Stories
30
Sources
11
Topics
10
For You lens
28 stories in this edition match your reader profile.
Reader signals
3
Searches
0
Matches
28
Top score
143
Search Intent
developer_tool
This query becomes a recent For You signal, so matching stories can move up on the next personalized pass.
Edition Index
Topic, entity, and source map
Topics
Lead Story
OpenHands/OpenHands is trending in AI open source
OpenHands/OpenHands is a GitHub AI repository with 87,790 stars. 🙌 OpenHands: AI-Driven Development
GitHub Trending AI / 10:54 PM
marimo-team/marimo is trending in AI open source
marimo-team/marimo is a GitHub AI repository with 22,748 stars. A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
Hacker News AI / 9:11 PM
SCH: An affordable sandbox for Coding Agents in your AWS account
HN 5 pts · 1 comments
Latent Space / 5:56 AM
[AINews] DeepSeek v4.1-Flash: 763B-P8B-D16B novel causal Encoder–Decoder architecture with vision marks the Return of the Whale
We agree with Sebastian: this should have been DeepSeek v5
Simon Willison LLMs / 5:47 PM
Quoting Boris Cherny
Production code written by Claude should have a higher bar than if it was written by a human. At Anthropic, we have many guardrails in place to make sure this is happening: lots of lint rules, lots of tests, Claude-driven end to end tests, Claude-powered fuzzers running daily, automated code reviews and security reviews, automated code refactoring, and so on. Without these, you can end up with a mess that is hard to maintain down the line. — Boris Cherny Tags: claude , ai , claude-code , llms , coding-agents , ai-assisted-programming , generative-ai , agentic-engineering , boris-cherny , anthropic
Product Hunt AI / 10:45 PM
Devin Voice
You say it, Devin ships it Discussion | Link
GitHub Trending AI / 9:42 AM
thedotmack/claude-mem is trending in AI open source
thedotmack/claude-mem is a GitHub AI repository with 93,809 stars. Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Hacker News AI / 9:21 AM
My Journey Towards Coding Agents: Building Sera
HN 1 pts · 0 comments
Hacker News AI / 8:20 AM
Show HN: Run coding agents on your own machine, steer them from anywhere
HN 2 pts · 0 comments
GitHub Trending AI / 6:41 AM
yamadashy/repomix is trending in AI open source
yamadashy/repomix is a GitHub AI repository with 28,329 stars. 📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.
Hacker News AI / 5:50 AM
Show HN: Weftgate, a local verification gate for coding agents
HN 1 pts · 0 comments
Product Hunt AI / 10:19 PM
Cognition's SWE-2
Cognition's coding model, 64% cheaper than Fable 5.1 Discussion | Link
AWS Machine Learning Blog / 9:58 PM
Reduce LLM latency with prefix-aware routing on Amazon SageMaker Inference
Amazon SageMaker Inference now offers prefix-aware routing, a routing strategy that sends requests sharing the same prompt prefix to the same instance so the KV cache stays warm. In benchmarks on Llama 3.1 70B, it reduced P50 time-to-first-token by up to 77% and raised KV cache hit rates from about 25% to over 80%.
The Verge AI / 7:44 PM
Schools are catching on to Big Tech’s playbook
It's the hot new thing in tech, and it's where all the jobs are. Students who don't learn to use it fall behind. And to help them catch up in time, its creators are graciously providing the resources and curriculum for learning it, often pro bono. That's the narrative AI companies are pitching schools on […]
AWS Machine Learning Blog / 3:53 PM
How AvioBook builds turnaround insights from operational data with Amazon Bedrock AgentCore
AvioBook, a Thales Group Company, prototyped Connected Analytics on Amazon Bedrock AgentCore to turn AvioBook Connect's operational data into plain-language, evidence-based answers for airline managers and dispatchers, helping them find and act on the causes of flight turnaround delays.
YC AI / 3:35 AM
Mirrors launched from YC as an AI company
Mirrors is a Fall 2026 YC AI company: Catch and fix AI agent regressions before they reach production.
Latent Space / 3:33 AM
[AINews] not much happened today
a quiet day
YC AI / 8:06 PM
ByteAsk launched from YC as an AI company
ByteAsk is a Fall 2026 YC AI company: The AI coding agent for C and C++.
arXiv AI/ML / 5:59 PM
arXiv paper: IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications
A new arXiv AI paper by Yiling Ma, Yilun Zhao, and Sihong Wu, and 2 more studies IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications.
Ars Technica AI / 4:34 PM
Google's AI genome system evaluates every possible one-base change
Most one-base changes to the human genome do nothing, but a few are significant.
arXiv AI/ML / 5:54 PM
arXiv paper: Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation
A new arXiv AI paper by Jiacheng Xu, Feng Chen, and Xiuneng Xu, and 1 more studies Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation.
Hacker News AI / 1:20 AM
A.I. Slopware Is Everywhere Now. Nobody Is Using It
HN 6 pts · 0 comments
Hacker News AI / 11:45 PM
AgentsDock: An IDE designed for agentic AI research
HN 44 pts · 16 comments
Simon Willison LLMs / 3:27 AM
Datasette 1.0a39 and 0.65.4 security releases
Datasette 1.0a39 and 0.65.4 security releases Today we're releasing two new security patch versions of Datasette: 1.0a39 and 0.65.4 - one for the current alpha series and one for the stable 0.65.x family. These are security fixes which you should apply if you are running a Datasette instance on the public web - in particular if that instance mixes both public and private tables. Following issues reported by Sevban Dönmez , Alex Garcia and I ran an extensive audit of Datasette using Claude Fable 5.1, GPT-5.6, and GPT-6 Astra. We then spent almost a week collaborating on and reviewing the fixes. They helped find some very subtle bugs. We'll be incorporating security audits by frontier models into all of our development work going forward. Alex came up with a way of splitting the work which I found extremely productive: Alex Garcia and I worked together running and then responding to the audit, working in a shared private repository. For most of the issues we split the work: one of us would create the automated tests highlighting the issue, then the other would implement the fix. This ensured that two separate humans had eyes on each of the issues, in addition to our coding agents running different models. Tags: releases , security , ai , datasette , generative-ai , llms , agentic-engineering , ai-security-research
AWS Machine Learning Blog / 10:26 PM
Deploying Qwen3.8-2.4T-A95B on Amazon SageMaker HyperPod with vLLM
Learn how to deploy Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter open-weight model, on Amazon SageMaker HyperPod with vLLM. This walkthrough covers cluster provisioning, NVFP4 quantization, and an OpenAI-compatible endpoint with built-in reasoning, tool calling, and native MTP speculative decoding.
YC AI / 3:20 PM
Frontrunner launched from YC as an AI company
Frontrunner is a Fall 2026 YC AI company: Cursor for GTM.
Hacker News AI / 3:19 PM
Google: Attackers are using prompt injection against coding agents
HN 6 pts · 0 comments
Hacker News AI / 4:20 AM
Show HN: Grok CLI – Grok-native agentic coding harness
HN 4 pts · 0 comments
Latest story in this edition: 1:33 AM
Back to front page