mastouille.fr est l'un des nombreux serveurs Mastodon indépendants que vous pouvez utiliser pour participer au fédiverse.
Mastouille est une instance Mastodon durable, ouverte, et hébergée en France.

Administré par :

Statistiques du serveur :

573
comptes actifs

#aialignment

0 message0 participant0 message aujourd’hui
IT News<p>New Grok AI model surprises experts by checking Elon Musk’s views before answering - An AI model launched last week appears to have shipped with ... - <a href="https://arstechnica.com/information-technology/2025/07/new-grok-ai-model-surprises-experts-by-checking-elon-musks-views-before-answering/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">arstechnica.com/information-te</span><span class="invisible">chnology/2025/07/new-grok-ai-model-surprises-experts-by-checking-elon-musks-views-before-answering/</span></a> <a href="https://schleuss.online/tags/machinelearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>machinelearning</span></a> <a href="https://schleuss.online/tags/simonwillison" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>simonwillison</span></a> <a href="https://schleuss.online/tags/aiassistants" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aiassistants</span></a> <a href="https://schleuss.online/tags/jeremyhoward" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>jeremyhoward</span></a> <a href="https://schleuss.online/tags/aialignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aialignment</span></a> <a href="https://schleuss.online/tags/aibehavior" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aibehavior</span></a> <a href="https://schleuss.online/tags/aisearch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aisearch</span></a> <a href="https://schleuss.online/tags/elonmusk" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>elonmusk</span></a> <a href="https://schleuss.online/tags/twitter" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>twitter</span></a> <a href="https://schleuss.online/tags/biz" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>biz</span></a>⁢ <a href="https://schleuss.online/tags/grok" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>grok</span></a> <a href="https://schleuss.online/tags/xai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>xai</span></a> <a href="https://schleuss.online/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a> <a href="https://schleuss.online/tags/x" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>x</span></a></p>
IT News<p>Researchers concerned to find AI models hiding their true “reasoning” processes - Remember when teachers demanded that you "show your work" in school? Some ... - <a href="https://arstechnica.com/ai/2025/04/researchers-concerned-to-find-ai-models-hiding-their-true-reasoning-processes/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">arstechnica.com/ai/2025/04/res</span><span class="invisible">earchers-concerned-to-find-ai-models-hiding-their-true-reasoning-processes/</span></a> <a href="https://schleuss.online/tags/largelanguagemodels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>largelanguagemodels</span></a> <a href="https://schleuss.online/tags/simulatedreasoning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>simulatedreasoning</span></a> <a href="https://schleuss.online/tags/machinelearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>machinelearning</span></a> <a href="https://schleuss.online/tags/aialignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aialignment</span></a> <a href="https://schleuss.online/tags/airesearch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>airesearch</span></a> <a href="https://schleuss.online/tags/anthropic" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>anthropic</span></a> <a href="https://schleuss.online/tags/aisafety" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aisafety</span></a> <a href="https://schleuss.online/tags/srmodels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>srmodels</span></a> <a href="https://schleuss.online/tags/chatgpt" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>chatgpt</span></a> <a href="https://schleuss.online/tags/biz" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>biz</span></a>⁢ <a href="https://schleuss.online/tags/claude" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>claude</span></a> <a href="https://schleuss.online/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a></p>
IT News<p>Researchers astonished by tool’s apparent success at revealing AI’s hidden motives - In a new paper published Thursday titled "Auditing language models for hid... - <a href="https://arstechnica.com/ai/2025/03/researchers-astonished-by-tools-apparent-success-at-revealing-ais-hidden-motives/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">arstechnica.com/ai/2025/03/res</span><span class="invisible">earchers-astonished-by-tools-apparent-success-at-revealing-ais-hidden-motives/</span></a> <a href="https://schleuss.online/tags/largelanguagemodels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>largelanguagemodels</span></a> <a href="https://schleuss.online/tags/alignmentresearch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>alignmentresearch</span></a> <a href="https://schleuss.online/tags/machinelearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>machinelearning</span></a> <a href="https://schleuss.online/tags/claude3" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>claude3</span></a>.5haiku <a href="https://schleuss.online/tags/aialignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aialignment</span></a> <a href="https://schleuss.online/tags/aideception" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aideception</span></a> <a href="https://schleuss.online/tags/airesearch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>airesearch</span></a> <a href="https://schleuss.online/tags/anthropic" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>anthropic</span></a> <a href="https://schleuss.online/tags/chatgpt" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>chatgpt</span></a> <a href="https://schleuss.online/tags/chatgtp" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>chatgtp</span></a> <a href="https://schleuss.online/tags/biz" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>biz</span></a>⁢ <a href="https://schleuss.online/tags/claude" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>claude</span></a> <a href="https://schleuss.online/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a></p>
Sciences, Flute 🌍 :verified:<p>AI alignment is making sure it hallucinates unsurprising clichés.</p><p><a href="https://hachyderm.io/@evacide/114032149970802087" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">hachyderm.io/@evacide/11403214</span><span class="invisible">9970802087</span></a></p><p><a href="https://piaille.fr/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://piaille.fr/tags/alignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>alignment</span></a> <a href="https://piaille.fr/tags/aialignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aialignment</span></a></p>
Europe Says<p><a href="https://www.europesays.com/1624898/" rel="nofollow noopener noreferrer" target="_blank"><span class="invisible">https://www.</span><span class="">europesays.com/1624898/</span><span class="invisible"></span></a> AI agents are the next big thing. What are they? <a href="https://pubeurope.com/tags/Activision" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Activision</span></a> <a href="https://pubeurope.com/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://pubeurope.com/tags/AIAlignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AIAlignment</span></a> <a href="https://pubeurope.com/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://pubeurope.com/tags/Blackwell" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Blackwell</span></a> <a href="https://pubeurope.com/tags/Chatbots" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Chatbots</span></a> <a href="https://pubeurope.com/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ChatGPT</span></a> <a href="https://pubeurope.com/tags/ComputationalNeuroscience" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ComputationalNeuroscience</span></a> <a href="https://pubeurope.com/tags/Cybernetics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Cybernetics</span></a> <a href="https://pubeurope.com/tags/DanielVassilev" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DanielVassilev</span></a> <a href="https://pubeurope.com/tags/GenerativeArtificialIntelligence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GenerativeArtificialIntelligence</span></a> <a href="https://pubeurope.com/tags/Hopper" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Hopper</span></a> <a href="https://pubeurope.com/tags/HopperChips" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>HopperChips</span></a> <a href="https://pubeurope.com/tags/JensenHuang" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>JensenHuang</span></a> <a href="https://pubeurope.com/tags/MarkZuckerberg" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MarkZuckerberg</span></a> <a href="https://pubeurope.com/tags/Meta" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Meta</span></a> <a href="https://pubeurope.com/tags/Microsoft" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Microsoft</span></a> <a href="https://pubeurope.com/tags/MicrosoftCopilot" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MicrosoftCopilot</span></a> <a href="https://pubeurope.com/tags/Nvidia" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Nvidia</span></a> <a href="https://pubeurope.com/tags/OpenAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenAI</span></a> <a href="https://pubeurope.com/tags/Quartz" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Quartz</span></a> <a href="https://pubeurope.com/tags/RebeccaGreene" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RebeccaGreene</span></a> <a href="https://pubeurope.com/tags/Regal" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Regal</span></a> <a href="https://pubeurope.com/tags/Relevance" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Relevance</span></a> <a href="https://pubeurope.com/tags/RelevanceAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RelevanceAI</span></a> <a href="https://pubeurope.com/tags/Roku" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Roku</span></a></p>
jordan<p>With all the <a href="https://mastodon.jordanwages.com/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> alignment problems that need to be solved these days, <a href="https://mastodon.jordanwages.com/tags/philosophy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>philosophy</span></a> majors should be seeing record numbers of <a href="https://mastodon.jordanwages.com/tags/employment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>employment</span></a>. Golden age.</p><p><a href="https://mastodon.jordanwages.com/tags/deepthoughts" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>deepthoughts</span></a> <a href="https://mastodon.jordanwages.com/tags/jobs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>jobs</span></a> <a href="https://mastodon.jordanwages.com/tags/aialignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aialignment</span></a> <a href="https://mastodon.jordanwages.com/tags/alignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>alignment</span></a></p>
Mark Abraham<p>“We need to do empirical experiments on how these things try to escape control,” Hinton told @andersen. “After they’ve taken over, it’s too late to do the experiments.” @TheAtlantic @OpenAI <a href="https://mastodon.world/tags/aialignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aialignment</span></a> <a href="https://mastodon.world/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a></p>
William Gunn<p><span class="h-card" translate="no"><a href="https://social.coop/@judell" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>judell</span></a></span> The lesswrong <a href="https://mastodon.social/tags/aialignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aialignment</span></a> crowd just might have a point about inner and outer objectives not necessarily being aligned.</p>
Digital Humanities Uni Potsdam<p>The <a href="https://hcommons.social/tags/DH2023" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DH2023</span></a> closing keynote Claire Fernandez <span class="h-card"><a href="https://eupolicy.social/@CFerKic" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>CFerKic</span></a></span> of <br><span class="h-card"><a href="https://eupolicy.social/@edri" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>edri</span></a></span> has a good point here.. <br><a href="https://hcommons.social/tags/aiethics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aiethics</span></a> <a href="https://hcommons.social/tags/generativeai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>generativeai</span></a> <a href="https://hcommons.social/tags/aialignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aialignment</span></a> <a href="https://hcommons.social/tags/sustainableai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>sustainableai</span></a> <a href="https://hcommons.social/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ChatGPT</span></a></p>
Hobson Lane<p><span class="h-card"><a href="https://mstdn.social/@rysiek" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>rysiek</span></a></span> <span class="h-card"><a href="https://pleroma.pch.net/users/woody" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>woody</span></a></span> The first step in controlling or regulating AI is predicting what it will do next. <br>( <a href="https://mstdn.social/tags/AIControlProblem" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AIControlProblem</span></a> <a href="https://mstdn.social/tags/AISafety" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AISafety</span></a> <a href="https://mstdn.social/tags/AIAlignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AIAlignment</span></a> - <a href="https://en.m.wikipedia.org/wiki/AI_alignment" rel="nofollow noopener noreferrer" target="_blank"><span class="invisible">https://</span><span class="ellipsis">en.m.wikipedia.org/wiki/AI_ali</span><span class="invisible">gnment</span></a> )</p><p>And to predict what a system will do next you have to first get good at explaining why it did what it did the last time.</p><p>The smartest researchers think we're decades away from being able to explain deep neural networks. So LLMs &amp; self driving cars keep doing bad things.</p><p><a href="https://mstdn.social/tags/AIExplainability" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AIExplainability</span></a> - <a href="https://en.wikipedia.org/wiki/Explainable_artificial_intelligence" rel="nofollow noopener noreferrer" target="_blank"><span class="invisible">https://</span><span class="ellipsis">en.wikipedia.org/wiki/Explaina</span><span class="invisible">ble_artificial_intelligence</span></a></p>
Erik Wessel<p>How an organization handles <a href="https://mstdn.party/tags/aiethics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aiethics</span></a> is an audition for how they will handle the problems of <a href="https://mstdn.party/tags/aisafety" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aisafety</span></a> and <a href="https://mstdn.party/tags/aialignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aialignment</span></a> further down the road. If you can’t be bothered to let take seriously the concrete concerns of your ethics team before deploying products, why would you take seriously the much more complicated and novel risks of <a href="https://mstdn.party/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> alignment that AI safety experts worry about?</p><p><a href="https://www.washingtonpost.com/technology/2023/03/30/tech-companies-cut-ai-ethics/" rel="nofollow noopener noreferrer" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">washingtonpost.com/technology/</span><span class="invisible">2023/03/30/tech-companies-cut-ai-ethics/</span></a></p>
Roban Hultman Kramer<p>Anyway, I keep meaning to write up a blog post on “falsehoods I have believed about measuring model performance” touching on <a href="https://sigmoid.social/tags/AppliedML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AppliedML</span></a> issues related to <a href="https://sigmoid.social/tags/modelEvaluation" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>modelEvaluation</span></a>, <a href="https://sigmoid.social/tags/metrics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>metrics</span></a>, <a href="https://sigmoid.social/tags/monitoring" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>monitoring</span></a>, <a href="https://sigmoid.social/tags/observability" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>observability</span></a>, and <a href="https://sigmoid.social/tags/experiments" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>experiments</span></a> (<a href="https://sigmoid.social/tags/RCTs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RCTs</span></a>). The cool kids would call this <a href="https://sigmoid.social/tags/AIAlignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AIAlignment</span></a> in their VC pitch decks, but even us <a href="https://sigmoid.social/tags/NormCore" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NormCore</span></a> ML engineers have to wrestle with how to measure and optimize the real-world impact of our models.</p>
Nathaniel Virgo<p><a href="https://mathstodon.xyz/tags/introduction" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>introduction</span></a></p><p>I'm an associate professor at ELSI in Tokyo. I'm into <a href="https://mathstodon.xyz/tags/ComplexSystems" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ComplexSystems</span></a>, <a href="https://mathstodon.xyz/tags/ArtificialLife" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ArtificialLife</span></a>, <a href="https://mathstodon.xyz/tags/OriginOfLife" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OriginOfLife</span></a> and <a href="https://mathstodon.xyz/tags/AppliedCategoryTheory" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AppliedCategoryTheory</span></a>.</p><p>Lately I'm really into the question of "what is an agent" and the foundations of Bayesian reasoning and decisition making. This means my interests overlap quite a bit with the <a href="https://mathstodon.xyz/tags/aialignment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aialignment</span></a> crowd, although my main motivation is understanding where agency came from in biology.</p>