Show HN: Reteach – AI tutor that feels human (reteach.study)
1 pointsby 1 minute ago
—discuss
Google plans first test ofAl chips in space under Project Suncatcher (blog.google)
1 pointsby 5 minutes ago
—discuss
London's schools are running out of children (ft.com)
1 pointsby 5 minutes ago
—discuss
Just how hot and dry was your summer? – UK postcode lookup (bbc.co.uk)
1 pointsby 6 minutes ago
—discuss
AMBA – Free and Open Advanced Microcontroller Bus Architecture (arm.com)
1 pointsby 7 minutes ago
1comments
About Those Property Taxes (pxlnv.com)
1 pointsby 12 minutes ago
—discuss
Show HN: Lift and Coast (Browser based F1 game) (lift-and-coast.vercel.app)
1 pointsby 13 minutes ago
—discuss
Recipe for Disaster v1.0
1 pointsby 15 minutes ago
1comments
Show HN: Jevper – an LLM API client constrained to the Jev wire format (github.com/zhulinchng)
1 pointsby 16 minutes ago
—discuss
Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models (arxiv.org)
1 pointsby 17 minutes ago
—discuss
Control-Token Injection Suppresses Chain-of-Thought and Defeats Reasoning-Based (arxiv.org)
1 pointsby 20 minutes ago
—discuss
Show HN: A single-use authorization boundary in Rust
1 pointsby 22 minutes ago
—discuss
Peter Thiel slams pope's AI encyclical as gift to Chinese Communist Party (politico.com)
2 pointsby 23 minutes ago
1comments
Oldest recorded voices, haunted dolls, and more from Tempest Instruments (cdm.link)
2 pointsby 30 minutes ago
—discuss
I stopped letting LLMs do arithmetic (medium.com/jwbobbink)
4 pointsby 34 minutes ago
—discuss
Tell HN: No company scaled revenue as fast as AI companies
2 pointsby 36 minutes ago
1comments
700 MB/s of Kafka throughput, on Postgres (rynr.dev)
3 pointsby 37 minutes ago
—discuss
AI Agents are breaking into Online Retailers for $25 a target (gambit.security)
4 pointsby 42 minutes ago
—discuss
Taste Bench (omneky.com)
6 pointsby 42 minutes ago
—discuss
Show HN: Knowledge Signal – A JEV-powered rubric assessment tool for study notes (github.com/sumant1122)
2 pointsby 44 minutes ago
—discuss
You sent the wrong attachment and leaked the banks deal list. What happens next? (ft.com)
3 pointsby 47 minutes ago
—discuss
Developer Process Automation: The sane way to automate developer hours (12gramsofcarbon.com)
2 pointsby 49 minutes ago
—discuss
Show HN: Miru: Zoomer Daemon for Wayland (is-a.dev)
2 pointsby 50 minutes ago
—discuss
When Agent Met Agent (flybridge.com)
2 pointsby 51 minutes ago
—discuss
New RSA attack forges signatures without factoring the key (arstechnica.com)
3 pointsby 52 minutes ago
—discuss
Pressures building up in yen carry trade (wsws.org)
1 pointsby 52 minutes ago
—discuss
TileRT Takes the Top Spot on AgentX with AMD Instinct MI355X GPUs (tilert.ai)
2 pointsby 56 minutes ago
—discuss
Show HN: SelMem – selective reconstructive memory for LLMs (github.com/jbsalles)
1 pointsby 59 minutes ago
—discuss
Show HN: A benchmark comparison of C++ vs. Node.js performance (vikky2810.github.io)
1 pointsby 1 hour ago
—discuss
Tracking Singularity – A Curated Log of Important Events in AI Since Mid 2026 (trackingsingularity.com)
2 pointsby 1 hour ago
—discuss

Jev Based Code Review

4 pointsby 1h agogithub.com

Most PRs that are generated by agents today get YOLO merged because its hard for human mind to comprehend when your agent just suddenly shows up with 230 file changes. This is an attempt to reduce the mental burden by classifying each change in a review to P0, P1, P2. Only P0 are shown by default. The priorities are configurable. The diffs are also show using a natural language. The original code is one toggle away.

1h agoHN ↗

Nice idea. This could make large agent-generated PRs much easier to review.

Open thread on HN ↗