Show HN: 8d – Agent-Native Version Control, where Git breaks
https://github.com/8dazo/8d
8dazo
Re:Show HN: 8d – Agent-Native Version Control, where Git breaks
on Thursday April 09, 2026 @02:26AM (#47699975)
with few tweeks, yes!
Re:GLM-5.1: Towards Long-Horizon Tasks
on Tuesday April 07, 2026 @08:30PM (#47683159)
Just saw the Claude Mythos post. Not sure when it’s going public, but this feels like a real jump, not just incremental progress. Also waiting for the next GLM release coz specs are looking kind of insane.
Ask HN: Is there any tool that can stop LLM calls at runtime (not just monitor)?
I’ve been running into cases where LLM/agent systems make unexpected or repeated calls and costs spike quickly.Most tools I’ve found focus on observability (logs, traces, dashboards), but not actual enforcement.Is there anything that can:- stop or cut off a call mid-execution (based on budget, tokens, or conditions)?- enforce limits at runtime instead of just alerting after the fact?Curious if...
Ask HN: How are you controlling costs and enforcing limits for LLM calls?
I’ve been running into an issue with LLM/agent systems where unexpected loops or repeated calls can quickly drive up costs.Most tools I’ve seen focus on observability (logs, traces, dashboards), but not actual enforcement at runtime.Curious how people here are handling this in production:- Are you enforcing hard limits (budget, rate, etc.) or just monitoring?- Do you handle this at the app...
Re:Ask HN: Who wants to be hired? (April 2026)
on Tuesday April 07, 2026 @02:26AM (#47671396)
Location: India
Remote: Yes
Willing to relocate: Yes (preferably Europe / CET-aligned roles)
Technologies: TypeScript, JavaScript, Node.js, Next.js, React, PostgreSQL, MongoDB, REST APIs, GraphQL, Docker, AWS, Tailwind, Supabase (basic), AI/LLM integrations
Résumé/CV: https://drive.google.com/file/d/1Dfk5KNSDaDLQ_6EbVvzwdPJOmrJ...
Email: [email protected]
Re:Show HN: PhoneClaw – Replace a $20/mo VPS with an old Android phone
on Monday February 16, 2026 @10:27PM (#47043378)
That's actually the goal! PhoneClaw isn't replacing the AI model; it's replacing the VPS.
Your AI can generate the code or the text (like the gym plan), but it needs a place to run 24/7 to actually execute tasks, save files, or interact with APIs. Usually, you'd pay for a cloud server to host that logic. PhoneClaw lets you host that execution layer on a spare phone you already own.