Search: “context”

Meta is planning to power its AI data centers with solar energy beamed from space. If it works, solar farms could produce power 24/7 without batteries or backup generators. The company behind it all i

This post draws a comparison between how parents measure their babies' development and relationship milestones, noting that both shift from month-based to year-based metrics around the 18-24 month mar

Elon Musk expressed enthusiasm for large-scale machinery in a post on X (formerly Twitter). The statement likely reflects his interest in heavy equipment or industrial machines relevant to his compani

The year of the harness 🤝 Harnesses are our most direct layer to turn a model into a great product experience for users by shaping model behavior towards a goal This matters today because models have

I cannot provide an accurate summary for this entry as the title appears truncated and incomplete, cutting off mid-sentence. The text suggests a discussion about open source security concerns and geop

Jerry Liu predicts that genuinely useful long-running AI agents will become a reality by 2026, viewing this development as simultaneously inevitable and remarkable. The post reflects on how advances i

create_agent - how we build Deep Agents on the simplest harness primitive underlying all of the harness engineering, research, and API design in Deep Agents is a very simple primitive in LangChain cal

most of the time, you want an agent loop to run uninterrupted. that's where the utility comes from! but some decisions shouldn't be delegated to the agent. two situations come up consistently: 1/ befo

NEW paper: Recursive Multi-Agent Systems // Recursive Multi-Agent Systems // Great read for the weekend. (bookmark it) Multi-agent systems often pass full text messages between agents at every step. T

Sam Altman highlights a feature called 'pets in Codex,' suggesting it's a practical tool within OpenAI's Codex that may seem minor but offers more utility than initially apparent. The post encourages

On 5/5 @realDanFu and team will discuss DSV4’s hybrid attention and KV cache efficiency, should be a great session! Join us Tue 5/5: #DeepSeek-V4's hybrid attention + sparse MoE reduces KV cache up to

When training Grok 4.3, we spoke directly with devs and businesses to understand what they actually needed: a model that’s fast, affordable, and great at tool calling. The result is a daily driver tha

Codex allows users to iteratively refine documents and presentations by opening files, requesting modifications, and making adjustments within a single conversation thread. The tool enables a collabor

Goblin and related magical mentions were overrewarded in training, and the behavior was reinforced over successive models. We removed the goblin-affine reward signal for future models, and filtered tr

Hermes Agent + LM Studio 👾🪽 LM Studio is the most popular way to run open-source LLMs on your own hardware. Your Hermes Agent now runs natively on @lmstudio: auto-discovering your models, loading them

LM Studio is the most popular way to run open-source LLMs on your own hardware. Your Hermes Agent now runs natively on @lmstudio: auto-discovering your models, loading them on demand with the right co

// OCR-Memory // Well this is a unique approach to store memory for long-horizon agents. Most of the agent memory systems compress trajectories into text summaries and hope the model remembers what ma

Did a very different format with @reinerpope – a blackboard lecture where he walks through how frontier LLMs are trained and served. It's shocking how much you can deduce about what the labs are doing

Full Workshop: @OpenAI Codex masterclass The agent is no longer just one chat window. In this workshop, @reach_vb and @kagigz get into how coding systems start to change when you can delegate work acr

IMO DeepSeek v4 demonstrated utter confidence and competence by not benchmaxxing, not focusing on some BS final run cost, not even spending inference-optimal compute. just showed up, demonstrated SOTA

Proactive agent that thinks and acts like you. Multiplayer AI Brain for teams. Proper GUI for commanding 50 agents. http://Sauna.ai is all three. Sauna goes live today. First 2000 people, use access c

Qwen 3.5 from @Alibaba_Qwen is now available on @FireworksAI_HQ Training Platform across the Managed and Training API workflows. Try SFT, DPO, RL with smart defaults or your own custom loss function w

Scientists just built a robot smaller than the width of a human hair (!) It has no motor, no computer and no battery It's a 3D-printed, flexible chain of microscopic segments that, after being hit wit

The DeepSeek-V4-Pro discount has been extended until May 31, 2026, 15:59 UTC! 🔥DeepSeek-V4-Pro API is 75% OFF until May 5th, 2026, 15:59 (UTC Time)! Don't miss out on this massive discount. 🛠️Integrat

This post appears to discuss allegations that a U.S. President sought to obtain $10 billion in taxpayer funds for personal use. The content is incomplete in the provided title, making it difficult to

Excited to support @NVIDIA Nemotron 3 Nano Omni, now available on Fireworks. It's the first open model that handles vision, audio, video, and text in a single inference loop. Built for multimodal sub-

Replit's Free Agent feature will be available starting at 5:00am PST on May 2 for a 24-hour period. This announcement likely indicates a limited-time access window for users to utilize the Free Agent

GLM 5.1 from @Zai_org is now available on @FireworksAI_HQ Training Platform across the Managed and Training API workflows. Try SFT and DPO with smart defaults or your own custom loss function with a 2

Introducing Mesa: the most powerful filesystem ever built, designed specifically for enterprise AI agents. Every team building agents eventually hits the same wall: where do the files live? Not the ch

Nemotron 3 Nano Omni is available locally on Ollama! This requires the latest Ollama 0.22 release. Meet Nemotron 3 Nano Omni 👋 Our latest addition to the Nemotron family is the highest efficiency, ope

Should we care about AI happiness? In our new research, we find evidence of functional AI wellbeing across several independent measures. We find which AI models are happiest, how to make them happier,

this is a great read on thinking through how to simplify agent orchestration to it’s core interestingly converges on an architecture very similar to babyagi 2, which stored functions (agent tools) in

'AI should elevate your thinking, not replace it.' I don't disagree, but the issue is that current LLMs are not really trained to support that out of the box. I've solved this by building my own agent

Gemma 4 (26B + 31B) from @GoogleDeepMind is now available on the Fireworks Training Platform across the Managed and Training API workflows. Try SFT and DPO with smart defaults or your own custom loss

going to buy 2 rtx 6000 just because of the capabilities of local models becoming great! no more outsourcing of research to the api Xiaomi MiMo-V2.5 is now officially open-sourced！ MIT License, suppor

Introducing our new work: “Learning to Orchestrate Agents in Natural Language with the Conductor” accepted at #ICLR2026 https://arxiv.org/abs/2512.04388 What if we trained an AI not to solve problems

Progressive disclosure keeps agents focused. Join us at Interrupt May 13-14 for a conversation with @levie about @Box + Deep Agents https://interrupt.langchain.com/ AI agents work better when they bri

Xiaomi MiMo-V2.5 is now officially open-sourced！ MIT License, supporting commercial deployment, continued training, and fine-tuning - no additional authorization required. Two models, both supporting

This post announces a 'Proactive Agent Build Day' event hosted by AGI House in collaboration with Even Realities, with registration available through their events platform. The event appears to be foc

In other words, you need the world models that LeCun, Schmidhuber, Fei Fei Li, and I have been advocating for all along. Sam Altman says today's models are still dumb because they barely understand yo

Scaling massive monolithic LLMs continues to yield incredible results. But to truly unlock their ceiling, the next frontier is test-time compute and dynamic orchestration. Nature solves complex proble

Gary Marcus argues that programmers are returning to handcoding despite AI tools, suggesting that AI-assisted coding has encountered practical limitations or drawbacks that make manual coding preferab

btw we are cooking something with @hhua_ (not final yet but keep calendar open after ICML in Seoul) 🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M con

🔥DeepSeek-V4-Pro API is 75% OFF until May 5th, 2026, 15:59 (UTC Time)! Don't miss out on this massive discount. 🛠️Integration Updates: 🔹Claude Code: Set model to deepseek-v4-pro[1m] to unlock 1M conte

Great paper on improving proactive agents. (bookmark it) Proactive agents act before you do. But how do you evaluate something that's supposed to anticipate needs you haven't expressed? This work intr

Ethan Mollick critiques a discussion about permanent underclass as being 'incredibly toxic,' likely addressing harmful rhetoric or assumptions about socioeconomic stratification in society. The post a