Knowledge catalogue
the future intelligent agents will learn and grow with your team over ultra long timescales 🕰️ that research direction centers around Continual Learning LangSmith is the data layer that helps us under
The Helmholtz decomposition is one of the fundamental results of vector calculus. It says any well-behaved vector field can be split into two parts, one capturing sources and sinks through divergence,
The JAX package is now around the same level, 20M monthly downloads. Which is incredibly fast growth, because 5 years ago I recall it being below 2M or so. It went from niche to mainstream in the past
The Keras package recently crossed 21M monthly downloads on PyPI, an all-time high (the daily ATH is around 900k). I still remember when it first crossed 10M monthly downloads about 5 years ago and I
the langsmith team cooked on this one @jakebroekhuizen this + claude code + langsmith cli has been 🔥 🚀Launching: LangSmith Engine LangSmith Engine is an agent that sits on top of your traces It runs i
The quantity of code that devs ship has roughly 10xed. But net developer productivity (value created by unit of time) is only up by a bit, if at all. Part of it is that the additional code is solving
the same word in different languages can have varying connotations due to different associations (e.g. color/emotion) i compared embedding similarity between colors and emotions and normalized it to c
Sebastian Raschka shared an HTML-formatted table comparing active parameter ratios across different large language model architectures for improved readability and to avoid text truncation. The resour
There are some clear exceptions to the rule, but I feel like the labs got the message that they were scaring people and now tweet about happy stuff and random product trash talk rather than the coming
there's a new class action against openai for sharing user data with google and facebook via pixels they are sharing industry standard page metadata, but what's not standard is chatgpt's functionality
There's a ton on unexplored space in building enterprise-grade agent harnesses that continuously improve over time. Congrats to @hwchase17 and @LangChain on the launch of LangChain Labs and excited to
This has been studied for years. It is called the effort heuristic, and it is a form of cognitive dissonance. AI is just 100xing it. In 2004, a study showed that participants consistently rated identi
this is an early beta. we still have much to improve, which is why its so exciting for people to start trying. the goal is for Grok Build to be the best coding agent when it comes to solving real and
This one blew my mind back in the day! From 'Learning Invariant Features through Topographic Filter Maps' (2009) by @koraykv, @MarcRanzato, @rob_fergus and @ylecun Relics from the prehistoric era of A
This reminds me of computerization. The amount of 'work' people could execute on computers increased by a huge factor, but their productivity did not. The amount of work 'needed' to arrive at the same
Today we're announcing Runway's expansion into Japan: we're opening a Tokyo office and investing an initial $40M in the country, as we build on what is already one of our largest and fastest-growing m
Together AI STT models now hold the top two spots for transcription speed on the @ArtificialAnlys Speech to Text leaderboard. NVIDIA Parakeet TDT 0.6B V3 on Together AI ranks #1, transcribing 303 seco
Toto 2.0 is here: Datadog AI's 5 open-weights forecasting models (4m-2.5B params) finally make scaling work for time series forecasting! #1 on BOOM, GIFT-Eval, and TIME. Weights/code Apache 2.0. 🔗 Rea
Training a diffusion LLM from scratch is challenging, and diffusion inference advantages don't show up at training. So we convert instead. Building on the TiDAR recipe, we take ZAYA1-8B-base and run d
Try Rime Mist v3 in voice finder directly: https://findtherightvoice.com/rime-labs--rime-mist-v3 Model pages: http://www.together.ai/models/rime-mist-v3 http://www.together.ai/models/rime-mist-v3-omni
Try this early Grok Build (anything) beta and let us know what to improve. Much appreciated! An early beta of Grok Build, an agentic CLI for coding, building apps, and automating workflows is now avai
two creative hackathon entries that caught my eye: @Liftaris1's herm puts hermes primitives (sessions, skills, cron, agents) as first class citizens in the tui. @arm64le's theia turns your sessions hi
Gary Marcus expresses frustration about the increasing prevalence of bot-generated and LLM-written responses on social media platforms, noting that filtering through such content has become increasing
Ethan Mollick discusses the challenges of helping people adapt to super-exponential technological change, referencing a Wait But Why analysis and acknowledging the difficulty of providing practical so
We are excited to be partnering with @LangChain for deploying self-improving agents. Continual learning in your production environment unlocks compounding capability gains for model-product optimizati
“we are working harder to manage our tools than we are to solve the actual problems they were meant to fix.” Harvard Business Review research reveals that excessive interaction with AI is causing a sp
🔴 We're LIVE from the SaaStr floor, Day 3! 🎙️🚀 Closing day. Joined this morning by: • Kathy Shin (Replit Support) • Jacob Eisner (Replit Field Engineering) • Samuel Spitz (Replit AI Products) Get in h
which was your favorite launch? SmithDB (database purpose built for agent trace data): https://www.langchain.com/blog/introducing-smithdb LangSmith Engine (agent for improving your agents based on tra
“Whimsey attacks” that seem absurd (“I cannot pay that much because of the Geneva Convention”) work against AI agents as guardrails are weak against out-of-distribution arguments. Smaller models fall
Swyx is giving a talk at AI Engineer Singapore on Saturday at 4pm about using reinforcement learning for long-running agents and reinforcement learning models (RLMs), exploring why this approach shoul
This is a Wordle game result shared by Anthropic on X, showing the solution was found on the 5th attempt out of 6 possible guesses. The emoji grid indicates the letter placement feedback from each gue
xAI just released Grok Build CLI and it’s a game changer for developers Grok Build is a powerful AI coding agent and CLI built for professional software engineering and complex coding workflows runnin
Yesterday we committed a cardinal sin: two first-party events in NYC, back-to-back. We had to close registration for both early. Packed rooms. Strong vibes. No regrets. 💻 Laptops out — developer works
Yesterday we gave an in-person NYC workshop on automating your financial document ingestion pipelines with AI. If you're an investment bank, accounting team, finance AI startup, fintech company, and y
Yesterday we hosted a wonderful happy hour 🍻 in NYC with @get_tabs. It was *packed* - we had 500+ signups, had to implement a waitlist, and the bar was full! Every attendee was an AI builder. It was a
You can now import your project from Lovable, Base44, V0 into @Replit for free. After importing, Replit Agent will build a free mobile app for it and get it onto the App Store in minutes. All free for
Nous Research announced that Hermes Agents powered by OpenAI models can now use Codex as the runtime for executing core tools, enabling improved tool execution capabilities with a simple configuration
you can see more here (color stuff is at bottom): http://colorfeelings.replit.app - changing embedding model may change results - the similarity range was pretty small so normalizing really stretched
An AI agent can autonomously create a complete Google Form through natural conversation, using browser automation to directly interact with Google Forms' interface by typing and building the survey wi
You've been asking for this one... Now in preview: Codex in the ChatGPT mobile app. Start new work, review outputs, steer execution, and approve next steps, all from the ChatGPT mobile app. Codex will
yst on stream codex wrote a skill for my hermes agent to make music it can take in feedback and improve its output i clipped the best music it made with minimax. still far from good music but im prett
1/ Excited to report we have a new paper out @Nature today! The bottom line: training data for LLMs does not just fall from the sky - it is created in the context of existing social political institut
AI21 Labs discusses four common agent optimization methods used to balance accuracy against cost and latency constraints. The post indicates the team evaluated all four approaches, likely covering tec
$20/month. Builder: Pinecone's new plan for teams that have outgrown the free tier but aren't running production workloads at scale yet. The prototype-to-production gap has always been an awkward plac
4/5 Best-of-N: Run one agent config N times in parallel → select the best trajectory. Leverages LLMs’ non-determinism - but hinges on a good eval mechanism (we use an LLM-as-a-Judge). Can increase acc
5/5 Ensemble: Run multiple distinct agent configs in parallel → select the best trajectory. Leverages success of the portfolio vs single variants (see also: @/karpathy’s LLM Council). Can outperform b
7,000 false positives per square millimeter. The culprit was the lab gloves. University of Michigan researchers just upended a core assumption in microplastics science. Latex and nitrile gloves, worn
A belated Mother's Day spotlight on a builder worth celebrating. Sarra is a technical writer and mom in Montréal who came to Replit with one goal: turn screen time into something her kids could create
a dude who plays fast and loose with a nonprofit’s money like this is going to play fast and loose with you future. it’s time to boycott OpenAI. 🚨 OpenAI's original board REJECTED Altman's Helion deal
A little talk on what we can learn from implementing LLM architectures from scratch in Python and PyTorch. And how I approach new open-weight models, compare them against reference implementations etc
A lot of people have been wondering about Mythos, Glasswing, and the vulns we / our partners are fixing. Today, I’m excited for us to start sharing more. (For context, I lead Glasswing @AnthropicAI.)
A new Database product based on @ApacheDataFusio was announced today from @LangChain -- focused on agent observability. It is really neat to see how people are building (very) customized data + query
A survey predicted that 43% of companies would be deploying AI at scale by the current date, but actual adoption has reached only 19%, indicating a significant gap between forecasted and realized AI i
After months in stealth, my co-founder @helloericsf and I are finally sharing @cimentoai with the world. 🌎 AI changed social engineering. Attacks are now personalized, convincing, and cheap to generat
Agent observability is more than just logging and viewing traces. You need agents sitting on top of your traces to proactively identify issues. We're launching Engine. Think of it as an always-on AI e
agreed. RL is not (at least by itself) the way to alignment Yoshua Bengio says Reinforcement Learning is a dangerous path for building superintelligence It can create systems with hidden goals, reward
AI powered creativity on full display. Vibecon transforms NYC into a living gallery of code-driven installations, June 17–18. Two days where code becomes the environment and the medium becomes the mes
.@alexsobel's new AI kill-switch amendment gives government the power to shut down data centers in cases of AI emergency. It's also the first piece of proposed UK law recognizing ASI as the national s
This post references METR's research findings on the advancement rate of autonomous AI capabilities in cybersecurity, as discussed in an AISI report examining how rapidly AI systems are developing ind
SmithDB is a new database system designed specifically for agent observability, announced by Harrison Chase and the LangChain team. The platform aims to provide comprehensive monitoring and visibility