All entries

i recently left @Bloomberg after two great years. incredibly lucky to have joined @LangChain in time to work on this 🚀 Spend less time on triaging Ship fixes faster Catch regressions earlier Introduci

I setup Hermes this week. A lot of you said you want to try it out, I'm documenting the whole journey, week by week, what it learns, what it builds for itself, what this agent actually becomes after a

I spent a week on the ground in China visiting 14 AI labs. The more I saw, the clearer it became that export controls may have inadvertently created a durable efficiency moat – Chinese labs are extrac

I was going to say LangChain Labs is the most exciting thing we’ve announced recently, but with so many launches it’s hard to justify… but still incredibly thrilled to see this get started!! Checkout

if you want to mainline hermes agent memory architecture real quick... the three-tier memory of Hermes agent. AI agents forgets everything when your session ends. Hermes doesn't. it has three memory l

This post references a LangChain Interrupt event where Brace Sproul and Caroline shared insights about applied AI leadership, with the author suggesting that effective heads of applied AI need signifi

if you're already thinking about hacking around on agents this weekend, why not play around with @videodb_io api and potentially win a prize? videodb is an API for turning streaming video into text in

if you're an artist or creative wondering how to use agents to accelerate your work, or skeptical that they can: please stop what you are doing and look at the 6 examples in this thread The Hermes Age

If you're calling a third-party API, your competitor can make the same call tomorrow. @lqiao is the keynote speaker at @pycon tomorrow, breaking down how to build a durable moat using fine-tuned model

In 1859, Charles Baudelaire, perhaps one of the greatest artist of his time, said that photography was “art’s most mortal enemy,” arguing that it was a mechanical, soulless tool that should be restric

In the @nytimes, Media Lab Prof. @kesvelt and other scientists call for stronger oversight and regulation of AI technologies, including chatbots that can provide information on producing lethal biolog

in this embedding analysis, compared to other futuristic tech terms, AGI maps more strongly to anticipation than fear, especially in english, japanese, chinese, and italian it also shows stronger nega

Install. Try. Share Feedback. Ship stuff. An early beta of Grok Build, an agentic CLI for coding, building apps, and automating workflows is now available for SuperGrok Heavy subscribers. Through this

Interesting position paper on agentic AI as a foreseeable pathway to AGI. (bookmark it) There has been strong debate on whether a larger single model get us there or a multi-agent system. The authors

This post discusses how color-emotion associations vary across different languages and cultures, suggesting that analyzing color symbolism linguistically reveals distinct patterns in how colors are ma

Introducing LangSmith LLM Gateway: The runtime governance layer for your agents. 💸 Enforce cost limits 🔒 Detect PII ✅ Act on violations …All without leaving LangSmith. Now in Private Beta https://www.

Introducing Rime Mist v3 on Together AI, a production TTS family built for deterministic pronunciation and controllable voice output. AI natives can now deploy @rimelabs Mist v3 on Together AI dedicat

🌟Introducing🎻Violin — an Open-source Video Translation Skill. 📹Video is the dominant medium on the internet, yet most high-quality content (lecture, talk, podcast) is locked behind a single language,

Elon Musk humorously comments on the broad range of design challenges he oversees across his various companies—social media (X), artificial intelligence, and space exploration (SpaceX)—suggesting the

Jake will be working with a lot of folks on continual learning - if that’s interesting, reach out to him! An exciting time to be working on Continual Learning and everything around it - if you’re work

LangChain Labs is a new applied research initiative announced by LangChain focused on advancing continual learning capabilities. The effort represents the company's commitment to developing systems th

Kimi K2.6 and DeepSeek V4 Pro are now GA on @FireworksAI_HQ on Foundry + PTU support in the US Data Zone—predictable performance, data residency, enterprise SLAs. Frontier open models. Azure controls.

Kimi K2.6 is now open-weight #1 on Finance Agent Benchmark V2. Can AI do the job of a financial analyst? We just released V2 of our Finance Agent Benchmark and tested the frontier models. The results

LangChain 在 Interrupt 大会上发布了底层数据库 SmithDB 和自动化排障引擎 LangSmith Engine。 Agent 运行会产生海量 trace（执行轨迹），把旧数据库撑到了瓶颈。新底座 SmithDB 放弃了本地磁盘，全面转向对象存储，将核心查询速度拉高了 15 倍。 底座换新后，LangSmith Engine 顺势接管了查 Bug 的体力活。它在后台持续监控生

LangChain Labs has launched as a new initiative from the LangChain team. The announcement was made by Harrison Chase, the creator and lead developer of LangChain, on X (formerly Twitter). LangChain La

LangSmith Engine, 6 months later imo, reading and analyzing long agent traces is a huge bottleneck and obstacle for progress (especially as these systems grow in time horizon). Imagine reading a langs

LangSmith Engine feels like the missing piece for reliable agents. Clustering failures and suggesting targeted fixes turns raw traces into actionable improvements. This is how we scale agent developme

LangSmith Engine is a phase shift because traces are no longer just records to be manually inspected, they’re now the catalyst for recursive agent self-improvement Engine looks at your traces, finds w

LangSmith Fleet has introduced a free model option powered by Fireworks AI for users on Developer and Plus plans, lowering the barrier to entry for getting started with the platform. This update makes

Like any AI dev not employed by a closed lab, we share the ambition that at least 10x more should be capable of training frontier models in 2026. And like we all know, some 10x leaps can't survive a c

NVIDIA AI has released an official getting started guide for Hermes on DGX Spark, providing new users with foundational resources and instructions for deploying or working with Hermes on NVIDIA's DGX

A utility tool was created to streamline sharing GPU profile traces by uploading them to Hugging Face buckets using the command `uvx trace-tuil -b `. This simplifies the process of distributing perfor

Making humans responsible for their AI use seems like an incredibly reasonable way to address problems & opportunities in the use of AI for academic research, at least in the short term (autonomous sc

Meet Kimi Web Bridge - Kimi's browser extension. Agent can now interact with websites like a human: search, scroll, click, type and complete tasks. Supports Kimi Code CLI, Claude Code, Cursor, Codex,

DeepSeek maintains the highest efficiency in terms of active parameters relative to total model size, outperforming competitors in the ratio of parameters actually used during inference versus total t

Mist v3 is available across two endpoints: 👉 rime-labs/rime-mist-v3 for English TTS 👉 rime-labs/rime-mist-v3-omni for multilingual TTS across English, Spanish, French, and German 👉 Custom pronunciatio

Mitchell Hashimoto argues that programming languages have historically created vendor lock-in effects but are increasingly losing that characteristic, likely due to standardization, interoperability i

Mitchell's post here reminded me of a similar conversation I had recently about how cheap it can be to port native mobile apps to React Native using coding agents... and then port them back again late

Model. Harness. Context. The 3 main components of agents. As you build more agents, context increasingly lives AGENTS.md, skills, policies, examples, + generated research files. Context needs its own

Nous Research is promoting two resources: the Novita Sandbox, a platform for AI experimentation and development available at novita.ai/sandbox, and the Nous Portal for subscription management at porta

Most teams can pick frontier models. Fewer can run them at production scale without hitting constraints in latency, throughput, and governance. Fireworks AI on @Azure AI Foundry provides the inference

Mythos, a security researcher or team, successfully exploited macOS security vulnerabilities in a five-day timeframe, demonstrating the relative speed at which determined actors can compromise Apple's

Natively-agentic is just one of the perks. The overall experience is a step change from anything out there. And then you add the focus to details, user experience, and how supreme the team behind this

Neural networks do math by rotating shapes. We found a shape-rotating calculator hidden inside an LLM – and it’s used for more than just math! (1/6) Media Neural networks might speak English, but they

New course: Transformers in Practice. You'll get a practical view of how transformer-based LLMs work, so you can reason about their behavior, diagnose problems like slow inference, and make smarter de

NEWS: OpenAI hit with Class-Action Privacy Lawsuit for Sharing ChatGPT Data with Google and Meta. Sam Altman's OpenAI secretly embedded Meta’s Facebook Pixel and Google Analytics into ChatGPT, turning