Hacker News

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

Article URL: https://allenai.org/papers/olmo-hybrid

Comments URL: https://news.ycombinator.com/item?id=47264773

Points: 1

# Comments: 0

Article URL: https://github.com/avishek-sen-gupta/red-dragon

Comments URL: https://news.ycombinator.com/item?id=47264767

Points: 1

# Comments: 1

Article URL: https://varun.ch/posts/autofill/

Comments URL: https://news.ycombinator.com/item?id=47264765

Points: 1

# Comments: 0

Just launched the revamped Plought: a decision-making app to compare options with structured methods. This version includes new tools and summarized analysis based on your inputs.

Use it for hard choices like where to move, which job to take, or what car to buy.

Free, no login, and open source.

Your data stays private in your browser’s local storage, with export available.

Try it: https://plought.app/

Code: https://github.com/rossrobino/plought

Feedback welcome!

Comments URL: https://news.ycombinator.com/item?id=47264764

Points: 1

# Comments: 0

Article URL: https://paulgraham.com/brandage.html

Comments URL: https://news.ycombinator.com/item?id=47264756

Points: 2

# Comments: 0

Article URL: https://www.leanvibe.io/blog/bp-1772314620433

Comments URL: https://news.ycombinator.com/item?id=47264744

Points: 1

# Comments: 1

Article URL: https://landedstar.com/blog/posts/how-my-application-programmer-instincts-failed-when-debugging-assembler/

Comments URL: https://news.ycombinator.com/item?id=47264742

Points: 1

# Comments: 0

Hi HN! We're Gobhanu and Saatvik (brothers), building Vela (https://tryvela.ai) - AI agents that handle multi-party, multi-channel scheduling.

Scheduling is a constraint satisfaction problem disguised as email! It’s easy when it’s two people, one timezone, one channel. But it becomes a constraint satisfaction problem when inputs are unstructured natural language across multiple communication channels, constraints change mid-solve, and the objective function includes social dynamics that don't exist formally anywhere.

What if scheduling just happened? For example: a recruiter sends one message, and every interview across five candidates, three hiring managers, and two time zones gets booked, confirmed, and updated automatically. No links, no back-and-forth, no one spending hours with 20 emails. Everyone just gets the right invite at the right time, on whatever channel they actually use. That's what we built Vela to do.

You loop in Vela into your emails, SMS, WhatsApp, Slack, phone or integrate into an ATS etc and it takes over: reads context, checks calendars, proposes times, follows up when people ghost, and rebooks when things shift.

One of our first customers is a staffing firm that searched for a scheduling solution for almost eight years. Their coordinators manage hundreds of candidate-client interviews where each side needs separate email threads, separate Zoom accounts to avoid double-booking links, and calendar invites connecting parties who never directly communicate. A client reschedules one interview and it cascades into four others. A candidate responds on SMS to a thread that started on email. Vela solved this in just 10 minutes of onboarding.

The hardest part has been the data problem. Scheduling behavior varies enormously across populations. C-suite folks respond to email within hours and expect formal 3-option proposals. Truck drivers applying for logistics roles respond to SMS at odd hours from shared devices with "y tm wrks." The failure mode isn't parsing -- it's applying the wrong interaction pattern for the wrong segment and watching the conversation die. We've been building behavioral datasets from thousands of real interactions: response latency by role, channel preference by demographic, follow-up timing curves, how many options to propose before you hit decision paralysis. This data doesn't exist anywhere.

The core agent challenge is state across channels. When someone responds on SMS to a thread that started in email, Vela needs to unify identity, merge context, and continue without losing information. Phone numbers don't map cleanly to emails, people use nicknames on text, shared devices mean the responder might not be who you reached out to. Temporal NLU is its own problem -- "next Friday" means different things on Monday versus Thursday. We extract structured constraints from natural language and resolve against calendar state. When ambiguity can't be resolved, Vela asks -- but deciding when to ask versus infer depends on the stakes of getting it wrong.

We're live with paying enterprise customers and every client still surfaces edge cases that surprise us. Case studies on our site (https://tryvela.ai/case-studies/). You can check out a demo here: https://www.youtube.com/watch?v=MzUOjSG5Uvw.

We'd love feedback from anyone who's worked on multi-agent coordination, conversational AI across channels, or constraint satisfaction in messy real-world domains. Looking forward to your comments :)

Comments URL: https://news.ycombinator.com/item?id=47264741

Points: 1

# Comments: 0

Article URL: https://bluenotebook.io/blog/h100-nanochat-training/

Comments URL: https://news.ycombinator.com/item?id=47264729

Points: 1

# Comments: 1

Article URL: https://cleantechnica.com/2026/03/01/durens-hydrogen-bet-the-math-behind-a-looming-liability/

Comments URL: https://news.ycombinator.com/item?id=47264707

Points: 1

# Comments: 0

Article URL: https://www.mdpi.com/2078-2489/17/3/237

Comments URL: https://news.ycombinator.com/item?id=47264703

Points: 1

# Comments: 0