All entries

a quick fix if you saw higher rate limit usage in Opus 4.7 today- hope you enjoy trying it out We fixed a bug where rate limits on Claude subscriptions weren't properly adjusted for long context reque

A 'race' implies that it is something that is worth 'winning', which is not the case for superintelligence. Whoever finished first is just the first to trigger irrecoverable catastrophe. 'There is no

A real issue with the current state of our knowledge on the work implications of AI is that there was a genuine discontinuity in AI ability with the rise of practical agentic systems in 2026. We were

🇿🇦 A senior South African politician just got caught lying about Starlink to protect mobile network operators. Parliamentary communications chair Khusela Diko claimed Starlink 'doesn't move the needle

A startup called Sabi just came out of stealth with a beanie that reads your thoughts. 70,000 to 100,000 miniature EEG sensors woven into the fabric. You put it on like a winter hat and type by imagin

Adithya is putting his work where his heart is. If you believe in open research and open AI, join a company that actually lives those values, not a closed-source, revenue-maximizing one! Quick career

Agent evals are drifting away from production reality. Most benchmarks use clean tasks, well-specified requirements, deterministic metrics, and retrospective curation. Production work is messier, with

Claude Code's session management capabilities and 1 million token context window are highlighted in this post, which references an official Anthropic blog entry. The feature allows developers to maint

Claude Code's session management features and 1 million token context window capabilities are now documented on the official Claude Blog. The post, shared by Thariq on X, covers how developers can lev

Americans have a natural tendency to think of our country as unitary, with states as mere administrative boundaries. But the ethnic and cultural differences within the USA are staggering, greater than

Anthropic says Opus 4.7 hits 80.6% on Document Reasoning — up from 57.1%. But 'reasoning about documents' ≠ 'parsing documents for agents.' We ran it on ParseBench. → Charts: 13.5% → 55.8% (+42.3) — h

As AI gets better at writing code, the developer's job shifts toward managing that output. The fastest-growing task categories: documentation (+62%), architecture (+52%), code review (+51%), and learn

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