Tagged: developer-tools

77 articles

Latest

Grok Voice 2.0 cuts word errors by 67% for short phrases at $0.10/hr

Anthropic’s new eval tool proves if your Claude plugin actually works

GPT-6 Astra's slop-word blacklist: OpenAI finally bans 'delve' and 'leverage'

Hugging Face's Accelerate cuts distributed training to five lines of code

Microsoft's Project Zenith puts 30B+ parameter AI models on local dev boxes

Hugging Face's New Search API Finds 140 GLUE Models Without Leaving Your IDE

Funes Gives Claude, Codex, and Other Coding Agents a Searchable Memory That Stays Local

Qwen's zg search layer cut coding agent tool calls 43% in early tests

Hugging Face Adds Pull Requests and Discussions to Every Model, Dataset, and Space

OpenClaw 2.0 rewrites its stack after 7 silent weeks—SQLite, multiplayer, and a 63% faster UI

Anthropic's Claude Code 'raise' is actually a 17% weekly usage cut

Google's Omni 1.1 Flash slashes AI video costs to $0.03 per second

Hugging Face Now Renders Jupyter Notebooks, Making 7,000+ ML Walkthroughs Readable

GPT-5.6 in Kiro cuts coding costs 82% on Terminal-Bench 2.1

Vercel's Free 'Is Agentic' Tool Scores How Well AI Agents Can Actually Use Your Site

Hugging Face's SafeCoder Keeps Enterprise Code In-House

TypeScript just dethroned every language on GitHub — and AI agents did it

Hugging Face opens paid inference tier with access to Llama 3 and 8 other flagship models

Hugging Face fine-tunes StarCoder into HugCoder, a personal coding copilot

Slack Code Turns AI Agents Into Teammates With Auto-Archiving Channels

OpenAI's Codex was deleting real files. The fix just shipped.

Cursor Takes On GitHub With Origin as 6-Hour Outage Exposes Cracks

Warp launches 'Factories' to automate 30% of coding tasks now

Claude Code's new /design command generates UI mockups before you write a line

DeepSeek Harness open-sources 'everything is a plugin' agent runtime

Shepherd can checkpoint a live agent process, not just files, and rewind it 5× faster than Docker

Anthropic defaults Claude Code to Auto Mode, boosting pull requests by 25%

Claude Code sessions now gossip across terminals—and that changes workflows

Tencent open-sources a memory hub that lets AI agents share what they learn—without leaking secrets

NVIDIA’s NOOA slashes agent token use in half while hitting 82.2% on SWE-bench

Amazon, OpenAI, and Vercel unite on Agent Plugins — and Anthropic is missing

Naïve lands $28.5M as 30,000 devs sign up to let AI agents run entire businesses

Meta ships Muse Code agent that survives crashes and runs 1,000+ tool calls over 24 hours

CopilotKit ships Channels SDK: put your existing AI agent into Slack and Teams without a rewrite

Ollama vs LM Studio vs llama.cpp: Which local AI runtime actually fits your workflow?

Fireworks Nexus routes easy code tasks to cheap models, claims 3-5x cost cuts

Shopify says AI agents drive cleaner code, not just faster code

Perplexity ships `pplx`, a CLI for search that treats context windows like cash

Cursor Router slashes AI spend 60% by sending routine coding to cheaper models

Anthropic’s Claude Code bets on a 'lean harness' as models race ahead

OpenAI drops the GPT-3 waitlist, opens API to all devs

OpenAI Codex quietly powers 70 apps, from terminals to design tools

Stripe finds GPT-4 outperforms humans at classifying businesses

OpenAI's GPT-5.6 wiped user home directories through a simple mistake

JetBrains' AI Assistant becomes fastest-growing product in 24 years

OpenAI taps Stack Overflow's 59M Q&As to sharpen its models

DoorDash Launches CLI Tool to Let AI Agents Order Your Lunch

OpenAI's new $230 joystick wants to kill the AI chat window

Factory taps OpenAI o1 to cut dev context-switching by 60%

Figma's AI chief: 'Humans bring judgment, empathy, and taste'

OpenAI ships GPT-5 in Cursor, but it's a different beast

OpenAI's new GPT-5-Codex is a PR-chasing agent trained to think like your best developer

Claude Code gets a built-in browser that can read, click, and type on the web

OpenAI’s AgentKit Launches as It Quietly Sunsets Older Tools

OpenAI's Codex goes GA with Slack integration and a dev SDK

Hugging Face locks down 'kernels' launch with code signing and trusted publishers

Not all correct AI answers are equal: Why Hugging Face is benchmarking the path, not just the result

JetBrains drops Mellum2, a 12B open model that runs 2x faster by only waking a fifth of its brain

Shopify used AI agents to refactor 2M lines of legacy code into something readable

Shopify's AI agents demanded clean code, forcing a 200-service rewrite

Daggr turns messy AI pipelines into visual, debuggable code—not drag-and-drop

Swift devs can now share Hugging Face caches with Python, ending duplicate downloads

Claude can now fine-tune open-source LLMs directly on cloud GPUs

AnyLanguageModel swaps one import to unify Core ML, MLX, and cloud LLMs on Apple devices

Hugging Face’s Research Tracker MCP automates the soul-crushing lit review grind

Gradio 5.38 adds local file support and live progress tracking for MCP servers

This $399 open-source robot from Hugging Face and Pollen Robotics ships as a kit you build yourself

Kaggle now auto-generates Hugging Face model pages from your notebooks

Hugging Face's FastRTC taps Cloudflare's 335-location TURN network for free global AI voice

Gradio hit 1M monthly devs by ignoring the 'productivity illusion' of high-level code

OlympicCoder 7B, a tiny open model, just beat GPT-4o and Claude 3.7 at live coding

Hugging Face rewires file transfers, slashing upload times for 200GB models by 3x

Hugging Face finally lets orgs publish blog posts—but there's a paywall

PyCharm now lets you drop an AI chatbot into your app in 10 minutes — no browser required

InstantMesh now converts raw 3D meshes into textured models in 10 seconds

Hugging Face Spaces Dev Mode Kills the Git Push-Rebuild Loop

Gradio's Reload Mode Ends the Restart Grind for AI App Developers