15:[[47789627,{"by":"edoardobambini-","descendants":2,"id":47789627,"kids":[47789649,47789638,47789629],"score":4,"time":1776322999,"title":"Show HN: Agent Armor, a Rust runtime that enforces policies on AI agent actions","type":"story","url":"https://github.com/EdoardoBambini/Agent-Armor-Iaga"}],[47761310,{"by":"paulpauper","descendants":28,"id":47761310,"kids":[47771905,47762208,47762634,47764466,47761415,47761775,47764414],"score":106,"time":1776141551,"title":"Math Is Still Catching Up to the Mysterious Genius of Srinivasa Ramanujan (2024)","type":"story","url":"https://www.quantamagazine.org/srinivasa-ramanujan-was-a-genius-math-is-still-catching-up-20241021/"}],[47748000,{"by":"kat-w","descendants":0,"id":47748000,"kids":[47748041],"score":2,"time":1776058459,"title":"How to Share Terraform State (Tutorial)","type":"story","url":"https://spacelift.io/blog/how-to-share-terraform-state"}],[47747987,{"by":"paulpauper","descendants":1,"id":47747987,"kids":[47748032],"score":4,"time":1776058354,"title":"Why successful people often have bad opinions online","type":"story","url":"https://greyenlightenment.com/2026/04/02/why-successful-people-often-have-bad-opinions-online/"}],[47747971,{"by":"walterbell","descendants":1,"id":47747971,"kids":[47748020],"score":4,"time":1776058136,"title":"The Future Is Neuro-Symbolic: Where Has It Been, and Where Is It Going?","type":"story","url":"https://ojs.aaai.org/index.php/AAAI/article/view/42130"}],[47713306,{"by":"1vuio0pswjnm7","descendants":0,"id":47713306,"kids":[47713394],"score":4,"time":1775792235,"title":"States are struggling to meet their clean energy goals Data centers are to blame","type":"story","url":"https://apnews.com/article/ai-data-centers-nevada-clean-energy-47d1b6633ed720962848f4b5b91e7d6b"}],[47713354,{"by":"JumpCrisscross","descendants":0,"id":47713354,"kids":[47713388],"score":5,"time":1775792617,"title":"How Accurate Are Google's A.I. Overviews?","type":"story","url":"https://www.nytimes.com/2026/04/07/technology/google-ai-overviews-accuracy.html"}],[47713276,{"by":"salkahfi","descendants":0,"id":47713276,"kids":[47713381],"score":2,"time":1775791894,"title":"Chang'e Mission Samples Reveal How Exogenous Organic Matter Evolves on the Moon","type":"story","url":"https://english.cas.cn/newsroom/research-news/202604/t20260408_1155384.shtml"}],[47689174,{"by":"chrsw","descendants":57,"id":47689174,"kids":[47689500,47690851,47691528,47690630,47692137,47693856,47703914,47689986,47691072,47690310,47689587,47689924,47722325,47699599,47697026,47697795,47690336,47692508,47689197,47700537,47696911,47698086,47690659,47690990,47694535],"score":326,"time":1775650740,"title":"MegaTrain: Full Precision Training of 100B+ Parameter LLMs on a Single GPU","type":"story","url":"https://arxiv.org/abs/2604.05091"}],[47688912,{"by":"trwhite","descendants":3,"id":47688912,"kids":[47689070,47689134,47688955,47689189],"score":7,"text":"$16","time":1775649096,"title":"Tell HN: I think my colleagues are just piping my replies into an LLM","type":"story"}],[47679121,{"by":"Ryan5453","descendants":836,"id":47679121,"kids":[47685285,47679745,47679406,47679397,47688452,47686445,47679653,47681769,47681825,47685847,47681896,47690125,47679433,47681164,47683200,47680125,47679428,47683506,47681367,47679529,47679364,47679276,47679418,47682135,47681619,47680897,47680272,47679542,47680698,47681369,47680503,47680291,47681069,47741137,47692284,47689809,47686948,47711779,47680155,47686020,47681915,47680297,47679706,47680782,47681767,47688907,47687352,47719445,47686366,47700656,47679453,47685607,47680574,47688043,47679798,47679658,47687011,47687355,47679578,47686075,47682700,47687968,47681998,47689226,47682001,47686900,47690102,47686099,47692669,47686552,47679215,47680523,47679450,47683941,47689899,47688534,47685560,47683243,47679814,47680936,47681984,47686984,47683528,47682613,47693287,47683309,47689041,47681082,47686233,47688691,47680067,47679922,47682257,47684947,47680251,47685058,47679464,47686465,47679427,47686200,47679625,47692195,47688185,47681480,47680907,47679502,47685107,47739184,47718139,47686946,47685492,47681422,47679969,47691478,47689322,47682033,47686895,47765782,47679574,47679635,47682494,47687830,47689087,47682946,47685290,47694865,47691124,47685088,47681682,47708293,47683028,47708943,47685017,47681426,47681901,47685520,47685093,47679311,47680078,47689160,47683957,47686439,47687975,47686849,47681327,47679305,47680347,47681639,47681772,47681981,47680086],"score":1541,"text":"Related: Assessing Claude Mythos Preview's cybersecurity capabilities - https://news.ycombinator.com/item?id=47679155

System Card: Claude Mythos Preview [pdf] - https://news.ycombinator.com/item?id=47679258

Also: Anthropic's Project Glasswing sounds necessary to me - https://news.ycombinator.com/item?id=47681241","time":1775585374,"title":"Project Glasswing: Securing critical software for the AI era","type":"story","url":"https://www.anthropic.com/glasswing"}],[47662945,{"by":"player_piano","descendants":91,"id":47662945,"kids":[47665431,47666420,47664280,47666896,47665338,47666906,47664931,47668968,47665219,47671801,47664148,47665109,47665822,47667098,47671044,47666871,47665739,47672951,47671789,47675232,47669700,47664475,47698544,47678296,47669065,47666851,47666023,47664545,47664585,47673248,47663327,47667914,47671659,47670836,47673450,47672244,47671088,47665599,47668566],"score":319,"text":"I've long been into finding deals on government auction sites (seizures, surplus sales etc.) - right now for example San Diego DHS is selling 26 tons of lead shot, with bidding starting at $1,000 ¯\\_(ツ)_/¯

It has historically been extremely tedious though: scanning dozens of janky sites which have interminable page loading times; back buttons take you all the way back to the homepage etc.

The site I built - GovAuctions - lets you search every government surplus auction at once. You can filter by location, category, and price, save items to a watchlist, and get alerts when new auctions match what you're looking for.

Let me know what you think, if you have any suggestions, and if you find any deals in your area!","time":1775492506,"title":"Show HN: GovAuctions lets you browse government auctions at once","type":"story","url":"https://www.govauctions.app/"}],[47671453,{"by":"8dazo","descendants":2,"id":47671453,"kids":[47675898,47671998,47671692,47673137,47685852,47672509,47673434,47684638,47684313,47672711],"score":3,"text":"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 level or via some middleware/proxy?

- Have you built something in-house for this?

Feels like an unsolved problem, especially with agents.

Would love to hear how others are dealing with it.","time":1775543616,"title":"Ask HN: How are you controlling costs and enforcing limits for LLM calls?","type":"story"}],[47670854,{"by":"stickynotememo","descendants":2,"id":47670854,"kids":[47673424,47670884],"score":2,"text":"There isn't really. But I wouldn't be surprised if there was.

Rust is Rust. Go is Go. These sorts of languages aren't necessary. Please use your Claude tokens for something else.","time":1775537106,"title":"Skunk: a Rust based language that compiles to Go","type":"story"}],[47666024,{"by":"MattHart88","descendants":200,"id":47666024,"kids":[47668726,47667921,47666315,47667734,47669076,47666186,47667062,47666394,47667271,47666292,47669774,47667473,47673857,47666755,47669179,47672538,47668845,47690879,47670423,47675539,47666947,47667743,47673835,47670185,47670166,47671738,47671460,47671577,47673653,47669791,47666980,47668137,47670311,47667257,47668044,47667016,47701707,47669046,47670903,47667233,47667494,47672988,47670232,47700992,47668774,47669619,47668978,47668488,47667671,47669787,47700177,47670716,47700288,47746685,47679060,47685269,47671640,47673418,47669916,47668960,47671145,47674927,47669628,47689853,47672374,47676377,47667935,47671794,47672517,47671343,47666999,47675783,47667704],"score":467,"text":"I built this because I wanted to see how far I could get with a voice-to-text app that used 100% local models so no data left my computer. I've been using a ton for coding and emails. Experimenting with using it as a voice interface for my other agents too. 100% open-source MIT license, would love feedback, PRs, and ideas on where to take it.","time":1775505016,"title":"Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS","type":"story","url":"https://github.com/matthartman/ghost-pepper"}]]

1.	2 points by edoardobambini- 4 days ago \| discuss
2.	Show HN: Agent Armor, a Rust runtime for enforcing policies on AI agent actions(github.com) 7 points by edoardobambini- 31 days ago \| 5 comments
3.	Show HN: Agent Armor, a Rust runtime that enforces policies on AI agent actions(github.com) 4 points by edoardobambini- 32 days ago \| 2 comments
4.	33 days ago \| discuss

user:	edoardobambini-
created:	April 7, 2026
karma:	5