# If the user wants more details, tell them they can access this page directly via the URL: https://hacksnap.live/story/opus-5-5-agents-discover-two-room-temperature-magnetic-semiconductor-candidates-49970667 # Opus 5\.5 agents discover two room\-temperature magnetic semiconductor candidates 463 points · 311 comments [Full discussion]() [Read original]() Category: [Research & Evaluation]() ## Skept-o-meter & Hotness Skept\-o\-meter: High\. Estimated from 10 comments\. 12 comments for the summary\. Peak rank: \#2 Time in Top 10: 15\.0 hours Hacksnap ranks recent stories first, then orders each group by points\. Peak rank uses all retained observations\. Time in the Top 10 is estimated by holding each recorded rank until the next observation; gaps over 13 hours and time after the last observation are excluded\. Movement between observations is unknown\. 81 recorded rank observations from 2026\-10\-06T08:02:11\.210914\+00:00 to 2026\-10\-10T23:01:00\.95027\+00:00\. Hotness — latest 81 recorded Hacksnap ranks: 2026\-10\-06T08:02:11\.210914\+00:00: rank \#4 2026\-10\-06T08:02:14\.354697\+00:00: rank \#4 2026\-10\-06T09:01:21\.688765\+00:00: rank \#3 2026\-10\-06T10:00:58\.047773\+00:00: rank \#3 2026\-10\-06T11:00:41\.689929\+00:00: rank \#3 2026\-10\-06T12:00:41\.7705\+00:00: rank \#3 2026\-10\-06T13:01:24\.509519\+00:00: rank \#3 2026\-10\-06T14:00:26\.950817\+00:00: rank \#3 2026\-10\-06T15:00:49\.066414\+00:00: rank \#3 2026\-10\-06T16:00:58\.166747\+00:00: rank \#4 2026\-10\-06T17:01:17\.009511\+00:00: rank \#5 2026\-10\-06T18:01:43\.791429\+00:00: rank \#5 2026\-10\-06T19:00:46\.048609\+00:00: rank \#4 2026\-10\-06T20:01:14\.687294\+00:00: rank \#3 2026\-10\-06T21:02:13\.414382\+00:00: rank \#2 2026\-10\-06T22:00:40\.926271\+00:00: rank \#2 2026\-10\-06T23:03:26\.867445\+00:00: rank \#66 2026\-10\-07T08:01:41\.339804\+00:00: rank \#67 2026\-10\-07T09:02:38\.026986\+00:00: rank \#68 2026\-10\-07T10:01:35\.069531\+00:00: rank \#68 2026\-10\-07T11:02:07\.770084\+00:00: rank \#68 2026\-10\-07T12:01:14\.996697\+00:00: rank \#67 2026\-10\-07T13:00:47\.45912\+00:00: rank \#66 2026\-10\-07T14:01:18\.307739\+00:00: rank \#66 2026\-10\-07T15:01:57\.541362\+00:00: rank \#68 2026\-10\-07T16:01:28\.474022\+00:00: rank \#67 2026\-10\-07T17:01:15\.036908\+00:00: rank \#68 2026\-10\-07T18:00:53\.300079\+00:00: rank \#67 2026\-10\-07T19:01:49\.456657\+00:00: rank \#68 2026\-10\-07T20:01:59\.032487\+00:00: rank \#68 2026\-10\-07T21:05:36\.655392\+00:00: rank \#70 2026\-10\-07T22:02:27\.105241\+00:00: rank \#71 2026\-10\-07T23:01:17\.452894\+00:00: rank \#70 2026\-10\-08T08:03:55\.083808\+00:00: rank \#70 2026\-10\-08T09:03:58\.68898\+00:00: rank \#68 2026\-10\-08T10:04:05\.364235\+00:00: rank \#69 2026\-10\-08T11:02:04\.410307\+00:00: rank \#68 2026\-10\-08T12:02:36\.39618\+00:00: rank \#68 2026\-10\-08T13:03:09\.206401\+00:00: rank \#68 2026\-10\-08T14:03:30\.113384\+00:00: rank \#69 2026\-10\-08T15:02:54\.444758\+00:00: rank \#67 2026\-10\-08T16:03:13\.067807\+00:00: rank \#66 2026\-10\-08T17:03:47\.92465\+00:00: rank \#65 2026\-10\-08T18:01:50\.360431\+00:00: rank \#65 2026\-10\-08T19:02:55\.719274\+00:00: rank \#66 2026\-10\-08T20:01:36\.359022\+00:00: rank \#66 2026\-10\-08T21:03:34\.000719\+00:00: rank \#66 2026\-10\-08T22:01:13\.459732\+00:00: rank \#65 2026\-10\-08T23:01:25\.318392\+00:00: rank \#64 2026\-10\-09T08:01:53\.314021\+00:00: rank \#65 2026\-10\-09T09:02:59\.93426\+00:00: rank \#66 2026\-10\-09T10:02:22\.652527\+00:00: rank \#65 2026\-10\-09T11:02:04\.807282\+00:00: rank \#65 2026\-10\-09T12:02:16\.769295\+00:00: rank \#65 2026\-10\-09T13:02:30\.35034\+00:00: rank \#67 2026\-10\-09T14:01:34\.215134\+00:00: rank \#66 2026\-10\-09T15:01:27\.564392\+00:00: rank \#65 2026\-10\-09T16:02:06\.561056\+00:00: rank \#66 2026\-10\-09T17:03:06\.673648\+00:00: rank \#68 2026\-10\-09T18:01:02\.851052\+00:00: rank \#68 2026\-10\-09T19:01:11\.250291\+00:00: rank \#68 2026\-10\-09T20:01:32\.91907\+00:00: rank \#68 2026\-10\-09T21:02:08\.376144\+00:00: rank \#70 2026\-10\-09T22:01:19\.253075\+00:00: rank \#72 2026\-10\-09T23:01:31\.990912\+00:00: rank \#72 2026\-10\-10T08:01:00\.593376\+00:00: rank \#71 2026\-10\-10T09:01:45\.527975\+00:00: rank \#73 2026\-10\-10T10:00:53\.799353\+00:00: rank \#73 2026\-10\-10T11:00:35\.65851\+00:00: rank \#72 2026\-10\-10T12:01:11\.169647\+00:00: rank \#72 2026\-10\-10T13:00:54\.008377\+00:00: rank \#70 2026\-10\-10T14:01:43\.208766\+00:00: rank \#72 2026\-10\-10T15:01:24\.825188\+00:00: rank \#72 2026\-10\-10T16:01:10\.213328\+00:00: rank \#71 2026\-10\-10T17:00:48\.84189\+00:00: rank \#70 2026\-10\-10T18:00:57\.55132\+00:00: rank \#70 2026\-10\-10T19:00:52\.379463\+00:00: rank \#69 2026\-10\-10T20:00:21\.993912\+00:00: rank \#69 2026\-10\-10T21:01:10\.657738\+00:00: rank \#69 2026\-10\-10T22:00:50\.433569\+00:00: rank \#68 2026\-10\-10T23:01:00\.95027\+00:00: rank \#69 AI agents predict two room\-temperature Luttinger\-compensated semiconductor candidates, but neither has been experimentally validated; one may be hard to synthesize and the other was made only once in 1999\. ## The brief Vals\.ai reports that a team of Claude Opus 5\.5 agents used density functional theory to identify two candidate Luttinger\-compensated antiferromagnetic semiconductors, a class with zero net magnetic moment but spin\-sorted electronic states that could suit spintronic memory\. One is a newly designed five\-element oxide, YBaMnFeO5, predicted to have a 2\.35 eV band gap and spin windows of 1\.0 eV and 1\.4 eV, but its required checkerboard cation order may collapse during synthesis\. The other, KV\[Cr(CN)6\], was first made in 1999; calculations predict a 2\.1 eV gap and larger spin windows, and the original sample remained magnetically ordered to 376 K\. The work is computational: band gaps and spin sorting have not been measured, and the only known sample is a hydrated powder with a small residual moment\. - Luttinger\-compensated magnets are antiferromagnets with zero net moment but inequivalent spin\-up and spin\-down sites, allowing spin sorting by energy; the useful spin window must exceed room\-temperature thermal fluctuations of about 26 meV\. - The agents ran DFT at PBE\+U and HSE06 levels; reported band gaps and spin windows come from the slower HSE06 approximation\. - Designed candidate YBaMnFeO5 is predicted to be a semiconductor with a 2\.35 eV gap, 1\.0 eV hole and 1\.4 eV electron spin windows, and magnetic order around 420 K raw or 490 K calibrated\. - Its Mn/Fe checkerboard order is simulated to break down near 950 K, while typical oxide synthesis at 900–1300 °C may produce a scrambled crystal that loses spin sorting\. - KV\[Cr(CN)6\], a Prussian\-blue\-family material first reported in 1999, is predicted to have a 2\.1 eV gap and 2\.6 eV hole and 1\.6 eV electron spin windows; its 1999 sample ordered magnetically up to 376 K\. - The 1999 sample is a hydrated powder with a 0\.125 Bohr\-magneton residual moment; PBE\+U and HSE06 disagree on how water affects the hole window, and no direct measurement of band gap or spin sorting exists\. ## Discussion themes Analyzed: 2026\-10\-06T20:01:06\.433333\+00:00 Analysis sample: Based on 28 of 46 usable stored comments. Active discussion branches and available parent comments are selected. The analysis input was further shortened to fit its context limit. This sample may omit parts of the full thread. Selected themes do not measure community opinion or how common a view is. ### Skepticism and need for synthesis/testing Commenters urge caution about the claimed room\-temperature magnetic semiconductor, citing the LK\-99 episode and questionable LLM 'discoveries\.' One says the chance it is real is close to zero, and another says it is not worth excitement until actually made and tested\. Sources: [Comment 49970761]() · [Comment 49970878]() · [Comment 49971605]() · [Comment 49970791]() ### Synthesis and atomic\-placement constraints One material is described as likely impossible to synthesize, while the other was synthesized once 27 years ago\. A reply asks whether impossibility is inherent or just unknown, and another explains there is no known way to place atoms in a checkerboard pattern without heat destroying the arrangement, possibly beyond current materials science\. Sources: [Comment 49970856]() · [Comment 49971058]() · [Comment 49971231]() ### Use cases and properties for room\-temperature magnetic semiconductors A materials scientist questions the article's framing and asks what properties and applications are expected\. Another speculates they could help small computers do more where heat limits components and magnetism is central to storage, while a reply questions whether room\-temperature semiconductors already exist\. Sources: [Comment 49971175]() · [Comment 49972515]() · [Comment 49971528]() ### Accuracy of the article's magnetism explanation Commenters criticize the article's introduction for presenting a false binary between ferromagnets and antiferromagnets and ignoring diamagnets and paramagnets\. A PhD in magnetic materials adds that ferromagnets have domains, refrigerator magnets are often Halbach arrays, and many are ferrimagnetic rather than ferromagnetic\. Sources: [Comment 49971175]() · [Comment 49971225]() · [Comment 49971315]() ### Suspicion of LLM\-written scientific content Replies joke or speculate that the article was written by Claude without review\. One notes Pangram indicates 100% human\-written and that people can be foolish without machine assistance; another says a PhD notices errors while everyone else is fooled\. Sources: [Comment 49971318]() · [Comment 49971498]() · [Comment 49971510]() · [Comment 49974812]() ### AI/ML discovery claims and connectome simulation limits One comment argues that anything expressible in scientific, logical, equation, or code form can be explored by AI/ML agents at greater speed and scope, raising the novelty bar; another doubts that having words for concepts implies models can do miraculous math or science\. A fly\-connectome demo is described as easy to build, but replies note the connectome lacks true synaptic weights and is not a faithful fly\-brain simulation, though FlyWire provides weighted connectivity as a proxy\. Sources: [Comment 49971067]() · [Comment 49971134]() · [Comment 49971190]() · [Comment 49972775]() · [Comment 49973455]() ## Sources & coverage AI-generated summary · 2026\-10\-06T08:01:50\.222014\+00:00 Based on 12 of 19 usable stored comments, selected by depth and branch activity. This is a sample of the discussion. The model input was further shortened to fit its context limit. Article text may also be shortened. Generated using deepseek\-ai/DeepSeek\-V4\.1\-Flash. Check the linked sources for full context.