Roblox Re Aura Codes
…You can compete with friends and keep improving your skills in various ways, and such skills can be improved with codes. Codes give you free rewards that help you level up faster…
Search
All sources
github.blog
40
phoronix.com
13
9to5google.com
6
huggingface.co
5
theverge.com
4
9to5mac.com
4
developer.nvidia.com
3
neowin.net
3
vg247.com
3
theregister.com
3
techpowerup.com
2
tomshardware.com
1
Videos
More videos
You Are Being Told Contradictory Things About AI
France moves to Linux, KDE gets more theme, more age verification stance & other Linux News
Ubuntu 26.04 LTS Review – Is It Worth the Upgrade?
It's finally time for Wi-Fi 7 - TP Link Deco 7 Pro
Claude Mythos: Highlights from 244-page Release
The Two Best AI Models/Enemies Just Got Released Simultaneously
GPT 5.5 Arrives, DeepSeek V4 Drops, and the Compute War Intensifies
Are Local Models Finally Good Enough?
Energy-Based Transformers are Scalable Learners and Thinkers (Paper Review)
HW News - Valve Improves VRAM Usage, NVIDIA N1 CPU Spotted, Data Center Tax Parasites, GPU Prices
I might have been wrong about Razer - Razer Viper V4 Pro
The Infplane Hilbert - WORTH $3000??? Let's Discuss...
Top stories
Anthropic launches Claude Opus 4.8 with better coding and lower fast mode pricing
4d agoClaude Opus 4.8 launches today with agentic improvements, new features
5d agoClaude Opus 4.7 was just released last month, and 4.8 is already here with some massive improvements
5d agoPaper page - SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
1w agoXcode 26.5 adds two features that make agentic coding more useful - 9to5Mac
…Two of these improvements make agentic coding workflows even smarter. Here are the details. Xcode 26.5 adds two useful Coding Intelligence features Apple released Xcode 26.5 yesterday, with two features…
Copilot code review: Comment experience improvements - GitHub Changelog
Copilot code review: Comment experience improvements - GitHub Changelog
CodeQL 2.25.3 adds Swift 6.3 support - GitHub Changelog
…We’ve recently released CodeQL 2.25.3 , which adds support for Swift 6.3, promotes five C/C++ queries to the default code scanning query suite, and includes various accuracy improvements…
Discussions and forums
Building self-improving tax agents with Codex
Building self-improving tax agents with Codex
2
Launch HN: Superset (YC P26) – IDE for the agents era
Hey HN, we’re Avi, Kiet, and Satya. We’re building Superset (https://github.com/superset-sh/superset), an open-source agentic IDE for running coding agents like Claude Code, Codex, OpenCode etc in parallel.Demo: https://…
105
133
Launch HN: Twill.ai (YC S25) – Delegate to cloud agents, get back PRs
Hey HN, we're Willy and Dan, co-founders of Twill.ai (https://twill.ai/). Twill runs coding CLIs like Claude Code and Codex in isolated cloud sandboxes. You hand it work through Slack, GitHub, Linear, our web app or CLI,…
77
95
Show HN: JDS – a Copilot skill suite for structuring AI coding behavior
A few months ago I stumbled on obra's superpowers repository https://github.com/obra/superpowers. I really liked the approach and idea that you enforce discipline for your agent through a skill-based workflow. Even thoug…
8
Tell HN: Claude Code now allows Anthropic to remotely inject system prompts
I often patch the system prompts on my Claude Code executable in order to make Claude more effective. Every time I upgrade, I ask Claude himself to dissect the new binary and look for problematic system prompts to modify…
11
7
Code Quality permissions removed from security manager role - GitHub Changelog
…May.12 Improvement CodeQL 2.25.4 adds Swift 6.3.1 support, improvements to C# and Java, and more application security May.08 Improvement CodeQL 2.25.3 adds Swift 6…
Paper page - An Empirical Study of Automating Agent Evaluation
…We further propose the Eval@1 metric to measure whether generated evaluation code both executes and yields meaningful results on the first run. Our experiments show that EvalAgent produces focused evaluations, improving…
Paper page - A Causal Language Modeling Detour Improves Encoder Continued Pretraining
Papers arxiv:2605.12438 A Causal Language Modeling Detour Improves Encoder Continued Pretraining Published on May 12 Submitted by Rian Touchent on May 13 ALMAnaCH (Inria) Authors: Rian Touchent , Abstract Switching from…
GitHub Code Quality: Batch apply quality suggestions on pull requests - GitHub Changelog
…May.12 Improvement CodeQL 2.25.4 adds Swift 6.3.1 support, improvements to C# and Java, and more application security May.08 Improvement CodeQL 2.25.3 adds Swift 6…
Microsoft just made it possible to use VS Code completely offline with local AI
…Finally, this update delivers an improved issue reporting flow. To help Microsoft understand and fix problems you run into in VS Code, it has decided to improve the issue reporting flow with…
Claude attacks were 'Rorschach test' for infosec community
…improve "exponentially." Last year, in an interview with The Register , Joyce said AI will "soon" be a great exploit coder. On Monday, he told an audience of security experts and coders it…