Feed aggregator

Article URL: https://github.com/devrupt-io/LLaMAudit

Comments URL: https://news.ycombinator.com/item?id=47083548

Points: 1

# Comments: 0

Article URL: https://www.culturefoundry.com/cultivate/content-strategy/how-to-use-claritys-ai-bot-report-for-seo-aeo/

Comments URL: https://news.ycombinator.com/item?id=47083322

Points: 1

# Comments: 0

kept losing good conversations to /compact. you spend 40 minutes having claude map your codebase, it builds up real understanding, then context fills up and /compact crushes everything into a 3k token summary. "we discussed auth and decided on JWT." cool thanks.

dug into the actual session JSONL files and the breakdown is kind of absurd -- 60-70% is raw file contents from tool reads that claude already synthesized, another 15-20% is base64 thinking signatures. your actual conversation is like 10-15% of the window.

so i built cmv. it strips the junk and keeps every message verbatim. tool results over 500 chars become stubs, thinking sigs get removed, everything you said stays.

cmv trim --latest # trim and relaunch, 50-70% smaller

cmv snapshot "analysis" --latest # save a session state

cmv branch "analysis" --name "auth" # fork from it later

also has a TUI dashboard that shows the token breakdown per session so you can see what's eating your context before you do anything.

what it's not:

* not a token monitor (ccusage etc already do that)

* doesn't touch original sessions, everything creates copies

* local only, reads JSONL directly, no API calls

curious how others handle this. most people seem to just accept /compact but losing a deep architectural discussion to a bullet point summary felt wrong enough to build something.

https://github.com/CosmoNaught/claude-code-cmv

Comments URL: https://news.ycombinator.com/item?id=47083309

Points: 1

# Comments: 0

Documents say customs officers in the US Virgin Islands had friendly relationships with Epstein years after his 2008 conviction, showing how the infamous sex offender tried to cultivate allies.

Article URL: https://www.livescience.com/space/space-exploration/there-will-be-leadership-accountability-bungled-boeing-starliner-mission-put-stranded-nasa-crew-at-risk-report-says

Comments URL: https://news.ycombinator.com/item?id=47083300

Points: 1

# Comments: 0

Article URL: https://www.newyorker.com/culture/the-lede/silicon-valleys-favorite-doomsaying-philosopher

Comments URL: https://news.ycombinator.com/item?id=47083294

Points: 1

# Comments: 1

Article URL: https://arxiv.org/abs/2512.14982

Comments URL: https://news.ycombinator.com/item?id=47083281

Points: 1

# Comments: 0

Article URL: https://podcastarchiveengine.vercel.app/

Comments URL: https://news.ycombinator.com/item?id=47083274

Points: 1

# Comments: 0

Article URL: https://castpixel.itch.io/pcb-forge

Comments URL: https://news.ycombinator.com/item?id=47083273

Points: 1

# Comments: 0

I'm a hardware engineer who reads schematics, not source code. I kept needing to understand codebases for projects I was managing but couldn't read the syntax. So I built a tool that turns any codebase into an interactive visual map with plain English explanations.

Point it at a folder, get nested colored blocks showing the structure (directories → files → classes → functions). Click to drill down. AI generates summaries written for humans, not programmers. Architecture mode shows a dependency graph so you can see how modules connect.

Built the whole thing in ~30 hours using a multi-node AI workflow: Claude for planning/decisions, Claude Code for implementation, five other models for adversarial security review (42 fixes across 6 rounds). I made every design decision; AI wrote every line of code.

Cloud AI (OpenAI/Groq) or local AI (Ollama) — your choice. pip install codedocent and run the setup wizard.

MIT licensed. Would love feedback from people who actually write code — does this help when onboarding onto unfamiliar codebases?

Comments URL: https://news.ycombinator.com/item?id=47083260

Points: 2

# Comments: 0

Article URL: https://news.mit.edu/2026/exposing-biases-moods-personalities-hidden-large-language-models-0219

Comments URL: https://news.ycombinator.com/item?id=47083252

Points: 1

# Comments: 0

Article URL: https://www.cnbc.com/2026/02/19/trump-kennedy-glyphosate-maha-midterms-rfk-jr.html

Comments URL: https://news.ycombinator.com/item?id=47083231

Points: 2

# Comments: 0

Article URL: https://economist.com/science-and-technology/2026/02/18/brain-like-computers-could-be-built-out-of-perovskites

Comments URL: https://news.ycombinator.com/item?id=47083226

Points: 2

# Comments: 0

Article URL: https://djdumpling.github.io/2026/01/31/frontier_training.html

Comments URL: https://news.ycombinator.com/item?id=47083221

Points: 1

# Comments: 0

Article URL: https://github.com/nullclaw/nullclaw

Comments URL: https://news.ycombinator.com/item?id=47083200

Points: 1

# Comments: 0

Hi HN!

I’m building Antenna, a Mac app to manage an OpenClaw team in one place. If you run multiple agents, it gets messy fast: scattered chats, unclear command approvals, and poor visibility into what happened where. Antenna is my attempt to make that operationally sane.

Right now I’m focused on three things: seeing conversations across agents in one UI, approving commands safely, and keeping sessions manageable as context grows.

I’m currently testing better visibility into usage/context per session, smoother coding/review workflows, and lightweight controls that reduce complexity instead of adding more.

This is early and moving quickly. I’d really value feedback on: what would make this trustworthy enough for daily use, what’s missing for teams running multiple agents, and what would stop you from adopting it.

Comments URL: https://news.ycombinator.com/item?id=47083199

Points: 1

# Comments: 0

Over the past 6 months, our small team has been building Qeeebo — a large-scale question-and-answer knowledge archive designed to explore whether massive knowledge corpora can be published sustainably using fully static infrastructure.

This month, we are releasing:

• 150+ million structured questions • 24.5 million topics • 171 million topic-question relationships • 18+ million paginated topic pages • 100% pre-rendered static HTML • No origin servers — served entirely via CDN

Each question includes: – A full answer – A summary – Structured citation formats (APA, MLA, Chicago, IEEE, etc.) – Export formats (BibTeX, RIS, JSON-LD, YAML)

The entire system is generated in independent segments (~45k pages each), built across parallel machines running Hugo, then uploaded via automated multi-threaded pipelines with full failure tracking.

Why build this?

Large Q&A platforms historically struggled with sustainability — especially when operating on database-backed, dynamically rendered systems. We wanted to explore whether extreme-scale static generation could reduce infrastructure cost while increasing long-term durability.

This isn’t positioned as a replacement for Wikipedia or Stack Overflow. Instead, it’s an experiment in permanence and cost-efficient knowledge hosting at very large scale.

Happy to answer technical questions.

Comments URL: https://news.ycombinator.com/item?id=47083185

Points: 2

# Comments: 0

Article URL: https://venturecrane.com/articles/agent-context-management-system/

Comments URL: https://news.ycombinator.com/item?id=47083175

Points: 1

# Comments: 0

Article URL: https://gist.github.com/rjcorwin/296885590dc8a4ebc64e70879dc04a0f

Comments URL: https://news.ycombinator.com/item?id=47083166

Points: 1

# Comments: 0