Replit

Replit switches default AI model from Anthropic to OpenAI

Replit has replaced Anthropic's Claude with OpenAI as its default AI model, though Claude remains available on the platform. This change was confirmed by Replit's CEO.

Why it matters: The shift indicates a strategic preference for OpenAI's models in consumer AI applications, potentially influencing developer and user experiences on Replit. It also reflects ongoing competition among AI providers for platform dominance.

Replit CEO Envisions 'Self-Driving Companies' Powered by AI Agents

Replit CEO Amjad Masad predicts a future where AI agents manage routine tasks within companies, allowing humans to concentrate on strategic decisions. This concept is described as the rise of 'self-driving companies.'

Why it matters: This shift could transform workplace dynamics by automating operational work, potentially increasing efficiency and changing the role of human workers. Understanding this trend is key for businesses preparing for AI-driven organizational changes.

Replit Agent lets LLMs dynamically allocate effort and subagents

Replit Agent improves on traditional model routers by allowing the main model to dynamically select its subagents' tier and effort during a task. This approach enables the core model to adjust its own effort as the task unfolds, potentially surpassing static routing methods.

Why it matters: Traditional model routers are limited by always being less capable than the models they choose from, but Replit Agent's design lets the model itself manage resource allocation for better performance. This could enhance efficiency and effectiveness in multi-agent LLM systems.

Replit offers black-box pen tests to speed secure app launches

Replit now provides black-box penetration tests that allow developers to identify security flaws before launch without costly external vendors. This service helps build and deploy apps with real customer data within a day.

Why it matters: Penetration tests are essential for securing applications against cyberattacks, but traditionally they have been expensive and time-consuming. Replit's approach democratizes security reviews, enabling faster and more affordable app development.

Replit is now available in Claude

Replit is now available directly inside Claude, making it easier than ever to go from a conversation to a fully built, shipped product - without losing context, in one seamless workflow. Design in Claude, Build in Replit You can now design on-brand, beautiful...

Customize Replit Agent with Skills & Custom Instructions

Every team has conventions. How you structure a project. How you handle secrets. Your design system, your testing standards, your code style. The problem: AI Agents don’t know your conventions. So you explain it again on every prompt, paste in your standards...

Package Firewall: Blocking 8,000+ malicious packages daily

Replit already scans your projects for vulnerable dependencies, and audits your dependencies before you publish. But risk shows up earlier than that, while you are developing, the moment a malicious package gets installed. Today we're launching Package Firewa...

How Replit makes sense of code at scale

For any company making creative tools, being able to tell what its most engaged users are building on the platform is critical. When the bound of what’s possible to create is effectively limitless, like with code, sophisticated data is needed to answer this d...

Sep 29 Incident Update: Read-Only Repls

On Sep 29, we had a period of about 2.5h from 14:00 to 16:30 (Pacific Time), in which an incomplete build was pushed to our infrastructure that handles storing Repl data. This caused Repls opened during that time window to become read-only or stop working. An...