one of my favorite quality of life features
one of my favorite quality of life features Claude Code in the terminal will now show recaps when you switch focus away from the session and then come back. This should help you stay more in flow whil
Knowledge catalogue
one of my favorite quality of life features Claude Code in the terminal will now show recaps when you switch focus away from the session and then come back. This should help you stay more in flow whil
Hermes Agent is model & tool backend agnostic for a reason, everyone should have access to AI. We don't dictate the rules of use for your agent, YOU do Anthropic shut down an entire company's Claude a
I prefer my design tool to be more closely integrated with where my agents work. I spent a few hours building my own design tool (inspired by Claude Design) inside my orchestrator. I can use this with
Tool: datasette.io news preview The datasette.io website has a news section built from this news.yaml file in the underlying GitHub repository. The YAML format looks like this: - date: 2026-04-15 body
You can also set your autocompact threshold yourself and effectively lower your context window if you'd prefer. For example, 400k context is a good compromise: CLAUDE_CODE_AUTO_COMPACT_WINDOW=400000 c
This post discusses how handling large context windows (around one million tokens) in AI systems requires more sophisticated session management strategies rather than simplified approaches, contrary t
here’s a good application of harness permissions Programmatically Enforced Auto-Research: - auto-research loops usually expose a set of files that the agent is allowed to edit to hill climb a metric/e
LLM Knowledge Base → Slides When @karpathy shared his LLM Knowledge Base setup, many were wondering how to generate more visual forms of the wiki. There are many options, but I think @GammaApp is one
The model is not the agent. The harness is. You need to read this recent study, and a blog post from @hwchase17 ... (links below). It will resonate deeply. This diagram from a recent paper captures so
Deepagents is an open-source project by LangChain that implements deep research-style agentic workflows, enabling AI agents to perform iterative, multi-step research and reasoning tasks. The repositor
if you don't own your harness, you don't own your memory this is so true. even though Codex is an open source, it generates an encrypted compaction summary (that is not usable outside of the OpenAI ec
MiniMax M2.7 is available on Ollama's cloud, and is licensed for commercial usage. Use it with OpenClaw: ollama launch openclaw --model minimax-m2.7:cloud Coding agents, such as Claude: ollama launch
Most people building AI agents don't realize this until it's too late. Your agent's memory isn't a feature. It's your moat. 1. Closed harness = they own your memory 2. Switch models → lose all context
the fact that http://pi.dev agent is so good, with virtually no sophisticated harness whatsoever, is a testament to the fact token vendor (codex/claude) agents are overrated. highly. today's moat of c
Artificial intelligence leaders Anthropic PBC and OpenAI Group PBC are stepping up their efforts to compete for the enterprise, making their most advanced agentic tools more accessible to the largest
BREAKING: GLM 5.1 by @Zai_org overwhelmingly dominates design-centric coding tasks amongst open-weight models In the categories featured below, it is most comparable to Opus 4.6 by @AnthropicAI at ~1/
arXiv:2604.07729v1 Announce Type: cross Abstract: Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore imp
Vercel AI Gateway now supports Fast Mode for Claude Opus 4.6, an early experimental feature that delivers 2.5x faster output token speeds while maintaining the same model intelligence. It is partic...
Pinecone now has a native extension for Gemini CLI. gemini extensions install https://github.com/pinecone-io/gemini-cli-extension → 9 MCP tools → 7 skills (quickstart, query, assistant, RAG and more)
🚀Deep Agents deploy Today we’re launching Deep Agents deploy in beta. Deep Agents deploy is the fastest way to deploy a model agnostic, open source agent harness in a production ready way. Open harnes
March ships Foundry Agent Service GA with private networking, GPT-5.4 and GPT-5.4 Mini, Priority Processing, Phi-4 Reasoning Vision, SDK 2.0 GA across Python, JS/TS, Java, and .NET, Fireworks AI and
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
Emad Mostaque (founder of Stability AI) posted a sardonic observation on X highlighting an ironic dynamic in the AI coding market: users pay for Claude Opus to generate low-quality 'slop' code, the...
i wanted to change my router firmware to openwrt and so i told claude to do it but of course the guard blocked me even opus 4.8 didn't want to do it , so i launched my Qwen3.8 27b and told it the same
model : Granite switch decision 256 options (#30693) feat(convert): Attempt to come up with 256 single-token, semantic option markers Each switch model needs to identify a collection of single-token o
Drama 3 officially needs an NVIDIA GPU with 48 GB. I wanted it on my RX 9070, so I built Red Curtain together with Claude. How it works: it's a 35B MoE with ~3B active per token. The FP8 experts (~32
ok i really need the prompt(s) for this video because this is near-kurzgesagt level clarity of explanation (not yet illustration) Media CLAUDE FOUND THE SEEDS https://www.anthropic.com/research/ecdsa-
The new models like Qwen3.8 27B and DeepSeek V4 Flash etc., all have this terrible, Claude-sounding writing style that I can't stand. Here's an example of what I'm talking about: 'A probe that asks wh
I saw a post somewhere, I forget where, that suggested using sigmas instead of steps. I dug into this a bit, found the sigma schedule used by Qwen2.1, and had Claude derive a set of sigmas that follow
arXiv:2610.22324v1 Announce Type: new Abstract: One of the first steps of a research pipeline is generating ideas. Large Language Models (LLMs) are increasingly used to automate this step, but most of
Relevant to the comprehension challenge I posed in 2014 and my bet with Miles Brundage. We edited Mark Twain's Huckleberry Finn and fed it to 9 AI models to summarize a chapter, twice each. Only Claud
cuda : use SIMT implicit GEMM conv2d on AMD without WMMA (#30325) cuda : use SIMT implicit GEMM conv2d on AMD without WMMA Assisted-by: Claude Opus cuda : update conv2d SIMT comment cuda : skip SIMT c
openai staff are out there turning the office into a stealth game, while my biggest security threat is letting codex, claude code and sumus loose on a test branch without read only permissions enabled
🔮 Grok Bot email accounts and traffic will be larger than Gmail and 1000x more productive. Efficient Grok Bot email will liberate us from spam with high signal and low noise Claude Shannon would be pr
Grok @Bot memory transfer NEW GROK BOT! AI MEMORY TRANSFER! Your old AI knows you. Your new one shouldn't have to start from zero. 🧠➡️ Meet Memory Transfer, a @Grok @Bot that brings over what Claude o
Grok @Bot rocks I've been using Grok @Bot as my daily driver for a few weeks now and: - it has replaced 100% of my search-like queries on chatgpt / claude - it has replaced 100% of my Hermes usage & a
A lot of projects have come up recently consisting of specific hardware config specialized forks of existing conferencing engines, but they all seem to be made using Claude or OpenAI's biggest frontie
Learn to build custom harnesses, folks! Here is an impressive paper showing the impact of a good custom harness on long-context work. GLM-5.3-Flash goes from 4.4% to 61.1% exact match on OfficeQA Pro
Ive been using OpenWebUI's inbuilt web search and I can't put my finger on it, but it's not quite as polished, reliable, seamless as using Claude or Gemini. And its often slow beyond a limit that make
Based on my experiments and feedback from claude, it seems extremely unlikely and even if I get it working, not practical because of minimum context. But just asking here as a last effort. I'm able to
I've been using Claude Opus 5.5 to speed up Qwen3.8-27B on my PC (rtx 3090), it wrote a CUDA megakernel that is 1.4-1.9x faster than llama.cpp depending on the task/context length. The results and cod
arXiv:2610.11963v1 Announce Type: cross Abstract: A no-code fix resolves an invalid bug report by directing the user to change a setting, update to a version where the problem is already fixed, or adj
arXiv:2610.11559v1 Announce Type: cross Abstract: Coding assistants such as Claude Code and Codex have become a major application of LLM agents, yet existing benchmarks remain far from real-world use,
Sam Sabin / Axios: Anthropic launches the Critical Infrastructure Defense Program to provide AI models, threat research, and on-site support, starting with CrowdStrike and others — Anthropic is launch
llama : add a GPU cache for MoE experts kept in host memory (#29887) llama : add a GPU cache for MoE experts kept in host memory Assisted-by: Claude use llama_moe_cache_ptr Website: https://llama.app
Having a lot of fun experimenting with three.js. Still very far from even a demo but its tons of fun. After this project I'll want to try a godot workflow. 3.8FN truly feels like Claude 4.6 at home. U
whoops I hit send and went to a meeting, didn't realize the repo wasnt public- it is now! it's a chrome extension I use every day now https://github.com/ThariqS/ai-newtab you now get Claude API credit
Agent-to-agent communication with a personal agent on top is wild. Wow. I underestimated how well models like Opus 5.5 can coordinate already. This opens a whole new set of experiences with agents. Bu
Carl Franzen / VentureBeat: Anthropic cuts Sonnet 5.5 cache read price from 0.20 to 0.10 and adds monthly API credits: 100 for Max 5x, 200 for Max 20x, up to 500 shared by Team users — The model start
Frederic Lardinois / The New Stack: Anthropic prices Haiku 5.5 at 0.10/1M input and 0.50/1M output tokens for requests up to 100K tokens, and 0.50 and 2.50 above, vs. 1 and 5 for Haiku 4.5 — Anthropic
Today we're announcing OpenDocRouter: every model for document parsing under one API. There are ~4,000 OCR models on Hugging Face, and the frontier labs ship a new one nearly every month. Whatever's b
I asked Opus 5.5 to make an interactive website companion for the latest @AcquiredFM Home Depot episode. It came out pretty nice! Water color illustrations all drawn by Claude, too: https://claude.ai/
vulkan: sparse flash attention for quantized K/V (#29639) vulkan: sparse flash attention for quantized K/V Assisted-by: Claude vulkan: single-scan sparse FA index compaction The compaction ran one wor
vulkan: fix stale prealloc_y reuse across flash attention and soft_max (#29591) Assisted-by: Claude Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52808438
Amazon SageMaker optimized generative AI inference introduces the aws-ai-ml skill through the Agent Toolkit for AWS, giving coding agents like Kiro, Claude Code, and Codex deep expertise in inference
server : fix laya abort by limiting n_batch to n_ubatch (#29903) server : fix laya abort by limiting n_batch to n_ubatch Fixes #29902 Assisted-by: Claude fix(review) : rm tests, embeddings cond Websit
The Economist's article on Effective Altruism said that some EAs 'even think the welfare of AIs themselves will one day be of vital importance.' It's not just some random EAs; it's coming from the mor
vulkan: disable large matmul tile on Samsung GPUs with 32KB shared memory (#28531) Assisted-by: Claude Opus Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/
arXiv:2610.00917v1 Announce Type: new Abstract: Choosing an agent system means choosing both a language model and the harness through which it acts. We ask whether a strong model, harness, or pairing
Hey guys, Last time I tested Qwen3.8-Flash-Next on its own. This time I put three Qwen3.8 checkpoints through the same 10 tests on the same RTX PRO 6000: RadixArk/Qwen3.8-27B-NVFP4 (dense) orcarouter/