Ideas for building
better software.

How NVIDIA scales expertise with ChatGPT Work

NVIDIA teams use ChatGPT Work to reduce manual tasks, connect fast-moving signals, and scale successful workflows globally.

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

Cloudflare Tunnel, Cloudflare Tunnel for SASE - Configure origin application settings for Cloudflare Tunnel in the dashboard

You can now configure origin application settings directly in the Cloudflare dashboard when adding or editing a published application route for a Cloudflare Tunnel. These settings control how cloudflared connects to your origin server and were previously only available in the Cloudflare One dashboard or via local configuration files. When editing a published application, expand Additional application settings to configure parameters organized into three categories: HTTP — Set a custom HTTP Host

This Week in Spring - August 18th, 2026

Poisoned Postgres connection pools

Did you know you can poison your Postgres connection pool? Most people have no idea what this means, but it could take down your entire database if you're not careful managing your connection pooler. An engineer's worst nightmare is waking up to a seemingly read-only database with no clear issue in sight. Unfortunately, this is exactly what one of our discord friends ran into on a Tuesday evening. Note Join our Discord community and catch debugging sessions like this live: discord.gg/planetsc

Cline is now available in the AI SDK harness layer

The lets you run established coding-agent runtimes through one unified interface, so you can switch runtimes without changing your application code. Today we are adding Cline, which runs through the same interface as other supported harness.AI SDK harness layerHarnessAgent is the official harness adapter for Cline, implemented in collaboration with the Cline team.@ai-sdk/harness-cline Cline runs fully in the host process and uses the sandbox as a remote filesystem and shell, so only its tools

GLM 5.3 now available on AI Gateway

is now available on AI Gateway.GLM 5.3 from Z.ai GLM 5.3 has improvements vs. GLM 5.2 at complex software engineering and at agent tasks that run across many steps, and it reaches those results while producing fewer output tokens than GLM 5.2 did at the same effort level. Z.ai also reports stronger vulnerability discovery, including reasoning across the successive stages of an exploitation chain. measures that work directly, scoring how reliably a model finds security vulnerabilities in applica

Sign JWTs from your Functions without managing private keys

Vercel KMS lets you sign JWTs and arbitrary messages from your Vercel Functions using managed asymmetric signing keys, so private keys never live in your code or environment variables. Your function authenticates with its token, and the private key stays inside Vercel's key management service while verifiers use only the public key.Vercel OIDC With Vercel KMS you can: Sign a token inside a function: Verify a token anywhere with a standard JOSE library, using the issuer's public JWKS: Set up an