Feed aggregator

tldr: We launched https://vantage.sh/models - a price to performance comparison tool for LLMs. If you're familiar with ec2instances.info....this is basically the LLM version of that.

- - - -

I'm Co-Founder and CEO of Vantage posting on behalf of our team that shipped this. Vantage is a cloud cost management platform. We also maintain https://ec2instances.info/ after buying the site a few years back. We've been hearing rumblings from the community looking for something similar for LLMs...so we built it.

The site is free and open-source and provides a centralized view of LLM model specifications, pricing, benchmarks, and hosting information. We're shipping early and looking for feedback. Give it a peek and let us know what you think.

Comments URL: https://news.ycombinator.com/item?id=47265549

Points: 1

# Comments: 0

Article URL: https://twitter.com/itsandrewgao/status/2029624157181497743

Comments URL: https://news.ycombinator.com/item?id=47265535

Points: 2

# Comments: 0

Article URL: https://callitearly.substack.com/p/what-went-wrong-before-anyone-noticed

Comments URL: https://news.ycombinator.com/item?id=47265526

Points: 1

# Comments: 0

Article URL: https://jyn.dev/remotely-unlocking-an-encrypted-hard-disk/

Comments URL: https://news.ycombinator.com/item?id=47265521

Points: 1

# Comments: 0

Article URL: https://thenewstack.io/openais-codex-is-now-on-windows/

Comments URL: https://news.ycombinator.com/item?id=47265504

Points: 1

# Comments: 0

Article URL: https://twitter.com/sama/status/2029622732594499630

Comments URL: https://news.ycombinator.com/item?id=47265487

Points: 2

# Comments: 0

Article URL: https://renderling.xyz/articles/introducing-wgsl-rs.html

Comments URL: https://news.ycombinator.com/item?id=47265480

Points: 1

# Comments: 0

Article URL: https://www.paxerp.com/blog/pax-origins

Comments URL: https://news.ycombinator.com/item?id=47265459

Points: 1

# Comments: 1

Article URL: https://tornikeo.com/docs-considered-harmful/

Comments URL: https://news.ycombinator.com/item?id=47265450

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=Kourq_Lz03U

Comments URL: https://news.ycombinator.com/item?id=47265439

Points: 1

# Comments: 1

Article URL: https://iafisher.com/notes/2026/03/scheduler-bug

Comments URL: https://news.ycombinator.com/item?id=47265436

Points: 1

# Comments: 0

Article URL: https://deploymentsafety.openai.com/gpt-5-4-thinking

Comments URL: https://news.ycombinator.com/item?id=47265432

Points: 1

# Comments: 0

Article URL: https://dimden.dev/blog/?id=15-webtiles-its-fine-to-accept-user-supplied-code-actually

Comments URL: https://news.ycombinator.com/item?id=47265425

Points: 2

# Comments: 0

I wanted to share my first-ever open-source project.

It’s a tool that surfaces your architectural decisions on pull requests or lets you check them locally using a CLI. You can also set up various rules to trigger actions based on changes in a PR.

I’d love to hear any feedback or suggestions on how I can improve it :>

Github Action : https://github.com/marketplace/actions/decision-guardian

NPM -: https://www.npmjs.com/package/decision-guardian

Source code -: https://github.com/DecispherHQ/decision-guardian

Comments URL: https://news.ycombinator.com/item?id=47265408

Points: 1

# Comments: 0

Hi HN,

I'm building Nexus Gateway, an AI gateway that helps developers reduce LLM API costs.

Problem: Many applications send repeated or semantically similar prompts to LLMs, which leads to unnecessary API calls and higher costs.

Solution: Nexus Gateway uses semantic caching to detect similar prompts and serve cached responses instead of calling the LLM again.

Features: • Semantic caching to reduce repeated API calls • Multi-model support (OpenAI, Gemini, Llama, Anthropic) • BYOK support • PII protection and sovereign AI layer (in progress)

Goal: Reduce LLM costs by 40–70% while improving latency.

I’d really appreciate feedback from the community.

Website: https://www.nexus-gateway.org

Comments URL: https://news.ycombinator.com/item?id=47265402

Points: 1

# Comments: 0

Article URL: https://github.com/zanetworker/aimux

Comments URL: https://news.ycombinator.com/item?id=47265394

Points: 1

# Comments: 1

I built GovernsAI to solve a problem I kept hitting while switching between OpenAI, Anthropic, and Google: no shared memory, no centralized access control, and PII leaking into prompts constantly.

It's essentially an AI OS layer that sits above the providers:

- Unified authentication across OpenAI, Anthropic, Google - Persistent memory management that follows you across models - A precheck service that catches PII before it hits any API - Budget enforcement and human-in-the-loop confirmation workflows - A browser extension (pii-guard) that intercepts at the input level

The architecture is documented in a paper I submitted to arXiv if you want to go deep on the design decisions.

Happy to answer questions about the infra choices, the memory layer, or why I built on top of providers instead of picking one.

https://governsai.com

Github: https://github.com/Governs-AI

Comments URL: https://news.ycombinator.com/item?id=47265365

Points: 1

# Comments: 0

Article URL: https://ritter.vg/blog-telemetry.html

Comments URL: https://news.ycombinator.com/item?id=47265356

Points: 1

# Comments: 0

Article URL: https://nmof.app.box.com/s/dhk54nhfonwr2g3jgbwubj5s4ip4rroy

Comments URL: https://news.ycombinator.com/item?id=47265349

Points: 1

# Comments: 0

Steve Gibson and Leo Laporte host a special episode of Security Now live from ThreatLocker's Zero Trust World 2026 in Orlando, Florida.

The final frontier of security is internal. Today, we have the tools, techniques and technologies to thwart attacks originating from outside our perimeter. We're now good at protecting our borders. But major high profile breaches occurring over the past several years have revealed that insufficient attention has been given to the security of our internal systems and networks. Today's greatest security weaknesses result from decades of system design, deployment and policy that have placed far too much trust on the conduct of those on the inside, behind our borders. Whether deliberate, inadvertent, or externally penetrating, the greatest challenge we now face is that of designing and deploying our internal security with strict adherence to the principles of least privilege and zero trust.

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsor:

• threatlocker.com/twit