Search: “tools”

Most people run a security scan for malicious packages before publishing a project But the risk starts the moment they're installed Today we're launching Package Firewall, built in partnership with So

Package Firewall is now enabled by default for every builder on Replit as part of Replit Auto-Protect And its already stopping ~8,000 malicious installs per day on Replit Read more at: https://replit.

Swyx posted about recruiting singer-researchers to create a dramatic musical adaptation of the Muon/Shampoo debate, using the melody from 'Your Obedient Servant' (likely referencing the Hamilton music

arXiv:2606.11070v1 Announce Type: cross Abstract: Recent advances in reasoning and tool-calling capabilities of large language models (LLMs) have enabled increasingly capable agentic systems. However,

Vercel has enabled threshold billing for Pro teams, allowing users to set spending limits and receive alerts when approaching or exceeding their budget thresholds. This feature helps Pro plan customer

Together AI is ISO 27001:2022 certified. A-LIGN (ANAB-accredited) completed a multi-month audit of our ISMS: customer data protection, access controls, secure development, and incident response. Detai

We're closing out SHIP LDN with @rauchg and @HarryStebbings for an exclusive fireside chat on building, backing, and what's next. Sign up for your spot on the waitlist today: https://vercel.com/ship/l

This is likely a discussion of Alan Kay's seminal 1984 paper on computer software that emphasizes the importance of understanding and working with the materiality of computational systems rather than

Amazon Web Services Inc. today introduced an artificial intelligence tool designed to help organizations lower their cloud bills. AWS FinOps Agent is initially available in public preview. It’s the la

arXiv:2606.09315v1 Announce Type: cross Abstract: BCI-to-agent pipelines turn decoded neural activity into an authorization channel for tool-use agents, exposing a new attack surface we call brain-pro

Vercel introduced budget management features for API keys on its AI Gateway, allowing developers to set spending limits and monitor costs for API key usage. This feature helps prevent unexpected charg

This paper benchmarks frontier automatic speech recognition (ASR) systems on their ability to handle code-switched speech, where bilingual speakers mix languages within a single conversation. The rese

arXiv:2606.09751v1 Announce Type: new Abstract: Foundation models are moving from response generation into operational roles. They plan across steps, call tools, request human input, coordinate with o

@DeepCogito needed sub-500ms time to first token at 1,000+ requests per minute for their frontier reasoning models. Together AI delivered. Hear from the Deep Cogito team on what it takes to build fron

Vercel has added domain search functionality to its command-line interface (CLI), allowing developers to search for and potentially register domains directly from the terminal. This feature integrates

Pinecone has introduced an open-source monitoring stack designed to provide full observability for its vector database service, supporting both SaaS and Bring Your Own Cloud (BYOC) deployment models.

A developer used Replit's parallel agents feature to simultaneously create multiple deliverables for a travel app startup: a functional mobile application, promotional video, and investor pitch deck.

A developer created a Windows GUI tool for managing and benchmarking different llama.cpp builds, addressing the needs of AMD GPU users who work with multiple compute backends like Vulkan, ROCm, and HI

I've had access to Fable for a bit. A genuine jump in capability, I could feed it a 15 page design document for a project and it would work for 9+ hours and deliver terrific results. But working with

arXiv:2606.08676v1 Announce Type: cross Abstract: AI coding assistants have significantly improved developer productivity by automatically suggesting code that aligns with user intent, and many of the

This article explains how to migrate continuous integration workflows from GitHub Actions to Hugging Face Jobs, likely covering the setup process, configuration differences, and benefits of using Hugg

more charts of other tiers where its less stark including the vibe shift chart from https://x.com/swyx/status/2064081945567580323 here It's finally out!!! @METR_Evals found that more than half of SWEB

Mythos is live! so excited to have our FrontierCode recognized as the next frontier coding bench. on FC Diamond, BOTH Opus 4.8 and GPT 5.5 don't meaningfully scale with effort, which many of you caugh

The Billion Pound Build is a Perplexity-hosted initiative inviting users to submit project pitches, likely focused on generating innovative ideas or solutions. This appears to be a community engagemen

arXiv:2501.06659v2 Announce Type: replace-cross Abstract: Many templatized documents are programmatically generated from structured data following a visual template. Such documents include invoices, t

arXiv:2606.07723v1 Announce Type: new Abstract: Open-vocabulary long-horizon manipulation requires robots to reason over flexible instructions and complex multi-object scenes while adaptively planning

Anthropic has reset rate limits for Claude API users, increasing both the 5-hour and weekly usage caps to allow greater access. This change was announced to coincide with the release of Fable 5, sugge

Yesterday at London Tech Week we announced the Billion Pound Build competition. Teams can enter to secure a share of £1M in Computer credits by using Perplexity Computer to build their company. The pi

1,500 teams entered the Billion Dollar Build and have been building for 7 weeks. 8 finalists present live on June 9 to our judges @LewisHamilton (7x World Champion Driver), @AravSrinivas (CEO, Perplex

OpenAI is preparing its biggest ChatGPT overhaul yet, aiming to transform it into a superapp that combines AI agents, coding tools, and third-party services. The change affects all 900 million weekly

Microsoft's durabletask PyPI package was poisoned in May 2026 with credential-harvesting malware that steals secrets from AWS, Azure, GCP, Kubernetes, and 90+ developer tools . In June, 73 Microsoft r

Phoenix crossed 10,000 GitHub stars. Here is how the open-source AI observability project grew from a Jupyter notebook extension into a community-shaped platform for traces, evals, OpenInference, and

arXiv:2606.06545v1 Announce Type: cross Abstract: Enterprise agent systems increasingly need to connect large language models to private tools, internal knowledge, and Model Context Protocol (MCP) int

arXiv:2606.07074v1 Announce Type: cross Abstract: Deep research agents have demonstrated remarkable capabilities in complex information-seeking tasks, yet this power comes at a steep computational cos

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

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

A really good read by @GergelyOrosz: https://newsletter.pragmaticengineer.com/p/ideas-slow-down-to-speed-up-when This situation of engineers who care about quality being underserved must change, and i

Amazing Digital Dentures was a hackathon project showcased on Hugging Face that attempted to apply AI or digital technology to denture design or manufacturing but ultimately did not reach completion o

idea - universal basic ai: 1 share of xai, oai, and ant to each US citizen. cost SpaceXai: 135.00 × 349 million = 47B OpenAI: 733.54 × 349 million = 256B Anthropic: 930.45 × 349 million = 325B total 6

one popular theory is that research paper alpha* and lab publishing ~died when researchers realized that instead of fighting with marketing depts they could simply walk out the door and get >$100m for

OpenAI is planning its biggest ChatGPT overhaul yet, aiming to turn it into a 'superapp' with coding tools and AI agents to boost revenue ahead of a potential stock market listing. The redesigned Chat

releasing tmr - the biggest code eval launch of the year glad to have played a small part in defining the agenda for this very critical next phase in koding lol heard a 2nd startup today that has made

This resource describes sponsor vouchers, particularly OpenAI Codex credits, available to participants in a Hugging Face hackathon event. It likely outlines how participants can access and use the pro

a smarter alternative to 'always use plan mode': always frame your task as a question, so that the model is invited to push back and rate the quality of the idea/suggest alternatives, rather than blin

arXiv:2606.05670v1 Announce Type: new Abstract: Does adding more agents help an LLM workflow once compared systems share the same benchmark loader, tool access, answer contract, usage accounting, and

I may have finally found the Python-in-a-sandbox solution I've been looking for... here's my latest experiment, this time running MicroPython in WebAssembly inside my Python applications https://simon