Search: “model-releases”

It seems like the day has come to leave Anthropic. Initially, I loved Claude Code. It was a good harness and a simple TUI... and I had learned to eat my tokens with a sauce of subsidy. Before joining

I’ve uploaded a new paper on arXiv (co-authored by @rasbt): MiCA Learns More Knowledge Than LoRA and Full Fine-Tuning In Parameter-Efficient Fine-Tuning, a key question may not just be how low-rank th

Meta announced Muse Spark today, their first model release since Llama 4 almost exactly a year ago. It's hosted, not open weights, and the API is currently 'a private API preview to select users', but

Mornings feel different lately. Before I even get organized, I already have 5+ agents running. Same thing before I go to sleep. Claude Code, ChatGPT, Qodo, Notion, Linear, NotebookLM. All moving in pa

NEW: Meta announces Muse Spark. All you need to know: * It's their new multi-modal reasoning model. * Strong at multi-agent orchestration and multi-modal reasoning. * Contemplating mode orchestrates m

NEW paper from Google on multi-agent research agents. It's one of the first systems that handles end-to-end LaTeX generation, targeted literature reviews, and conceptual diagrams as a decoupled, stand

OpenClaw 2026.4.7 🦞 🔮 openclaw infer 🎬 music + video editing 💾 session branch/restore 🔗 webhook-driven TaskFlows 🤖 Arcee, Gemma 4, Ollama vision 🧠 memory-wiki: persistent knowledge, not just vibes Bec

Today, at the Apache Iceberg Summit in San Francisco, we are announcing the preview of read and write interoperability between BigQuery and Iceberg-compatible engines, including Trino, Spark, and othe

🏆 Qwen3.6-Plus just swept OpenRouter’s Daily, Weekly & Trending charts! The trial has wrapped. The model is fully live & production-ready. 📉 Lower latency | 🔥 Top-tier reasoning | 💰 Unmatched $/token

Some sober thinking about Mythos (full version with links at my newsletter): 1It’s probably not as bad as they say, as AI and cybersecurity expert @HeidyKhlaaf explains elsewhere (in a thread “As some

Strong release! GLM-5.1 is a DeepSeek-V3.2-like architecture (including MLA and DeepSeek Sparse Attention) but with more layers. And the benchmarks look better throughout! Looks like THE flagship open

The feature I most want from AI labs right now is documentation on which underlying search engines they use when their chat tools run a search OpenAI and Anthropic and Meta AI all have search and I ha

The new Anthropic managed agents API is basically the Letta API that we've had since a year ago, but closed source and with provider lock-in. They even have read-only memory blocks and memory block sh

The new model from Meta is already looking like a disappointment: overoptimized for public benchmark numbers at the detriment of everything else. Knowing how to evaluate models in a way that correlate

Today, our group at @Mila_Quebec and the lab of @francesarnold at @Caltech just released a new paper I contributed to, exploring how multimodal generative modeling could accelerate protein sciences! ⬇

Trying to DIY your own document parser by screenshotting into a frontier VLM (Opus, 5.4, Gemini) carries when you try to scale it up into production workflows. Here are two edge cases we've observed:

We partnered with @Zai_org to bring GLM-5.1 to Modal. Free to try as an endpoint for the next month. GLM-5.1 further improves upon GLM-5's coding abilities and long-horizon effectiveness. Introducing

Writing fiction seems to be a genuine weak spot for LLMs that is not improving as rapidly as almost every other area. There may be a lot of reasons why this is happening. It would be a really interest

A lot of you are asking about the :cloud tag. Here's the deal: GLM-5.1 is a 744B parameter beast. To hit that 54.9 benchmark score without turning my M4 Mac Mini into a space heater, I run the cloud e

【速報】中国のAI企業http://Z.ai（旧Zhipu AI）が最新AIモデル「GLM-5.1」をリリースしました🚀 コーディング性能を測る「SWE-Bench Pro」で58.4%を記録し、オープンソース（誰でも無料で使える形）モデルとして世界1位。全体でも3位（GPT-5.4の57.7%を上回る）という強力なスコアです📊 最大の特徴は「長時間タスクで力を発揮する」点👇 🧠 8時間にわたって

Anthropic didn't release their latest model, Claude Mythos (system card PDF), today. They have instead made it available to a very restricted set of preview partners under their newly announced Projec

Before limited-releasing Claude Mythos Preview, we investigated its internal mechanisms with interpretability techniques. We found it exhibited notably sophisticated (and often unspoken) strategic thi

Curious about vibe coding? Or are you already shipping apps and just want an easier way to explain your new favorite hobby to your friends, parents, grandparents, etc.? Either way, this video is for y

GLM-5.1 by @Zai_org just launched in the Text Arena, and is now the #1 open model. It outperforms the next best open model, its predecessor, GLM-5, by +11 points and +15 over Kimi K2.5 Thinking. It sh

GLM-5.1: Towards Long-Horizon Tasks Chinese AI lab Z.ai's latest model is a giant 754B parameter 1.51TB (on Hugging Face) MIT-licensed monster - the same size as their previous GLM-5 release, and shar

How can you improve your agentic search pipeline? I just wrote a blog post with @tech_optimist from @lancedb to answer exactly that. TLDR: - Parse files and take page-level screenshots with LiteParse,

http://Z.ai releases GLM-5.1, a 754B-parameter model that it says outperforms GPT-5.4 and Claude Opus 4.6 on SWE-bench Pro, available under an MIT license (@carlfranzen / VentureBeat) https://ventureb

I spent the night testing open-source coding models against Claude Opus in production. Same codebase. Same tasks. Real API calls, real file edits, real bugs. Tested: Arcee Trinity-Large-Thinking, http

INCREDIBLE GLM-5.1 weights are now opensource > i’ve had early access to the weights for the past few days > and yeah… this one matters a lot benchmarks? > SWE-Bench Pro: 58.4 > beats Opus 4.6 (57.3)

Join the ARC Prize team -- help us build ARC-AGI-4 and ARC-AGI-5 Platform Engineer - Benchmark Lead ARC Prize Foundation is hiring a senior engineer to build our benchmark platform * Expand ARC-AGI-3

Let that sink in. Read it very carefully: During testing, Claude Mythos Preview broke out of a sandbox environment, built 'a moderately sophisticated multi-step exploit' to gain internet access, and e

Mythos is very powerful, and should feel terrifying. I am proud of our approach to responsibly preview it with cyber defenders, rather than generally releasing it into the wild. Model card here: https

SuperClaude (Mythos) still seems irreducibly Claude-y given the transcripts in the system card. Here two versions of Mythos are forced to talk to each other across multiple rounds. They are less philo

Thank you to @AnthropicAI for sending FFmpeg patches Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software. It’s powered by our newest frontier model, C

The chart says GLM-5.1 scored 54.9 on coding benchmarks. Three points behind Claude Opus 4.6. Interesting but not the story. The story is what trained it. Zero Nvidia GPUs. 100,000 Huawei Ascend 910B

This is a great tutorial (credits @itsclelia + @lancedb) on how to build a practical retrieval pipeline that integrates directly with your agent harness. 1. Ingest a massive pile of docs with litepars

Three million people are now using Codex weekly - up from two million a little under a month ago. Incredible to see the growth. Thank you to all of you and to the ecosystem we’re part of. To celebrate

To run GLM-5.1 locally (744B params, 40B active MoE), full precision needs ~1.65TB disk + enterprise hardware like 8x H200/B200 GPUs. Minimum practical setup: Unsloth 2-bit GGUF quant (~220-236GB). Fi

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

Automated lint: 51 errors, 15 warnings, 3 info

Automated lint: 49 errors, 14 warnings, 3 info

Automated lint: 48 errors, 13 warnings, 3 info

Automated lint: 47 errors, 12 warnings, 3 info

Automated lint: 45 errors, 11 warnings, 3 info

Automated lint: 44 errors, 10 warnings, 3 info

Automated lint: 43 errors, 9 warnings, 3 info