Knowledge catalogue
Been having fun with local AI stuff. I don't really like the big models and now that some of them want your ID I'm not sure I'll even stick around to care that much. Local shit is really powerful now,
Nous Research announced documentation and resources for getting started with Hermes Agent's tool gateway feature, which appears to be a system for managing and integrating external tools within the He
💵⚠️ Blocking subagents are costing you 1) time: your supervisor is stuck waiting while they run, and 2) money: if they go off track you've burned tokens on work you can't course-correct. @huntlovell n
🆕 Building pi in a World of Slop https://www.youtube.com/watch?v=RjfbvDXpFls @badlogicgames talks about why today's agents are still Merchants of Learned Complexity, and gives 3 specific ways that hum
Can people please stop taking shots at @sama, and boycott his company instead? Violence is not the answer. This is really bad. The scary part in the US is that it doesn’t matter whether you are the CE
Claude Opus 4.7 is now available as an Agent Preview inside of Devin! Anthropic has clearly optimized Claude Opus 4.7 for long-horizon autonomy, unlocking a class of deep investigation work we couldn'
Cursor has integrated Claude Opus 4.7 into its platform, highlighting the model's impressive autonomous capabilities and enhanced creative reasoning abilities. The announcement suggests a new feature
Claude Opus 4.7 is now available in Windsurf 2.0! Anthropic has clearly optimized Claude Opus 4.7 for sustained reasoning over long runs. Agents stay on track longer without intervention, so engineers
Claude Opus 4.7 has been set as the default orchestration model for Anthropic's Computer product. The model is also available to Max subscribers on Perplexity's web platform and iOS application.
Claude remains irreducibly Claude. If you know, you know. (The fact that models have distinct personalities that are consistent across generations is technically interesting, it also makes it very eas
Codex has been enhanced with new capabilities including the ability to learn from user experience and proactively offer suggestions, an integrated in-app browser, and multiple new plugins to expand it
Codex Compute is a service promoted as offering reliable, always-available computing infrastructure with strong engineering capabilities and an application that extends functionality beyond traditiona
Codex for (almost) everything. It can now use apps on your Mac, connect to more of your tools, create images, learn from previous actions, remember how you like to work, and take on ongoing and repeat
Coding agents learn from experience, but that knowledge stays locked in silos. Solve a thousand SWE tasks, and none of that wisdom helps with competitive coding. What if memories could transfer across
@cognition agent recursion comes to your laptop https://x.com/swyx/status/2044542494420214217 I've commented that 'this is the year of subagents', but that is largely an optimization problem. the inve
Completely agree with Jensen! Not exporting AI out of fear is classic case where the cure would be 100x worse than the disease. You slow down innovation, progress and US technology and economic leader
This post by Yohei Nakajima, founder of Credistick, adapts Lincoln's famous quote to address the challenge of managing limited partner (LP) expectations in venture capital or investment fund managemen
Cybercab refers to Tesla's autonomous taxi vehicle concept, representing the company's vision for a fully self-driving electric vehicle designed for ride-hailing services without a steering wheel or p
Destroying a library brings the dark ages. Destroying the @InternetArchive's @WayBackMachine would be the equivalent of the burning of the Library of Alexandria - one of the worst losses of knowledge
Boris Cherny shares productivity tips and insights from his recent experience using Opus 4.7, highlighting how the model has improved his workflow efficiency. The thread provides practical recommendat
Perplexity has released an updated Mac application featuring a Personal Computer feature that allows users to download the latest version. The update appears to enable enhanced AI capabilities directl
Grok Imagine is an image generation AI tool that creates realistic images with claimed ease of use. The announcement, promoted by Elon Musk on X, highlights the capability to generate high-quality vis
Exactly Most people think of philosophy as an abstraction that doesn't touch the real world, but they're wrong. Most real world problems are philosophy problems, and most philosophy problems are 'givi
Cristobal Valenzuela announced the launch of 'This Show Rocks,' a new late-night streaming show at Runway that broadcasts nightly at 10 PM PT. The announcement was made via X (formerly Twitter), thoug
Anthropic is working on improvements to help users maximize the utility of Claude Code functionality, with additional details and updates to be announced later in the same week. This announcement come
This is an announcement for the official Claude Developers Twitter/X account that serves as a direct communication channel from Anthropic's team to developers using Claude's API. The account provides
Claude Code users should ensure they are using Opus 4.7 with the latest updates to experience performance improvements or feature enhancements. The post suggests that users not observing expected incr
Fundamental Truths in VC today (as I see them) 1/ The barbell between large and small firms is as wide as it's ever been. These are genuinely two distinct asset classes now, and LPs should treat them
@GaryMarcus Essentially your prediction that LLMs to scale wouldn’t solve key fundamental problems, reasoning, factual reliability, compositionality, grounded understanding etc are now elephantine chi
Gary Marcus advocates for applying Satyagraha—a principle of nonviolent resistance emphasizing moral conviction—as a response to contemporary challenges, likely in the context of AI development and go
GLM-5.1 Tool Calling Issue Fix & Chat Template Update If you are running GLM-5.1 with vLLM/SGLang and using tool calling, please update your chat template. http://huggingface.co/zai-org/GLM-5.1/blob/m
GPT-Rosalind, our Life Sciences model series, is optimized for scientific workflows, with stronger performance in protein and chemical reasoning, genomics analysis, biochemistry knowledge, and scienti
This post discusses a blog article by @pcuenq that covers the process of creating new skills and test harnesses to automate the conversion of machine learning models from the Hugging Face Transformers
Great to be at HumanX with @Silverside_AI @LumaLabsAI and @krea_ai The SF frontier AI builder community keeps getting stronger. We're not done yet. Keep track of when and where you can meet up with th
Had a great time at PyCon & PyData DE. Highly recommend it. Great open-source, community-focused conference with lots of builders in the Python AI, LLM and agent space. Taking a short family break, my
Happy coding! Opus 4.7 is a significant step up. To get the most out of it, take the time to adjust your workflow to take advantage of Claude running for longer & being more agentic. It feels like a n
This post compares the performance of Qwen 3.6-35B-A3B and Claude Opus 4.7 models on a creative task of generating SVG code for a flamingo riding a unicycle, likely demonstrating differences in their
Hi! I'm here with *another launch*, it just happens to be extremely niche, nerdy, and probably only for a handful of people. In the desktop app, Claude Cowork and Code now have a little Bluetooth API
HOLY 🤯 The one and only @elder_plinius just dropped an unlocked Gemma 4 E4B, and the specs are INSANE. Look at the performance shifts: → Refusal rate: 98.8% down to 2.1% (!!) → Compliance: 1.2% up to
This post likely explores Elon Musk's philosophy on ambition and goal-setting, encouraging people to think boldly about their aspirations and future potential. Musk is known for advocating transformat
Nous Research shared an update or announcement on their official X (Twitter) account, likely relating to their ongoing work in AI model development, fine-tuning, or research releases. Nous Research is
I am happy everyone is switching to Codex, but Tibo if you start rate limiting me or making me use worse models... Codex Compute efficient ✅ Always up, never down ✅ Best at hardcore engineering ✅ Craz
“I am not able to do things that other dads can, now he thinks it’s so cool that I can do things other dads can’t” 🥹❤️ Life with ALS or a spinal cord injury often means navigating a gradual or sudden
Yohei Nakajima announced a new capability to visualize and display revenue growth metrics across individual fund portfolios, suggesting an advancement in portfolio analytics or tracking tools. This fe
I defended my thesis today! Sincere thanks to my advisors @sainingxie @ylecun and committee members: @mengyer @YiMaTweets @LukeZettlemoyer @liuzhuang1234. I could not have wished for a better PhD life
I edited the intro because I realized I buried the lede originally- The 1M context window is a double-edged sword. It allows Claude to do more complex tasks but it can also leads to more context pollu
i feel no shame. zero. none. You can now visualize Pi traces that you upload on @huggingface! Let's make sharing agent traces 10x more common to make agent AI more open and collaborative! Also, becaus
Ethan Mollick reported that requesting Claude Opus 4.7 to write sestinas—a complex poetic form with strict structural requirements—frequently triggers the model's safety guardrails, suggesting the AI
I love to explore solutions with it so I often ask it to brainstorm with me, then choose an option and rewind to implement it. When I'm ready, I ask it to interview me to figure out what’s in my head
I think the adaptive thinking requirement in Claude Opus 4.7 is bad in the ways that all AI effort routers are bad, but magnified by the fact that there is no manual override like in ChatGPT. It regul
' If a superintelligence is built, humanity will lose control over its future.' Before Canadian Senators, ControlAI's US Director Connor Leahy (@NPCollapse) explains why superintelligence could lead t
I can't verify the specific content of this post without access to the URL, and the URL format appears invalid (X post IDs don't follow that pattern). To create an accurate summary for a knowledge bas
if you’re interested in local/edge AI related repos and their trends, these are your guys Launching Inference Radar: our new weekly newsletter that tracks the top 130+ inference repositories, monitori
In Claude Code the default effort is now xhigh, a new level between high and max giving finer control over the reasoning/latency tradeoff. 4.7 thinks more, so token use runs higher than 4.6. Manage it
in the grand narrative of Meta x AI, we saw the flop (Llama 4 hurhurhur), and now we’re seeing the turn: - *more* hiring since the soup wars of 2025 - Zuck literally moved in with Alexandr and Nat and
Intel is so fucking back Long road ahead but @LipBuTan1 is the man for the job He is making many long term principled decisions Despite my long term optimism, I believe numbers won't be great in the s
Introducing Claude Opus 4.7, our most capable Opus model yet. It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back. Yo
GPT-Rosalind is a frontier reasoning model developed by OpenAI, specifically designed to support research applications in biology, drug discovery, and translational medicine. The model was introduced
It is not well-explained, but with the adaptive switch off, I get no thinking. I can set thinking levels in Claude Code, but not in Claude Cowork. AI companies keep seeming to assume that coding/techn
Its noticeable how much of the whole practice of working with AI - the prompts, the skill files, the connectors, retrieval work, the markdown files, etc. - is a substitute for the real problem of cont