founders, researchers, and builders front row for Fleet Week with @nvidia and @dtcp_capital. not to mention a gues

Pay close attention to custom harnesses. This is a super interesting paper showing the impact of training inside the harness. Qwen3-14B goes from 22.2% to 54.8% on Spider 2.0-SQLite when it is trained

Build your own harness, folks. Reading papers like this makes me realize how underexplored harness engineering really is. The authors find that on whole-repository migration, GPT-5.6 Sol goes from 6.5

Grok @Bot works well on your phone. Just download the app from Apple or Android. https://apps.apple.com/app/id6794501026 This feels unreal Used Grok Bot today, mostly from my phone I got more done fro

Markdown has become a universal representation of information between humans and agents. It preserves core primitives needed to express structure (headings, lists), allows agents to read the informati

On October 7, 2026 OpenAI released a session titled “Explore ideas through interactive visuals that respond as you learn, try, and discover.” The webcast showcased real‑time visual tools that adapt to

A new breed of startups is emerging to help businesses use AI smarter and cheaper, shifting towards open Chinese models and giving the likes of OpenAI and Anthropic a run for their billions. Read more

AI is driving the biggest infrastructure build-out in history, with @Google alone forecasting $200B of capex in 2026E. What are the real constraints on a system at this scale? Amin Vahdat is the chief

decision models + local ai = ❤️ tried Laya (421M) on llama.cpp in a little apple-picking benchmark, it's almost as good as Qwen 4B at 12x the speed. Media Decision models in llama.cpp are now availabl

Great report from Google and MIT. Co-designing ML models and the accelerators is an exciting research direction. This report introduces Coco, an agent platform TPU architects use for hardware and mode

Malware reverse-engineering: solving an out-of-distribution investigation task. When faced with an unknown binary, Mistral Large 4 reverse-engineers it end-to-end. In this case, it concludes the sampl

releasing my local AI slide deck covers from prefill vs decode, MoE vs dense, VRAM vs unified memory, quantization to speculative decoding, everything with llama.cpp feel free to reuse with attributio

Very good to see more competent labs training open-weight models. This Reflection's new Beam model seems to have strong reasoning efficiency, which I think is a big deal for long-running agents. 3-4x

We can't thank llama.cpp and @ggerganov enough for being among the pioneers of local AI. But we sure as hell can contribute back! Upstream contributions will now become a priority in @qvac. One of our

A tweet by Kristof (@CoastalFuturist) titled “How it feels to ask the Chinese ai models for help on something Claude won’t agree to” was posted at 1:30 AM on Oct 4, 2026. The post garnered 616.3 k vie

Clef Flash (9 billion‑parameter) is a multimodal model hosted on Ollama that converts a given state and a schema of typed questions into actionable decisions. Its counterpart, Clef, is also available

I just made the most expressive real-time motion harness for the Reachy Mini. It was created by: > synthesizing a massive motion dataset using Astra (over 10000 samples) > fine-tuning Qwen 3.5 4B usin

.@OpenRouter co-founder Alex Atallah, in his first podcast since Stripe acquired the company, joins @Replit co-founder Amjad Masad and a16z's Erik Torenberg on why the future of AI is independence and

Reasoning from scratch, round number 6! An introduction (and implementation) of Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO). 00:00 Introduction