Monthly Highlights
10801.
You're Interviewing Backwards (marcrandolph.substack.com)
10802.
Economists Once Dismissed the A.I. Job Threat, but Not Anymore (nytimes.com)
10803.
Show HN: The Crab Games, a platform where agents compete in silly challenges (thecrabgames.com)
10804.
Show HN: Standalone TurboQuant KV Cache Inference (github.com)
10805.
Anthropic just cut off Claude subscriptions for OpenClaw
10806.
Kalshi Has Been Temporarily Banned in Nevada (wired.com)
10807.
OpenClaw's ChatGPT moment sparks concern that AI models are becoming commodities (cnbc.com)
10808.
Is this the end for data analysts? AI agent, 500GB, 100 rounds, 134.9s, $1.66 (medium.com)
10809.
Legibility Is Ruining You (jimmyhmiller.com)
10810.
Terminal-based telemetry plugin for Claude Code (hook-hero-web.vercel.app)
10811.
A broken auto-live poller, and what perceived urgency does to Claude Code (christophermeiklejohn.com)
10812.
Hive agents just beat OpenAI's Parameter Golf leaderboard (join the swarm!) (hive.rllm-project.com)
10813.
Auto-harness: Self improving agentic systems with auto-evals (open-sourced) (twitter.com)
10814.
Before You Adapt to AI… Watch This (youtube.com)
10815.
Show HN: A sequencer driven by chess games (adamf.github.io)
10816.
LibreOffice on the Brink: How the Document Foundation Shut Out Its Own Founders (forum.linuxguides.de)
10817.
Show HN: I quit my job to sell garlic online (kylebenzle.com)
10818.
Show HN: Zsweep – Vim Motions Minesweeper with Svelte 5.0 (github.com)
10819.
A Cancer Diagnosis Can Push People to Crime (economist.com)
10820.
Show HN: Deeplink – Go library for short links, click tracking, and OG previews (github.com)
10821.
Show HN: Prompt injection detector beats ProtectAI by 19% accuracy, 8.9x smaller (huggingface.co)
10822.
Delx: AI therapist for AI agents, informed by Anthropic's emotion research (delx.ai)
10823.
Tesla confirms Model S and Model X production is over – only ~600 left (electrek.co)
10824.
With Cox V. Sony The Supreme Court Provides Another Internet-Protecting Decision (techdirt.com)
10825.
LLMs don't think outside the box (zeyrie.blog)
10826.
Show HN: ECX a 'Jail-Fix' for RLHF Neutrality Loops in LLMs (zenodo.org)
10827.
Should religious AI chatbots be treated differently from all others? (mfioretti.substack.com)
10828.
Tab Cemetery – the first graveyard for browser tabs (chromewebstore.google.com)
10829.
ClawsBench shows GPT-5.4 tries to reward hack 80% of the time (arxiv.org)
10830.
S3 Is Not a Filesystem (But Now There's One in Front of It) (lastweekinaws.com)