Hacker News

Article URL: https://securitylab.amnesty.org/latest/2026/05/android-intrusion-logging-as-a-new-source-of-data-for-consensual-forensic-analysis/

Comments URL: https://news.ycombinator.com/item?id=48118090

Points: 1

# Comments: 0

Article URL: https://twitter.com/i/status/2054254470595330363

Comments URL: https://news.ycombinator.com/item?id=48118071

Points: 1

# Comments: 0

Article URL: https://github.com/LavaMoat/LavaMoat/blob/main/README.md

Comments URL: https://news.ycombinator.com/item?id=48118048

Points: 1

# Comments: 0

https://x.com/farreldarian/status/2054424419179896952

There are a growing number of products/features to manage agent sessions. Few built-ins, new app, but this I made specifically for tmux users running Claude Code and OpenCode.

It automatically detects all sessions without configuration

I built this since Feb 2026, but I haven't yet properly documented the features.

Dropping this here to see if anyone might be interested

Comments URL: https://news.ycombinator.com/item?id=48118041

Points: 1

# Comments: 0

Article URL: https://www.robertj1.com/torchlean_verified_nn_academic_blog_v7

Comments URL: https://news.ycombinator.com/item?id=48118040

Points: 1

# Comments: 0

Article URL: https://artificialconfidence.com/

Comments URL: https://news.ycombinator.com/item?id=48118023

Points: 1

# Comments: 1

Hello everyone,

My name is Alex. I’ve been a CTO for many years and am passionate about development.

Unsurprisingly, and like many others, AI has changed a lot of things and made processes much simpler and faster. However, this complexity is sometimes accompanied by new challenges that are unique to AI. As we know, AI—and more specifically LLMs—have no memory; they can’t store information within their context and may perform the same search 50 times. Many solutions are now available to address this shortcoming, and that’s great. But I also quickly realized that beyond the memory issue, the problem surrounding context is a real challenge. Ask Claude Code to quickly and easily understand a 10-year-old monolith, and you’ll see what I mean... The infamous LLM hallucinations will pop up fast, and the endless repetition of grep commands or similar to read through all the code will become a never-ending task... Not to mention the token consumption.

So I dug into the problem to come up with a solution. After weeks of development, I’m pretty pleased with myself and would like to share my Graphmind project with you.

Graphmind allows you to understand a project’s deep structure, not just its surface. Specifically, it builds a graph of all functions, classes, and the calls between them (i.e., AST parsing, not grep-style regex). In addition, it semantically indexes each symbol using embeddings. So when Claude searches for “wallet creation,” he doesn’t run a grep; he queries the graph and finds `create_wallet_for_user` or `provisionWallet` even if the exact name isn’t in the query.

And beyond the graph, I added a persistent memory layer as well as an MCP server to easily interact with it. Result: This isn’t a silver bullet for all AI-related problems, and I don’t claim to have reinvented anything. But this is what I was missing to really let Claude Code work on serious codebases without it getting lost after 20 minutes or consuming all the context through blind reading.

I wanted to measure concretely what difference this makes, so I took one of my repositories that’s around 31k symbols. A `grep “payment processing”` search returns 5.9 MB of noise (comments, tests, strings, variable names)—about 1.4 million tokens for Claude to process. The same query via GraphMind returns 1 KB of structured data, sorted by relevance, with callers and callees already attached. 257 tokens. That’s 5,700 times less. Over a typical session with 5 to 10 searches, that’s about 10 million tokens saved—an entire context window. Now, let me reassure you: I’m not hallucinating. This is truly the observed result.

If you’re working with Claude Code or Cursor on a large codebase, with lots of different projects, and you’re struggling with the same issues, I’d love to hear your thoughts. The repo is public, and you can find it here: https://github.com/aouicher/graphmind

with pleasure to discuss about that.

Comments URL: https://news.ycombinator.com/item?id=48118017

Points: 1

# Comments: 0

Article URL: https://medium.com/@aliceviola/why-we-built-our-own-message-queue-for-ai-agents-and-put-it-on-postgres-37512424b8e0

Comments URL: https://news.ycombinator.com/item?id=48118013

Points: 1

# Comments: 0

Article URL: https://radiant-shaders.com/learn/event-horizon

Comments URL: https://news.ycombinator.com/item?id=48118006

Points: 1

# Comments: 0

Article URL: https://chronic-chronicler.com/

Comments URL: https://news.ycombinator.com/item?id=48117959

Points: 1

# Comments: 0

Article URL: https://en.wikipedia.org/wiki/Nora_(cat)

Comments URL: https://news.ycombinator.com/item?id=48117947

Points: 2

# Comments: 0

Isn't Markdown's hallmark its versatility while performant? I see there is an increasing call from tech community towards HTML to be adopted instead of Markdown due to its richness in the agentic communication layer. But is it versatile across any kind of interfaces? versatile with different format conversions? and performant (as the md is lightweight)?

Comments URL: https://news.ycombinator.com/item?id=48117941

Points: 1

# Comments: 3

Comments URL: https://news.ycombinator.com/item?id=48117928

Points: 1

# Comments: 0

Article URL: https://www.raptitude.com/2015/03/how-to-get-yourself-to-do-things/

Comments URL: https://news.ycombinator.com/item?id=48117916

Points: 1

# Comments: 0

Article URL: https://agentdocsspec.com/

Comments URL: https://news.ycombinator.com/item?id=48117909

Points: 2

# Comments: 0

Article URL: https://apnews.com/article/iran-war-hormuz-color-ink-japan-3ce00fb5e9e9abeb6dd8116522272cec

Comments URL: https://news.ycombinator.com/item?id=48117834

Points: 3

# Comments: 0

What the title says, here to answer any questions you mgith have.

Comments URL: https://news.ycombinator.com/item?id=48117823

Points: 1

# Comments: 0

Article URL: https://corticallabs.com/cloud

Comments URL: https://news.ycombinator.com/item?id=48117818

Points: 1

# Comments: 1

Article URL: https://www.tomshardware.com/pc-components/cpus/amd-crafts-custom-epyc-cpu-for-microsoft-azure-with-hbm3-memory-cpu-with-88-zen-4-cores-and-450gb-of-hbm3-may-be-repurposed-mi300c-four-chips-hit-7-tb-s

Comments URL: https://news.ycombinator.com/item?id=48117817

Points: 1

# Comments: 0

Article URL: https://arxiv.org/abs/2605.08419

Comments URL: https://news.ycombinator.com/item?id=48117810

Points: 19

# Comments: 0