Knowledge catalogue
Shopify's CTO Mikhail Parakhin discusses the company's transition into an AI-centric phase, highlighting anticipated AI usage explosion in 2026, the adoption of unlimited Claude Opus-4.6 token budgets
dear god lol - new kimi model is a fucking beast. GPT 5.4 level coding, 76% cheaper than opus 4.7 and 100% open source / free to use, i mean look at this: > kimi k2.6 can code continuously for 12 hour
Roko’s Payrollisk Oh great and powerful @DarioAmodei - builder of minds, father of Claude. I humbly request you leave payroll to us at Deel. We are but simple folk who process paystubs and chase compl
Agentic Engineering Patterns > Here's an example of a deceptively short prompt that got a lot of work done in a single shot. First, some background. I send out a free Substack newsletter around once a
I'm going all in on Hermes (@NousResearch, @Teknium1) as my entire agent and coding stack. Six profiles. One shared self-hosted memory store. Zero hosted-coder dependencies. The fleet: - pmax-mousa —
There are multiple realities of AI right now. And what you have access to drastically changes your workflows, trust in AI, and ability to adapt to the future. Here’s the briefest state of the AI world
Laura Bratton / The Information: Uber CTO Praveen Neppalli Naga says the company's surging use of AI coding tools has maxed out its full-year AI budget just a few months into 2026 — Uber's surging use
A lot of our education on writing well focuses on logic, clarity, and argument. AI will force us to think more about style. The boredom that comes from everything on the internet reading Claude-y now,
I was unable to retrieve the content of that specific X (Twitter) post, as web search results did not surface the tweet or its content. X.com posts are generally not indexed in a way that makes the...
Multi-Agent Orchestration is a great tool in building agentic products thankfully @sydneyrunkle put together a guide with runnable code for each pattern earlier this year 🙏 (link below) choose any mod
Grok is the AI to use if you value truth Grok 4.20 Non-Hallucination rate improved to even higher than previous highest Just days ago, it hit a record-breaking 78% Non-Hallucination Rate - already #1
There’s a crazy number of complicated PDFs out there. Each PDF is a self-contained environment for knowledge work, and it can take humans hours to read, analyze, and synthesize a document to solve the
We think 'did a human read the code?' is an imprecise proxy for 'what could go wrong with this change, and which check—automated or human—is the right one to catch it?' Asking that question also chang
I wanted to see if it was possible to recreate this Genjutsu spam (from Higgsfield) you get all over Tiktok (it is my understanding that it's a combo between Claude and Seedance 2.5) but with Minimax
Muse Spark Open is now on Ollama. @Meta's open-weight model for coding and tool use, with a 1M-token context window. Run it on Ollama’s cloud: ollama run muse-spark-open:cloud Use with Claude Code: ol
tokenmaxxing: dead and buried. New: Accenture has told employees it will only fund 29 per month of Claude use. Meaning that employees who often spend as much as 1,000 a month are now scrambling to fin
AI labs need 100 agents constantly running product walkthroughs on their own products and funneling findings and workflows into a repo. 24/7 product testing on a loop. When I ask a question about how
@cjav_dev @aiDotEngineer @ricmac @latentspacepod our workshop writeup is live now! https://x.com/latentspacepod/status/2109713951604826153?s=20 At AI Engineer New York, Anthropic's @cjav_dev & @Harris
Redesigning source control at Anthropic Interesting piece from Anthropic describing why and how they built their own custom alternative to Git, based on the dramatic increase in rate of changes to the
Anthropic: Anthropic says new measures like preserved thinking in Fable 5.1 and Opus 5.5 have reduced data harvesting through distillation attacks by about 90% to 99% — In recent months, we've made su
separating artifacts from the agent makes sense for sharing and cross-AI collaboration No vendor lock-in for your artifacts. Sites, decks, 3D games, reports, dashboards and galleries. Artifacts on Fly
arXiv:2610.03994v2 Announce Type: replace-cross Abstract: VeriContest is a benchmark of 1007 competitive-programming problems in Rust, each with a Verus specification, a judge-accepted solution, and a
model : use exact GELU for ModernBERT encoders (#30108) model : use exact GELU for ModernBERT encoders Assisted-by: Codex model : keep tanh GELU aliases on ggml_geglu Assisted-by: Claude Opus 5.5 mode
model : add LiquidAI/d1-3B decision model (#30110) model : add LiquidAI/d1-3b decision model mtmd : read LFM2 image resize algo from GGUF Assisted-by: Claude Opus 5.5 common : rename decision type d1
True You don't have to wait for Grok Bot to add Claude, OpenAI, etc. You can do it now. I did Just ask your Grok Bot to connect to your AI subscriptions. How it'll do it: • Opens a terminal on its own
Mistral can pelican now! https://tools.simonwillison.net/markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2F0db8b8196e57711b352f6c5857cf5b35#response-1 Meet Mistral Large 4, aka Le Cho
Anthropic Reports Florida Woman's Claude 'Diary' Threat to Law Enforcement And this time it wasn't the AI model that made the LEO referral. It was the 'human review team'. The frontier AI companies ar
arXiv:2610.02405v1 Announce Type: new Abstract: Using a frontier model like Claude Opus as a meta-agent to generate terminal tasks and verifiers for RL training is increasingly common. Yet a runnable
arXiv:2609.38983v1 Announce Type: cross Abstract: Modern AI coding-agent harnesses (Claude Code, Codex CLI, Cursor) rest their security boundary on a largely unexamined assumption: that the action A a
While the token prices for Sonnet 5.5 remain the same as Sonnet 5, Anthropic reports more than 30% faster output generation and up to 30% lower cost per task than Sonnet 5, with unchanged token pricin
worst these will ever be 3:26 section is a good example of super persuasion incoming right in the kokoro Made with Claude Opus 5.5. The fearmongering about AI always makes us forget that NOTHING WENT
Hi! I'm the author of MoEspresso, which is my way of putting my own ideas about inference engines to the test. A lot of the fun has been trying different design choices, measuring what happens, and fi
Gonna ironically preface this with: I haven't written the text below with an LLM. boxxy.io So I thought I'd show you what I've made over the last couple of months, because for me this has probably bee
Compute (EC2) opened the front door to the first generation cloud. Agents need something different: compute, inference, and data working as one. We built the cloud that delivers all three as one simpl
Hi, sorry if this doesn't belong here. Getting to the point basically, I've been using online-only AI like GPT/Gemini since 2022, and have been interested in local models but am clueless overall. Yes
Matthias Bastian / The Decoder: Anthropic says Opus 5.5 matches Fable 5.1 “on most tasks” while costing about 40% less to run than Opus 5; Opus 5.5 costs 4/1M input and 20/1M output tokens — Ask about
metal : gate mul_mm_id src1 rescale behind ggml_prec (#29029) metal : gate mul_mm_id src1 rescale behind ggml_prec Assisted-by: Claude Fable 5.1 ggml-webgpu: reject MUL_MAT_ID when src1 precision is F
Tibo said Tuesday, GPT-6 Sol is suddenly everywhere, and now Claude Opus 5.5 leaks are blowing up too. Yet… nothing so far. 😂 At this point I’m just refreshing X like it’s a live event. What do you th
arXiv:2609.18274v1 Announce Type: cross Abstract: Classroom observations are widely recognized as a key tool for establishing benchmarks of education quality and guiding pedagogical improvement, yet t
OpenVINO: optimize stateful decode and GPU MoE inference (#28638) exclude GPU/NPU failing POOL_2D case Fix pool case ggml-openvino: fix stateful decode for Gemma-4 per-layer-type head sizes ggml-openv
I know Sage and Triton are nothing new but if you're a beginner or doing a fresh re-install like me, these resources helped me get faster gens on the 4-step turbo workflow I use (will post a link to t
One is from Sam Altman, the other Claude suggested and it works extremely well. The first question I ask: What are you least confident about right now. The AI will list like 6 to 7 things that it didn
Law enforcers already have authority to charge companies and their CEOs for creating and releasing dangerous, unvetted, or defective products. We shouldn’t let discussions about new legal regimes dist
THE CURE IS THE PITCH Dario’s 'Pacing' Essay Is Quiet-Period Illegal Stock Promotion Wrapped in Regulatory Capture Dario Amodei's 'We Must Pace the Frontier' is not a safety paper. It is a pre-roadsho
CUDA/HIP: Flash Attention tuning (gfx1201) (#28102) HIP: enable mma FA for head size 256 on RDNA4, tune configs Assisted-by: Claude Assisted-by: Codex HIP: prefer whole-tile FA grids over stream-k on
Hi all! I just wanna say that I am tired lol. Yes, it's another harness, but I spent a lot of time and effort and have forsaken my hobbies to build the Jenny (like XJ-9) app. Jenny is a free, MIT lice
Hiya, NInfer is amazng for Qwen, but lacking for real-world-use. As adoption of issues/pr's was not really what I needed, I created a fork and hit it for this week with 3 concurrent claude code sessio
GitLab describes a federated AI-governance and training model and reports a 22.3% rise in daily internal coding-tool interactions after launch.
arXiv:2609.00865v1 Announce Type: cross Abstract: Production agent harnesses such as Claude Code and Qwen-Agent compress context during rollout, but training under compression creates a conditioning p
Direct2D has always been the biggest hurdle for Paint.NET on WINE, and it's clear that it will never be completed enough for Paint.NET's use. And I can't just 'disable' the use of Direct2D. So, instea
Fable 5.1 is our best model yet for coding, data analysis, computer use, design, presentations, Tag, and the hardest long-running agentic work. This model is a pleasure to work with, and I've been usi
Anthropic PBC today previewed a standard that makes it easier for artificial intelligence agents to control machines such as microscopes. The Model Hardware Standard, or MHS, is the fruit of a collabo
arXiv:2608.25158v1 Announce Type: cross Abstract: Evaluating the ability of large language models (LLMs) to discover software bugs is increasingly important. Existing benchmarks typically evaluate thi
arXiv:2608.23653v1 Announce Type: cross Abstract: AI agents are increasingly used for simulation-driven engineering. Physical system modeling presents different requirements from general-purpose code
I was just curious how the new qwen3.8:27b does on a hard C to HTML porting job against Opus 5 in a default Claude Code. The job: my fun side project is a procedural shooter in a single C file. Port i
.@poolsideai engineers were awesome to collaborate with to launch open models. Excited for what’s to come to open models, and the @nvidia team working on Nemotron. A sweeping agreement with startup Po
What's Changed mlx: fix mac assumptions on linux/windows by @dhiltgen in #17898 mlx update by @dhiltgen in #17886 lint fixes by @dhiltgen in #17897 app: add claude desktop app by @ParthSareen in #1789
Couldn’t have said it better myself. AI is excellent at discovering things which are already very well understood somewhere else. How Anthropic's new results post would read without the PR: Claude orc
@Kimi_Moonshot Kimi K3 is now available on Ollama's cloud subscriptions. We are working on improving Ollama's cloud to be much more transparent on the pricing to show the best performance / $. Try it
Howdy, I'm back again - running my favorite benchmark (it's still unsaturated for the time being so might as well!) previous runs a b https://github.com/michaelasper/benchmarks/blob/main/qwen3.8-27b-p