mastodon.ie is one of the many independent Mastodon servers you can use to participate in the fediverse.
Irish Mastodon - run from Ireland, we welcome all who respect the community rules and members.

Administered by:

Server stats:

1.6K
active users

#benchmarks

1 post1 participant0 posts today
Alo Japan<p><a href="https://www.alojapan.com/1331021/japanese-led-xrism-makes-first-ever-direct-detection-of-sulfur-in-two-states/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">alojapan.com/1331021/japanese-</span><span class="invisible">led-xrism-makes-first-ever-direct-detection-of-sulfur-in-two-states/</span></a> Japanese-led XRISM makes first-ever direct detection of sulfur in two states <a href="https://channels.im/tags/benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>benchmarks</span></a> <a href="https://channels.im/tags/GraphicsCard" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GraphicsCard</span></a> <a href="https://channels.im/tags/Japan" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Japan</span></a> <a href="https://channels.im/tags/JapanNews" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>JapanNews</span></a> <a href="https://channels.im/tags/Japanese" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Japanese</span></a> <a href="https://channels.im/tags/JapaneseNews" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>JapaneseNews</span></a> <a href="https://channels.im/tags/laptop" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>laptop</span></a> <a href="https://channels.im/tags/nasa" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>nasa</span></a> <a href="https://channels.im/tags/netbook" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>netbook</span></a> <a href="https://channels.im/tags/news" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>news</span></a> <a href="https://channels.im/tags/notebook" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>notebook</span></a> <a href="https://channels.im/tags/processor" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>processor</span></a> <a href="https://channels.im/tags/reports" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reports</span></a> <a href="https://channels.im/tags/review" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>review</span></a> <a href="https://channels.im/tags/reviews" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reviews</span></a> <a href="https://channels.im/tags/test" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>test</span></a> <a href="https://channels.im/tags/tests" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tests</span></a> <a href="https://channels.im/tags/XRISMSatellite" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>XRISMSatellite</span></a> <a href="https://channels.im/tags/XRISMSatelliteDetectsSulfurInTwoStates" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>XRISMSatelliteDetectsSulfurInTwoStates</span></a> An international team of scientists has, for the first time, directly detected sulfur in both its gas and solid phases in the interstellar medium — the gas-</p>
Benjamin Han<p>“The best-performing model is Gemini 2.5 Pro, achieving a score of 31% (13 points), which is well below the 19/42 score necessary for a bronze medal. Other models lagged significantly behind, with Grok-4 and DeepSeek-R1 in particular underperforming relative to their earlier results on other MathArena benchmarks.”</p><p>MathArena - IMO Blogpost <a href="https://matharena.ai/imo/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">matharena.ai/imo/</span><span class="invisible"></span></a></p><p><a href="https://sigmoid.social/tags/math" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>math</span></a> <a href="https://sigmoid.social/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llm</span></a> <a href="https://sigmoid.social/tags/reasoning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reasoning</span></a> <a href="https://sigmoid.social/tags/benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>benchmarks</span></a></p>
Alo Japan<p><a href="https://www.alojapan.com/1323451/casios-fan-favorite-dw-5600khg24-1jr-japan-themed-g-shock-now-back-in-stock-for-a-limited-time/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">alojapan.com/1323451/casios-fa</span><span class="invisible">n-favorite-dw-5600khg24-1jr-japan-themed-g-shock-now-back-in-stock-for-a-limited-time/</span></a> Casio’s fan-favorite DW-5600KHG24-1JR Japan-themed G-Shock now back in stock for a limited time <a href="https://channels.im/tags/benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>benchmarks</span></a> <a href="https://channels.im/tags/casio" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>casio</span></a> <a href="https://channels.im/tags/CasioDW5600KHG241JRRestock" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CasioDW5600KHG241JRRestock</span></a> <a href="https://channels.im/tags/DW5600KHG24BuyJapan" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DW5600KHG24BuyJapan</span></a> <a href="https://channels.im/tags/DW5600KHG241JR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DW5600KHG241JR</span></a> <a href="https://channels.im/tags/GShock" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GShock</span></a> <a href="https://channels.im/tags/GraphicsCard" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GraphicsCard</span></a> <a href="https://channels.im/tags/Hokusai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Hokusai</span></a> <a href="https://channels.im/tags/HokusaiGSHOCK2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HokusaiGSHOCK2025</span></a> <a href="https://channels.im/tags/Japan" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Japan</span></a> <a href="https://channels.im/tags/JapanExclusiveGSHOCK" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>JapanExclusiveGSHOCK</span></a> <a href="https://channels.im/tags/JapanNews" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>JapanNews</span></a> <a href="https://channels.im/tags/laptop" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>laptop</span></a> <a href="https://channels.im/tags/LEDBacklight" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LEDBacklight</span></a> <a href="https://channels.im/tags/LimitedEdition" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LimitedEdition</span></a> <a href="https://channels.im/tags/LimitedEditionCasioJapan" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LimitedEditionCasioJapan</span></a> <a href="https://channels.im/tags/netbook" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>netbook</span></a> <a href="https://channels.im/tags/news" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>news</span></a> <a href="https://channels.im/tags/notebook" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>notebook</span></a> <a href="https://channels.im/tags/processor" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>processor</span></a> <a href="https://channels.im/tags/reports" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reports</span></a> <a href="https://channels.im/tags/restock" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>restock</span></a> <a href="https://channels.im/tags/review" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>review</span></a> <a href="https://channels.im/tags/reviews" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reviews</span></a> <a href="https://channels.im/tags/test" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>test</span></a> <a href="https://channels.im/tags/tests" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tests</span></a> <a href="https://channels.im/tags/TimeStationNEOGSHOCK" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TimeStationNEOGSHOCK</span></a> <a href="https://channels.im/tags/UkiyoE" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>UkiyoE</span></a> <a href="https://channels.im/tags/Yamagata" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Yamagata</span></a></p>
➴➴➴Æ🜔Ɲ.Ƈꭚ⍴𝔥єɼ👩🏻‍💻<p>Okay, here it is. This is the unofficial official timeline of <a href="https://lgbtqia.space/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a>. I'm going to tell you what to expect, and it's definitely not: this all goes away and we return to before. </p><p>Are you ready for this? Are you sure? Well, read on.</p><p>Before I continue, I'm going to lay out some AI <a href="https://lgbtqia.space/tags/benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>benchmarks</span></a> that we'll use to define "how good / scary is this AI?" This is in rough order of difficulty.</p><p><a href="https://lgbtqia.space/tags/Lovelace" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Lovelace</span></a> <a href="https://lgbtqia.space/tags/Test" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Test</span></a> for <a href="https://lgbtqia.space/tags/Emergence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Emergence</span></a>: "Can a system produce surprising and useful outputes that weren't explicitely programmed via weak emergence?"</p><p><a href="https://lgbtqia.space/tags/Loebner" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Loebner</span></a> Test: "Can a computer fool casual human judges in text conversations?" ( <a href="https://lgbtqia.space/tags/Modern" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Modern</span></a> <a href="https://lgbtqia.space/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> AIs are close to this )</p><p><a href="https://lgbtqia.space/tags/Turing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Turing</span></a> Test (Original Imitation Game): "A man or a computer and a woman are both answering text interrogations trying to convince them that they are the woman. Can the computer perform as well as the man?" (This was the actual orginial <a href="https://lgbtqia.space/tags/TuringTest" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TuringTest</span></a>.)</p><p>Strengthened <a href="https://lgbtqia.space/tags/Imitation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Imitation</span></a> Game: "A man or a <a href="https://lgbtqia.space/tags/computer" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>computer</span></a> and a woman are both answering text interrogations. Can the computer perform as well as the woman?"</p><p><a href="https://lgbtqia.space/tags/Coffee" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Coffee</span></a> Test: "Can a <a href="https://lgbtqia.space/tags/system" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>system</span></a> enter a strangers house with no prior infor and using <a href="https://lgbtqia.space/tags/perception" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>perception</span></a>, imitation, and <a href="https://lgbtqia.space/tags/reasoning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reasoning</span></a> figure out how to make a cup of coffee?"</p><p><a href="https://lgbtqia.space/tags/College" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>College</span></a> <a href="https://lgbtqia.space/tags/Student" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Student</span></a> Test: "Can a robot enroll in college, attend classes like an actual student, learn from the instructions things it didn't know before, and graduate?"</p><p><a href="https://lgbtqia.space/tags/VoightKampff" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VoightKampff</span></a> Test: "Can a machine withstand adversarial exper interrogation and still pass as <a href="https://lgbtqia.space/tags/human" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>human</span></a>?"</p><p><a href="https://lgbtqia.space/tags/Harnad" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Harnad</span></a>'s Total Turing Test: "Is the system indistinguishible from humans in every aspect?" (This is a <a href="https://lgbtqia.space/tags/DuckTest" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DuckTest</span></a>.) </p><p>Non <a href="https://lgbtqia.space/tags/Duck" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Duck</span></a> Test: "Even with full access to internals, can experts find no evidence that it isn't a genuine human mind?"</p>
Lorry<p>All I want in the world today, is a quickly bootable ISO benchmarking tool so I can quickly work out which of these 15 laptops deserves the SSD!</p><p><a href="https://infosec.exchange/tags/Linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Linux</span></a> <a href="https://infosec.exchange/tags/Windows" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Windows</span></a> <a href="https://infosec.exchange/tags/Benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Benchmarks</span></a></p>
it's B! Cavello 🐝<p>What is it called in other fields when you test stuff for safety/toxicity/etc?<br>Threshold? Limit? Standard?</p><p>I think there’s actually a variety of language out there, based on searching around a little, but it’s not a benchmark.</p><p>I think that it could be valuable to separate <a href="https://mastodon.publicinterest.town/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> safety testing that is about searching for capabilities that exceed a limit from <a href="https://mastodon.publicinterest.town/tags/benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>benchmarks</span></a>, which are capabilities we WANT.</p>
Erik Jonker<p>A new day a new AI benchmark.<br><a href="https://www.nature.com/articles/d41586-025-02177-7" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">nature.com/articles/d41586-025</span><span class="invisible">-02177-7</span></a><br><a href="https://mastodon.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://mastodon.social/tags/benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>benchmarks</span></a></p>
Alo Japan<p><a href="https://www.alojapan.com/1317281/playstation-sega-and-square-enix-confirmed-for-tokyo-game-show-2025/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">alojapan.com/1317281/playstati</span><span class="invisible">on-sega-and-square-enix-confirmed-for-tokyo-game-show-2025/</span></a> PlayStation, SEGA, and Square Enix confirmed for Tokyo Game Show 2025 <a href="https://channels.im/tags/benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>benchmarks</span></a> <a href="https://channels.im/tags/GraphicsCard" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GraphicsCard</span></a> <a href="https://channels.im/tags/laptop" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>laptop</span></a> <a href="https://channels.im/tags/netbook" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>netbook</span></a> <a href="https://channels.im/tags/news" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>news</span></a> <a href="https://channels.im/tags/notebook" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>notebook</span></a> <a href="https://channels.im/tags/PlayStationNews" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PlayStationNews</span></a> <a href="https://channels.im/tags/processor" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>processor</span></a> <a href="https://channels.im/tags/reports" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reports</span></a> <a href="https://channels.im/tags/review" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>review</span></a> <a href="https://channels.im/tags/reviews" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reviews</span></a> <a href="https://channels.im/tags/SEGAGames" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SEGAGames</span></a> <a href="https://channels.im/tags/SonyPlayStationGames" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SonyPlayStationGames</span></a> <a href="https://channels.im/tags/SquareEnixGames" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SquareEnixGames</span></a> <a href="https://channels.im/tags/SquareEnixNews" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SquareEnixNews</span></a> <a href="https://channels.im/tags/test" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>test</span></a> <a href="https://channels.im/tags/tests" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tests</span></a> <a href="https://channels.im/tags/Tokyo" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Tokyo</span></a> <a href="https://channels.im/tags/TokyoGamesShow2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TokyoGamesShow2025</span></a> <a href="https://channels.im/tags/TokyoNews" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TokyoNews</span></a> <a href="https://channels.im/tags/%E6%9D%B1%E4%BA%AC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>東京</span></a> <a href="https://channels.im/tags/%E6%9D%B1%E4%BA%AC%E9%83%BD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>東京都</span></a> Tokyo Game Show 2025 is shaping up to be one of the largest in the event’s history as PlayStation, Sega, and Square Enix have been offici</p>
Christopher Stark<p>Steinzeit Windows-Benchmarktools unter Linux mit WINE getestet:</p><p><a href="https://www.christopherstark.de/seite-2/steinzeit-benchmarks-unter-wine/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">christopherstark.de/seite-2/st</span><span class="invisible">einzeit-benchmarks-unter-wine/</span></a></p><p><a href="https://mastodon.social/tags/linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>linux</span></a> <a href="https://mastodon.social/tags/wine" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>wine</span></a> <a href="https://mastodon.social/tags/linuxgames" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>linuxgames</span></a> <a href="https://mastodon.social/tags/benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>benchmarks</span></a> <a href="https://mastodon.social/tags/cpu" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cpu</span></a> <a href="https://mastodon.social/tags/prozessor" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>prozessor</span></a> <a href="https://mastodon.social/tags/windows" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>windows</span></a> <a href="https://mastodon.social/tags/computer" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>computer</span></a> <a href="https://mastodon.social/tags/it" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>it</span></a> <a href="https://mastodon.social/tags/software" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>software</span></a> <a href="https://mastodon.social/tags/hardware" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>hardware</span></a> <a href="https://mastodon.social/tags/amd" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>amd</span></a> <a href="https://mastodon.social/tags/intel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>intel</span></a> <a href="https://mastodon.social/tags/opensource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opensource</span></a> <a href="https://mastodon.social/tags/emulator" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>emulator</span></a></p>
🧿🪬🍄🌈🎮💻🚲🥓🎃💀🏴🛻🇺🇸<p>I ran <a href="https://mastodon.social/tags/BrowserBench" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BrowserBench</span></a> on a few of the browsers I have installed on my Ryzen/Radeon Windows 11 machine and the results are typical (<a href="https://mastodon.social/tags/Gecko" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Gecko</span></a> browsers are slow) and unusual (<a href="https://mastodon.social/tags/Opera" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Opera</span></a> is falling behind)</p><p><a href="https://mastodon.social/tags/webDev" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>webDev</span></a> <a href="https://mastodon.social/tags/browser" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>browser</span></a> <a href="https://mastodon.social/tags/benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>benchmarks</span></a> <a href="https://mastodon.social/tags/web" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>web</span></a> <a href="https://mastodon.social/tags/browsers" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>browsers</span></a> <a href="https://mastodon.social/tags/firefox" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>firefox</span></a> <a href="https://mastodon.social/tags/brave" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>brave</span></a> <a href="https://mastodon.social/tags/opera" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opera</span></a> <a href="https://mastodon.social/tags/edge" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>edge</span></a> <a href="https://mastodon.social/tags/librewolf" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>librewolf</span></a> <a href="https://mastodon.social/tags/floorp" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>floorp</span></a></p>
Benjamin Carr, Ph.D. 👨🏻‍💻🧬<p>The Best Boring <a href="https://hachyderm.io/tags/Benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Benchmarks</span></a>: <a href="https://hachyderm.io/tags/RockyLinux10" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RockyLinux10</span></a> &amp; <a href="https://hachyderm.io/tags/AlmaLinux10" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AlmaLinux10</span></a> Performance Against <a href="https://hachyderm.io/tags/RHEL10" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RHEL10</span></a> Review<br>Testing on an AMD EPYC 9755 2P (EPYC Turin) server and using the same hardware across all tests, the performance of <a href="https://hachyderm.io/tags/RockyLinux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RockyLinux</span></a> 10 and <a href="https://hachyderm.io/tags/AlmaLinux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AlmaLinux</span></a> 10 were right on-par with <a href="https://hachyderm.io/tags/RedHat" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RedHat</span></a> <a href="https://hachyderm.io/tags/EnterpriseLinux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EnterpriseLinux</span></a> 10 itself. Hence the best kind of boring benchmarks when the performance is right on track for where it should be. <br><a href="https://www.phoronix.com/review/almalinux-10-rocky-linux-10" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">phoronix.com/review/almalinux-</span><span class="invisible">10-rocky-linux-10</span></a><br><a href="https://hachyderm.io/tags/RHEL" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RHEL</span></a> <a href="https://hachyderm.io/tags/Linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Linux</span></a></p>
Mathias Hasselmann<p>One of these rare cases when optimized builds are 10 times faster than debug builds...</p><p><a href="https://gist.github.com/hasselmm/ae45282538a4b981d2169c8aa42fead9" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">gist.github.com/hasselmm/ae452</span><span class="invisible">82538a4b981d2169c8aa42fead9</span></a></p><p><a href="https://mastodon.green/tags/Programming" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Programming</span></a> <a href="https://mastodon.green/tags/Benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Benchmarks</span></a></p>
All for Gardening<p>Roblox Grow a Garden codes June 2025 <a href="https://www.allforgardening.com/1318482/roblox-grow-a-garden-codes-june-2025/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">allforgardening.com/1318482/ro</span><span class="invisible">blox-grow-a-garden-codes-june-2025/</span></a> <a href="https://vive.im/tags/benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>benchmarks</span></a> <a href="https://vive.im/tags/Codes" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Codes</span></a> <a href="https://vive.im/tags/garden" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>garden</span></a> <a href="https://vive.im/tags/GraphicsCard" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GraphicsCard</span></a> <a href="https://vive.im/tags/GrowAGarden" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GrowAGarden</span></a> <a href="https://vive.im/tags/laptop" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>laptop</span></a> <a href="https://vive.im/tags/netbook" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>netbook</span></a> <a href="https://vive.im/tags/notebook" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>notebook</span></a> <a href="https://vive.im/tags/processor" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>processor</span></a> <a href="https://vive.im/tags/reports" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reports</span></a> <a href="https://vive.im/tags/Review" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Review</span></a> <a href="https://vive.im/tags/reviews" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reviews</span></a> <a href="https://vive.im/tags/roblox" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>roblox</span></a> <a href="https://vive.im/tags/test" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>test</span></a> <a href="https://vive.im/tags/Tests" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Tests</span></a></p>
Benjamin Carr, Ph.D. 👨🏻‍💻🧬<p><a href="https://hachyderm.io/tags/AMD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AMD</span></a> <a href="https://hachyderm.io/tags/EPYC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC</span></a> <a href="https://hachyderm.io/tags/4565P" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>4565P</span></a> &amp; <a href="https://hachyderm.io/tags/4585PX" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>4585PX</span></a> <a href="https://hachyderm.io/tags/Benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Benchmarks</span></a> Against <a href="https://hachyderm.io/tags/Xeon" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Xeon</span></a> <a href="https://hachyderm.io/tags/6369P" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>6369P</span></a><br>For "conventional" <a href="https://hachyderm.io/tags/server" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>server</span></a> workloads like web serving and databases, the EPYC 4005 series dominates.<br>With up to 16C/32TH, <a href="https://hachyderm.io/tags/AVX512" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AVX512</span></a>, DDR5-5600 memory and other advantages, the EPYC 4005 series is the very easy answer for those that may be looking for affordable <a href="https://hachyderm.io/tags/HPC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HPC</span></a> <br>The AMD <a href="https://hachyderm.io/tags/EPYC4005" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EPYC4005</span></a> series <a href="https://hachyderm.io/tags/CPU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CPU</span></a> deliver excellent generational uplift over the EPYC 4004 series and outright obliterating the <a href="https://hachyderm.io/tags/Xeon6300" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Xeon6300</span></a> series<br><a href="https://www.phoronix.com/review/amd-epyc-4585px-4565p-benchmarks" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">phoronix.com/review/amd-epyc-4</span><span class="invisible">585px-4565p-benchmarks</span></a></p>
Nicole Hennig<p>Introducing HealthBench: OpenAI <a href="https://openai.com/index/healthbench/?_bhlid=99c22d264d81560c41bfe7e02e0ff141b4321e86" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">openai.com/index/healthbench/?</span><span class="invisible">_bhlid=99c22d264d81560c41bfe7e02e0ff141b4321e86</span></a> <a href="https://techhub.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://techhub.social/tags/healthcare" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>healthcare</span></a> <a href="https://techhub.social/tags/benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>benchmarks</span></a></p>
Thomas Wouters<p>You know how sometimes a little hobby side-project can get a bit out of hand? An unexpected performance regression on speed.python.org that only showed up on GCC 5 (and 7) led me to set up more rigorous tracking of Python performance when using different compilers. I'm still backfilling data but I think it's pretty awesome to see how much, and how consistently, free-threaded Python performance has improved since 3.13:</p><p><a href="https://github.com/Yhg1s/python-benchmarking-public" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/Yhg1s/python-benchm</span><span class="invisible">arking-public</span></a></p><p><a href="https://social.coop/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Python</span></a> <a href="https://social.coop/tags/benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>benchmarks</span></a> <a href="https://social.coop/tags/PEP703" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PEP703</span></a></p>
Ionut Balosin<p>🚀 Call for Contributors – <a href="https://mastodon.social/tags/JVM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>JVM</span></a> <a href="https://mastodon.social/tags/Performance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Performance</span></a> <a href="https://mastodon.social/tags/Benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Benchmarks</span></a></p><p>If you're interested in contributing to the <a href="https://mastodon.social/tags/JVM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>JVM</span></a> <a href="https://mastodon.social/tags/Performance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Performance</span></a> <a href="https://mastodon.social/tags/Benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Benchmarks</span></a> project - an initiative that gained significant traction in the <a href="https://mastodon.social/tags/Java" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Java</span></a> community through our recent <a href="https://mastodon.social/tags/JDK17" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>JDK17</span></a> and <a href="https://mastodon.social/tags/JDK21" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>JDK21</span></a> analyses - check out the repo:</p><p>🔗 <a href="https://github.com/ionutbalosin/jvm-performance-benchmarks" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/ionutbalosin/jvm-pe</span><span class="invisible">rformance-benchmarks</span></a></p><p>🧵 DM me or open a PR to get started</p><p><a href="https://mastodon.social/tags/Java" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Java</span></a> <a href="https://mastodon.social/tags/JVM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>JVM</span></a> <a href="https://mastodon.social/tags/OpenJDK" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenJDK</span></a> <a href="https://mastodon.social/tags/GraalVM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GraalVM</span></a> <a href="https://mastodon.social/tags/JMH" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>JMH</span></a> <a href="https://mastodon.social/tags/Performance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Performance</span></a> <a href="https://mastodon.social/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSource</span></a></p>
Miguel Afonso Caetano<p>"Bluntly, the Y-axis simply doesn’t make much sense. And needless to say, if the Y-axis doesn’t make sense, you can’t meaningfully use the graph to make predictions. Computers can answer some questions reliably now, for example, and some not, and the graph tells us nothing about which is which or when any specific question will be solved. Or consider songwriting; Dylan wrote some in an afternoon; Leonard Cohen took half a decade on and off to write Hallelujah. Should we average the two figures? Should we sample Dylan songs more heavily because he wrote more of them? Where should songwriting go on the figure? The whole thing strikes us as absurd.</p><p>Finally, the only thing METR looked at was “software tasks”. Software might be very different from other domains, in which case the graph (even it did make sense) might not apply. In the technical paper, the authors actually get this right: they discuss carefully the possibility that the tasks used for testing might not be representative of real-world software engineering tasks. They certainly don't claim that the findings of the paper apply to tasks in general. But the social media posts make that unwarranted leap.</p><p>That giant leap seems especially unwarranted given that there has likely been a lot of recent data augmentation directed towards software benchmarks in particular (where this is feasible). In other domains where direct, verifiable augmentation is less feasible, results might be quite different. (Witness the failed letter ‘r’ labeling task depicted above.) Unfortunately, literally none of the tweets we saw even considered the possibility that a problematic graph specific to software tasks might not generalize to literally all other aspects of cognition.</p><p>We can only shake our heads."</p><p><a href="https://garymarcus.substack.com/p/the-latest-ai-scaling-graph-and-why" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">garymarcus.substack.com/p/the-</span><span class="invisible">latest-ai-scaling-graph-and-why</span></a></p><p><a href="https://tldr.nettime.org/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://tldr.nettime.org/tags/GenerativeAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GenerativeAI</span></a> <a href="https://tldr.nettime.org/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLMs</span></a> <a href="https://tldr.nettime.org/tags/Chatbots" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Chatbots</span></a> <a href="https://tldr.nettime.org/tags/Automation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Automation</span></a> <a href="https://tldr.nettime.org/tags/Benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Benchmarks</span></a> <a href="https://tldr.nettime.org/tags/SoftwareDevelopment" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SoftwareDevelopment</span></a> <a href="https://tldr.nettime.org/tags/Programming" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Programming</span></a> <a href="https://tldr.nettime.org/tags/AIHype" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AIHype</span></a></p>
ResearchBuzz: Firehose<p>Gizmodo: Meta Cheated on AI Benchmarks and It’s a Glimpse Into a New Golden Age. “They dropped a whole bunch of highly technical data to brag about how Meta’s AI was smarter and more efficient than models from companies better associated with AI: Google, OpenAI, and Anthropic. These release posts are always mired in deeply technical data and benchmarks that are hugely beneficial to […]</p><p><a href="https://rbfirehose.com/2025/04/13/gizmodo-meta-cheated-on-ai-benchmarks-and-its-a-glimpse-into-a-new-golden-age/" class="" rel="nofollow noopener" target="_blank">https://rbfirehose.com/2025/04/13/gizmodo-meta-cheated-on-ai-benchmarks-and-its-a-glimpse-into-a-new-golden-age/</a></p>
Nicole Hennig<p>Announcing the OpenAI Pioneers Program <a href="https://openai.com/index/openai-pioneers-program/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">openai.com/index/openai-pionee</span><span class="invisible">rs-program/</span></a> <a href="https://techhub.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://techhub.social/tags/evals" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>evals</span></a> <a href="https://techhub.social/tags/benchmarks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>benchmarks</span></a></p>