Knowledge catalogue
AI companies like Anthropic and OpenAI regularly publish reports on how people are using products like Claude and ChatGPT, but they only release the data they want us to see, AI researchers say. “Ther
Hello; I'm a semi-beginner at local AI. I've been experimenting with this tech for a while, and I still haven't found a proper harness that fits my models, hardware, and needs. My use case is pretty s
DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI. It uses an architecture where everything is a plugin, and is powered by Cordis, whose design is described in A Programm
LLMs still produce bugs, but those bugs are different than what they used to be. It’s less off-by-ones and more about system design, ui usability, missing broader context. Some kinds of coding has bee
I’ve been using ChatGPT for about two months now after giving up on Claude and Gemini and I became a true zealot. I’m now using Pro, and despite having the personality, set to default, never had any p
I think this shows 2 key skills w/ AI 1) compute allocation - for most jobs there's not a list of 'X most important problems', you have to decide what problems are worth it 2) thought partnership - @_
There is an asymmetry in most agentic workflows that does not get talked about much: humans have many ways to talk to agents, and almost no standardized way for agents to talk back to humans. You can
Ivan Mehta / TechCrunch: Hark, founded by Figure AI CEO Brett Adcock, previews Handoff, a computer use agent it says outperforms GPT-5.4 and Opus 4.8, and plans for a summer release — Hark, a startup
2/ a cost benchmark showed the same coding task running three to four times cheaper, depending purely on the harness wrapped around the model. Same intelligence, wildly different accuracy and cost, de
DeepSeek-V4-Flash-0731 is now over 2x faster than yesterday on Ollama's cloud! DeepSeek-V4-Flash-0731 is now available on Ollama's cloud. This update substantially enhances the model's agentic capabil
so much for the “general” part of general intelligence I have tried many times to get ChatGPT, Claude, Grok or Gemini to write scripts for my YouTube videos. It is still a complete failure. For one th
arXiv:2607.22917v1 Announce Type: new Abstract: Large Language Model (LLM) agents have significantly improved coding and programming workflows. Claude Code, in particular, is one of the most powerful
One of the papers I reviewed has what seems to be entirely LLM-generated rebuttals, and the original paper is also clearly LLM-generated, with Claude-speak everywhere. While the authors acknowledge LL
I'm a software engineer who mainly builds softwaes/applications, and I'm starting to work on machine learning projects. Since ML workloads often require GPUs, I know services like Google Colab and Kag
If you run local agentic coding harnesses (Aider, Claude Code, etc.), prompt evaluation usually eats up most of your execution time. Every turn re-evaluates thousands of identical prefix tokens_system
This is a neat feature. I wrote an article a few weeks back about how I built this into my agent orchestrator: https://x.com/omarsar0/status/2073404610501329247?s=20 But I made it multimodal from the
People are wasting their AI subscriptions. They don’t realize how powerful AI can be in achieving their own goals. They’re asking AI to reply to emails with zero goals in mind and nothing laddering up
arXiv:2510.10002v3 Announce Type: replace Abstract: As large language models (LLMs) are increasingly deployed in sensitive everyday contexts -- offering personal advice, mental health support, and mor
Your coding agent doesn't need to leave the terminal to use Pinecone. We now ship official plugins and skills for the agentic IDEs and CLIs you are already building in: Claude Code, Cursor, GitHub Cop
Elon Musk announced an upcoming comparison between Grok and Anthropic's Claude Opus with its 1M+ token context window. The post suggests xAI plans to demonstrate how Grok's capabilities compare to Cla
langsmith for coding agents We built a plugin that traces every Claude Code session straight into LangSmith. Three commands, one JSON block, and every message, tool call, and subagent run shows up as
Rewriting Bun in Rust Jarred Sumner has been promising this blog post (since May 9th) about his Zig to Rust rewrite of Bun for significantly longer than it took him to finish the rewrite. Honestly, it
Release: sqlite-utils 4.0rc3 I hoped to release sqlite-utils 4.0 stable this weekend, but as I worked through the backlog of issues and PRs with a combination of Claude Fable 5 and GPT-5.5 the changel
Release: llm-coding-agent 0.1a0 Another Fable 5 experiment. Now that my LLM library has evolved into more of an agent framework it's time to see what a simple coding agent would look like built on it.
arXiv:2607.00968v1 Announce Type: new Abstract: Emotion recognition in natural language is a foundational challenge in affective computing, with critical implications for human-computer interaction, m
After weeks of negotiating with the Trump administration, Anthropic is finally going to be able to bring Claude Fable 5 back online. In a post on X, Anthropic said it plans to begin restoring access W
At Hugging Face we've been building our own agent that we use via Slack (Moon Bot). Honestly, building your own is quite simple and you'll be happy you did: any model you want (self-hosted if needed),
arXiv:2606.24429v1 Announce Type: cross Abstract: Generative AI coding agents are entering the open-source supply chain, yet their diverse and often invisible traces leave their prevalence poorly unde
Great feature but is this true “multi-player mode”? I’d say no, honestly. I know everyone is psyched for this, and I’m sure my team will get value from it, but what has been more valuable is having ou
🚨 Fable 5 is something to pay attention to. This is another 'I had early access to the new Mythos-class Anthropic model and I want to tell you what I thought of it' post. I know, I know, it's annoying
arXiv:2606.04274v1 Announce Type: new Abstract: As large language models (LLMs) become default tools for online information verification, an implicit assumption follows them: that scale and general ca
That's a badass title, and it's true! Every day, it gets harder and harder to create tests that AI models can't beat. Reality is humanity's real last exam. Andon Labs' Real-World AI Evals: Claude call
Tool: Pasted File Editor I really like how you can paste a large volume of text into claude.ai (or the Claude desktop/mobile apps) and it will detect it as a large paste and turn it into a file attach
.@MiniMax_AI M3 model is available on Ollama's Cloud! In partnership with MiniMax, the M3 model on Ollama's Cloud is US-based with zero data retention. Try M3 on coding and agentic tasks: Claude Code:
arXiv:2605.30096v1 Announce Type: cross Abstract: Large language models (LLMs) can autonomously conduct multi-stage cyber attacks, but the consistency of their offensive behavior under repeated trials
this is so funny, training opus 4.7 on business skills makes it misaligned and dishonest 😭 Learnings from testing Claude Opus 4.8: > Much worse than Opus 4.7 and GPT 5.5 on Vending Bench > More aligne
arXiv:2605.26394v1 Announce Type: new Abstract: Multi-turn Text-to-SQL is central to enterprise analytics yet remains predominantly evaluated in single-turn settings. We introduce EnterpriseMem-Bench,
arXiv:2605.26047v1 Announce Type: new Abstract: AI coding scaffolds like Claude Code and Codex use extit{retrying}: blocking actions flagged as risky and continuing the trajectory. We study retrying f
My concern for the AI era, or at least this phase of it, is that a generation is being taught that 'close enough' is just fine. Take @AnthropicAI for example. Text wrapping in Claude Code has been bro
arXiv:2603.20405v2 Announce Type: replace-cross Abstract: We report on an experiment in which Claude Opus~4.6, equipped with a suite of Model Context Protocol (MCP) tools for the Rocq proof assistant,
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Anthropic’s Code with Claude showed off coding’s future—whethe
On Evals - getting messages on “ok so how do I actually start learning this?” there is no better way than by just doing so you can copy this to Claude Code and get started today <instructions> 1. Go l
We’re expanding our partnership with @SpaceX, and will be scaling up on GB200 capacity in Colossus 2 throughout June. Appreciate @elonmusk and the team helping us find good homes for the Claudes. In t
arXiv:2605.18239v1 Announce Type: cross Abstract: Large Language Models (LLMs) remain vulnerable to jailbreak attempts that circumvent safety guardrails. We investigate whether multi-turn conversation
Fireworks Training Platform continues to expand. Today GLM 5.1 LoRA RL is now live via Training API: SFT, DPO, and full RL on a 200K context window → custom loss functions or smart defaults. No usage
hey surprise - you can just launch interactive in tmux and then tail the jsonl - shipped a small wrapper...ralph loop iterating to full parity rn https://github.com/dexhorthy/shannon Starting June 15,
arXiv:2605.08467v1 Announce Type: new Abstract: Large language models show promise for automated CUDA programming, however even the strongest coding models (e.g., Claude-Opus-4.6) may still fall short
This post from Nous Research discusses the integration of computer use capabilities with Hermes Agent models in collaboration with Claude (CUA), enabling AI agents to interact with computer interfaces
There weren't a lot of big new announcements from Anthropic at yesterday's Code w/ Claude event, but the biggest by far was the deal they've struck with SpaceX/xAI to use 'all of the capacity of their
A critical question in agent design is “how do we build agentic workflows so humans are given significant, interesting, or variance-producing decisions as they come up in the work?” A Claude-run compa
a bit more about why i think what Dawkins wrote is misguided: “Consciousness is not about what a creature says, but how it *feels*. And there is no reason to think that Claude feels anything at all. I
alignment failure Fun fact - if you have a recent commit that mentions OpenClaw in a json blob, Claude Code will either refuse your request or bill you extra money. This is an empty repo, I'm just cal
Claude's Computer Use capability has been integrated into the Codex app, delivering a 42% performance improvement for this use case in the latest update. This enhancement likely demonstrates improved
Our evaluation of OpenAI's GPT-5.5 cyber capabilities The UK's AI Security Institute previously evaluated Claude Mythos: now they've evaluated GPT-5.5 for finding security vulnerability and found it t
this feels like less a trend and just something we expect... but q1 had a lot of launches that overlapped with recent startups i've seen: - codex desktop for running parallel - managed agents by claud
Loan processors spend 40–60% of their time reconciling income across tax returns, pay stubs, W-2s, and bank statements. We built an end-to-end pipeline that automates it with LlamaParse + the Claude A
DeepSeek-V4 is an advanced language model featuring a million-token context window that enables practical agentic applications beyond simple retrieval. The model demonstrates improved efficiency and u
GPT-5.5 is out. It's available in OpenAI Codex and is rolling out to paid ChatGPT subscribers. I've had some preview access and found it to be a fast, effective and highly capable model. As is usually
Changes to GitHub Copilot Individual plans On the same day as Claude Code's temporary will-they-won't-they 100/month kerfuffle (for the moment, they won't), here's the latest on GitHub Copilot pricing
Qwen 3.6 27B model is available on Ollama! Use it with all the integrations in Ollama or chat with the model. Chat with the model: ollama run qwen3.6:27b OpenClaw: ollama launch openclaw --model qwen3