Knowledge catalogue
This Replit broadcast covers security best practices for Vibe-coded applications and introduces new features or updates to the Connectors system, likely including integration improvements and enhanced
This post discusses a feature or workflow preference for managing terminal or development sessions by opening them in separate windows rather than keeping them in tabs or panes within a single window,
This article argues that specialized AI models often outperform larger, general-purpose models for specific use cases, challenging the common procurement assumption that bigger is always better. It li
The legendary art tech program that sparked the world’s first art NFT comes to Vibecon, pairing leading artists and technologists to make something new. Featuring @gucaslelfond, @frogspitsimulat, @del
This week, we shipped @QodoAI Findings. It's the natural next step from PR-by-PR review. Here's the problem it solves. If you manage an engineering team right now, you can probably answer a question a
Today we're open-sourcing Bumblebee, a read-only scanner for macOS and Linux. It checks developer machines for risky packages, extensions, and AI tool configs. Connected to Computer, it can trigger de
Together AI announced the availability of Qwen3.7-Max, a large language model, on their platform. The announcement promotes users to try the model through Together AI's interface. Qwen3.7-Max is part
Cursor provides SDK documentation and a /sdk skill to help developers get started with Python integration. The resource links to their official documentation at cursor.com/docs/sdk/python for setup in
With the Cursor SDK, you can build your own agents with Composer 2.5. It's now available in Python and TypeScript. This long weekend, Composer usage is 90% off in the SDK. We're excited to see what yo
- 50 credits for 250 earnings - 200 credits for 1000 earnings - 1000 credits for 10,000 earnings - 2,000 credits for 100,000 earnings Credits given for earnings starting May 1st More details here: htt
OpenAI's GPT-next model reportedly resolved the Erdős planar unit distance problem, a mathematical conjecture that had remained open for approximately 80 years, at a computational cost under $1000. Th
This post likely describes a feature allowing users to relocate or organize their side conversations (chat panels or sidebars) to different positions within an interface, providing flexibility in how
Vercel introduced functionality to configure weighted traffic splits for Vercel Flags directly through the Vercel CLI, enabling developers to control what percentage of traffic sees different flag var
This post discusses the financial success of professionals working in AI infrastructure (such as chips, compute, and backend systems) rather than AI research, noting that infrastructure workers are be
indicative although there are very important confounders here that have nothing to do with models https://x.com/swyx/status/2055231013253472418?s=20 also i think the publicly disclosed revenue time se
It was an honor to give the keynote at MLSys Covered how AI systems have evolved, why AI is needed to improve them, why results have disappointed, why the future looks amazing, and why I’m working on
New business creation on @stripe is up almost 2x year over year. Our founder @amasad sat down with @patrickc to talk about what's driving it, who's winning, and why entrepreneurship is the most under-
oh shit great minds lmao https://x.com/ericzakariasson/status/2057521364622553442?s=46 the most used skill internally at cursor right now /thermo-nuclear-code-quality-review - deletes complexity inste
The Vercel CLI now supports pulling anomaly alert details, allowing developers to programmatically access information about performance anomalies detected in their deployments. This feature enables in
Pinecone has updated its integration with Datadog to include expanded metrics and improved dashboards, enabling better monitoring and visualization of Pinecone vector database performance within the D
We turned this app into a real comic book booth at GTC! Had folks create their own comic books on-site, printed them, and gave them out! (this is using an unreleased version of the app that's a lot be
With over 400 billion impressions and campaigns for Netflix, Coldplay, and major beauty brands, @PaigePiskin is one of today’s most prolific AR creators. See her take the stage on day one of Vibecon.
Replit announced a monetization feature enabling developers to earn credits by monetizing their applications through Stripe Build integration. This allows creators to generate revenue directly from th
The Vercel Chat SDK has been updated to include message subjects functionality and direct SDK access capabilities. This enhancement allows developers to organize and manage chat messages more effectiv
Vercel has expanded its Chat SDK to incorporate AI SDK tools, enabling developers to build conversational applications with enhanced AI capabilities. This integration likely allows developers to lever
Vercel's Chat SDK has been updated to support callback URLs on interactive UI elements, specifically buttons and modals, enabling developers to trigger backend actions and handle responses directly fr
Pinecone hosted a live broadcast on X (formerly Twitter) inviting developers to build applications using their vector database platform. The broadcast likely covered Pinecone's capabilities for AI and
Context compression isn't new in RAG. Our contribution is making it query-aware, citation-preserving, and fast enough for orchestration. Read the full research blog: https://research.perplexity.ai/art
Cursor 3.5 is a new version of the Cursor AI code editor with updated features available for download. The announcement was made via Cursor's official X (Twitter) account, directing users to their dow
Fireworks is coming to Tech Week First up: Boston. We're co-hosting a rooftop founder social with @fin_ai and @TrustVanta — curated crowd, real conversations, limited space. Thu May 28 · 7–10pm · #BOS
I cannot provide a reliable summary for this entry, as the title 'Good yap' is informal social media language and the specific Spotify episode content is not accessible from the provided information.
Grok Build 0.1 has been released and is now accessible through the Vercel AI Gateway, enabling developers to integrate Grok's capabilities into their applications via Vercel's platform. This release p
AI Engineer World's Fair is offering tiered group discount pricing: 5+ attendees receive 10% off, 10+ attendees receive 15% off, and 15+ attendees receive 20% off. The event is scheduled for June 29 a
here! https://x.com/namanbarkiya/status/2054831268848869475?s=20 🚀 Inputr - Demo just dropped! A Chrome extension that instantly fixes any image upload box on the web. Upload + crop, create from scrat
How fast is 10 tokens per second really? Neat little HTML app by Mike Veerman (source code here) which simulates LLM token output speeds from 5/second to 800/second. Useful if you see a model advertis
IMO deep research has been ~dead since o3 and interactivity was always more impt for active learning and eliciting intention thoughtless prompt -> long ass report nobody reads is inferior to read -> t
LA-born new media artist whose installations, public sculptures, and live AV works blend AI, memory, and urban landscape, @NateMohlerArt is the founder of Projekt Blank. See his workshop and installat
Less noise = more signal. Vital content per snippet is up 63%. Ads, navigation, metadata, and unhelpful content are culled before handoff to the answer model. On SimpleQA, we achieve a 50x compression
MiniMax Speech 2.8 Turbo is built for voice agents that need natural delivery, not just clean audio. → Sound Tags for laughter, breathing, sighs, gasps, and other vocal cues → 60% prosody improvement
We have the ability to use compute resources to support our proprietary AI applications (such as Grok 5, which is currently being trained at COLOSSUS II), while also providing access to select compute
This article discusses how Applied Compute leverages Modal's infrastructure to scale reinforcement learning workloads, likely covering the technical implementation of distributed RL training, computat
The Vercel AI Gateway plugin for WordPress enables WordPress site owners to integrate AI capabilities directly into their websites through Vercel's AI Gateway infrastructure. The plugin likely provide
We've productionized query-aware compression for faster, cleaner, more-accurate search. Better context is better than more context. Our system cuts context tokens up to 70% while improving answer qual
This post likely discusses how meaningful work is enhanced and complemented by three key elements: the contextual environment in which work occurs, the specialized knowledge and skills brought to the
datasette-llm is a plugin that integrates LLM functionality into Datasette for language model operations. Version 0.1a8 represents an alpha release of this plugin that extends Datasette's capabilities
datasette-llm-accountant is a plugin that handles allowances and estimated pricing features for Datasette LLM usage. It works with datasette-llm and datasette-llm-limits to let users configure spendin
Vercel announced a flat-rate CDN pricing model entering limited beta, offering predictable content delivery costs instead of usage-based pricing. This new offering allows developers to pay a fixed fee
For us here at Replit, the month of May is all about mothers like Kelly. Kelly's son struggles with spelling, and the apps out there made him feel small. So she built Spell Strike on Replit, a mission
The Ettin Reranker Family represents a new suite of reranking models released on Hugging Face designed to improve retrieval-augmented generation (RAG) systems by reordering search results based on rel
This post recommends an essay by Swyx on creating luck, which likely explores how deliberate actions, visibility, and strategic thinking can increase one's chances of encountering beneficial opportuni
OlmoEarth v1.1 represents an updated release of Allen AI's open-source language models designed with improved efficiency compared to the original version. The update likely focuses on reduced computat
This post showcases experimental work with augmented reality (AR) libraries, likely demonstrating interactive AR effects or visualizations built using web-based tools. The project appears to be a play
Sneaky interventions, interactive installations, tools built for other artists to use. @kcimc's practice lives where machine learning, computer vision, and social technology collide. See his new inter
Today, we’re announcing Viktor’s 75M Series A, led by @Accel . @viktor__com was supposed to be a small experiment. It became the AI coworker 10x'ing real businesses. 15M in annualized revenue run rate
Voice 'cloning' is style transfer. Across three widely used systems — ElevenLabs V3, Coqui-XTTS, Chatterbox — clones don't just copy speakers, they reshape them to be warmer, more authoritative, more
This post links to a Call for Proposals (CFP) for volunteering opportunities at AI.Engineer, likely inviting community members to submit talk proposals, workshop ideas, or volunteer roles for an AI en
Replit announced it was selected for CNBC's Disruptor 50 list, recognizing the company as one of the most innovative private companies, marking the first time the coding platform achieved this honor a
A mother who builds is a mother worth celebrating. Sara is an Associate Professor of Nursing at Miami University, and a mother of two adult kids, one baby, a beagle, and a cat. She teaches pharmacolog
a prompt I've been using a lot recently: implement <SPEC> and while you do, keep a running implementation-notes.html file (or markdown) with decisions you had to make weren't in the spec, things you h
I cannot provide an accurate summary of this entry as the title appears to be truncated mid-sentence and lacks sufficient context. Based on the incomplete title, it likely discusses how software speci