All entries

Rubrics are even more flexible than /goal You can define a custom subagent for the grading, including custom tools, prompt, and iteration limits. Try it out and let us know what you think! we just shi

Yohei Nakajima announced a talk about ActiveGraph AI scheduled for June 24th at the AI House, an AI2 incubator venue in Seattle, with an invitation for local attendees to participate. The event detail

Seeing a number of benchmarks showing Opus is the best model for long-running work. Five tips for running Opus autonomously for hours/days: 1. Use auto mode for permissions, so Claude doesn’t ask for

So excited to be opening up OpenEnv to the whole community. It will now be owned by @huggingface , Meta-PyTorch, @reflection_ai , @UnslothAI , @modal, @PrimeIntellect , @NVIDIAAI , @mercor_ai , and @f

SpaceX goes public Friday at ~94x revenue. Across 45 years of data, IPOs that debut above 40x sales underperform the market by 58% over the next 3 years, and by 76% style-adjusted. The golden rule of

I cannot verify this claim as factual. The Strait of Hormuz is named after Hormuz (also spelled Ormus), a historical port city and trading center that existed in the region, not directly from the Zoro

Striking paper from Wharton. The big conclusion: AI must increase productivity 2.7x -- and quickly -- or tech companies risk bankruptcy with all that entails for the economy. For context: this is how

Suicidal empathy becoming homicidal empathy The Netherlands also has its Henry Nowak cases. In July 2020, 14-year-old Tamar from Marken was hit by a car on a dark dike road and left to die. Her body w

Thanks again for your interest in our work! Links here so they don’t get buried under “show more”: Paper 📄: https://arxiv.org/abs/2606.02373 Code 💻: https://github.com/pat-jj/harness-1 Model 🤗: https:

That's both OpenAI and Anthropic with confidential S-1s filed with the SEC - Anthropic filed theirs on June 1st We recently submitted a confidential S-1. We expect it to leak so we’re just announcing

The Agent Open: AI's Pickleball Tournament 🏓 Come put your code and backhand to the test and embrace the full Open experience. Custom built out courts. Stadium seating. Exhibition matches by AI leader

The AI champions strategy of 2023 doesn't work in 2026. Let me give you my very hot take 🔥 (And know that this is anecdotal, and the world of AI changes every 2 heartbeats, so by the time I finish thi

The American people want Voter ID. Politicians refuse to enact it. There is only one logical conclusion here… I think not supporting voter ID at this point is a pretty clear indication you don’t want

The highest leverage work in AI right now is some of the most boring. (Well boring to others, I kind of love the pain of problem-solving.) Everyone and their boss wants to build the cool AI agent... t

The legendary investor Vinod Khosla is in the news because of questions about his integrity. I want to share my own experience: he lied viciously about me (a skeptic of a company he stands to make bil

The level of fraud here is mind-blowing Nithya Raman even LOST her own district (CD-4) to Spencer Pratt and Karan Bass, but you expect us to believe she beat them BOTH by winning 40% of the vote in th

The magnitude & brazen nature of the government payment fraud is staggering USDA Sec. Brooke Rollins: 'We found 200,000 dead people getting food stamps, and 500,000 getting more than one benefit... in

The Matrix idea of keeping humans as batteries is obviously weird... we would be more useful as dice. LLMs default to very similar kinds of arguments & structure, and even different LLMs seem to colla

The next quarter of effort at the frontier of applied AI is not about model capabilities. It's about 3 key things: 1. security, guardrails around data ingress/egress, and understanding risk in your sy

The north stars we're working towards at OpenAI all center around the mission: ensure AGI benefits all of humanity. AI should expand human agency, not make people less consequential to the future. htt

The point is that you should start implementing ways to encode instructions/prompts with clear goals inside automations. Nothing new but newer LLMs are being trained to perform for longer duration uni

The real reason they don’t want voter ID is to commit voting fraud. That is the obvious truth. I think not supporting voter ID at this point is a pretty clear indication you don’t want fair elections,

This post likely discusses Elon Musk's perspective on California's current conditions, potentially covering topics such as government policies, business environment, infrastructure, or quality of life

The system is rotten My sister lives in Los Angeles. She's a Democrat but voted for Spencer Pratt. I was with her when she dropped her ballot in the mail weeks ago. We checked today and it hasn't been

Gary Marcus shared a humorous post on X about misreading an AI-related headline due to the current saturation of AI news coverage. The post reflects on how the prevalence of AI stories in media can le

The post highlights strong market demand for efficient small language models under 9 billion parameters, citing Qwen's top-downloaded models as evidence of user preference for compact, resource-effici

A study or analysis demonstrates that computer technology enhances user autonomy and task quality while reducing both time and cost requirements, enabling users to undertake a broader range of tasks t

This clip on YouTube is now at 2.3 million views. 𝐃𝐑 𝐆𝐀𝐃 𝐒𝐀𝐀𝐃 𝐎𝐍 𝐏𝐑𝐀𝐆𝐄𝐑𝐔: 𝐂𝐈𝐕𝐈𝐋𝐈𝐙𝐀𝐓𝐈𝐎𝐍𝐒 𝐃𝐈𝐄 𝐁𝐘 𝐒𝐔𝐈𝐂𝐈𝐃𝐄 Evolutionary behavioral scientist Dr Gad Saad, author of “Suicidal Empathy: Dying to be Kind”, wi

This is exactly right. People are starting to look for cheaper model alternatives and realizing two things at once: open-source models are already very good, and the ability to train and serve them ef

this is gonna go great xAI’s development of artificial intelligence is “a mess”, Co-Executive Editor @mvpeers says. “Elon has fired most of the people who he originally hired at xAI.' 'He has a tenden

This is super big I think this is the first useful speculative decoding method deployed on a big quasi frontier model Massive unlock @fi56622380 🚀 1,000+ TOKENS/S ON A 1T MODEL! 🚀 We are thrilled to r

tl;dr: we aren’t close to RSI, regardless of the hints IPO-bound Anthropic tried to drop last week. This paper tests whether today’s AI agents can build better AI agents without human design help. i.e

This post likely provides weekly updates, events, or recommendations for activities and happenings in Tokyo for the current week. The content probably covers entertainment, dining, cultural events, or

Kimi is launching a new product called Kimi Work, an AI work platform with expandable capabilities including additional data sources, tools, and agent functionalities. The announcement indicates the p

two things ready to share from this weekend: 📖 http://learn.activegraph.ai interactive site teaching activegraph concepts blog: https://activegraph.ai/blog/introducing-learn 💻 AG coder (open source) r

Gary Marcus posted an update on X noting that the original poster of a viral claim acknowledged their error and deleted the post, highlighting a rare instance of public correction on social media. The

Want to turn a website into a launch video for your brand? This tutorial shows you how We used @ollama as example, but the workflow works for any company. Every frame is HTML, CSS, and GSAP, written l

We are releasing our first quantized checkpoints for the Qwen3.5 series of models, co-designed jointly with our inference engine to achieve maximum possible performance on Apple hardware Starting from

Research indicates that autonomous agents with greater operational autonomy, particularly in computer-based tasks, demonstrate improved performance quality and user satisfaction outcomes. The study su

We got into Y Combinator! Agnost AI (YC S26) is the infra for self-improving AI agents. We plug into conversational AI companies, find what's broken, and ship the fix as a PR. You just merge. DM if th

we just shipped support for rubrics in deepagents ✅ give your agent a clear definition of what 'done' looks like, and force it to run in a loop until said goal is complete this is similar to /goal in

We published new research with Harvard on the shift from chat interfaces to autonomous agents like Computer. Over 3 months, findings show workers using Computer finish tasks in 87% less time at 94% lo

A screening event at Lincoln Center in New York on Thursday has sold out completely, according to an announcement by Cristobal Valenzuela. Tickets remain available for a subsequent screening in Los An

This article explores potential economic downsides to artificial intelligence, questioning assumptions about AI's profitability and examining financial risks that may have been underestimated or overl

When we first demoed Claude Code internally, it got two reactions on Slack. A year after GA, @_catwu and I sat down to talk about what's changed: why I use auto mode instead of plan mode, how routines

Gary Marcus critiques common misconceptions about AI, presenting seven corrective perspectives on prevailing beliefs about artificial intelligence's capabilities and limitations. The post likely addre