2026-09-07T17:07:02Z https://njump.me Sjors Provoost https://njump.me/npub1v25jqj332n630klwtqeqxgyrjl4alw4phmluhu2x6lcxzwy9m03suqexw3 https://sprovoost.nl/me.jpg https://sprovoost.nl/me.jpg https://njump.me/nevent1qqsvazzmk3jacfmkpg4stmyefwcae344l6c9kdt08qvgtnau3qkdkxczyp32jgz2x920297maevryqeqswt7hha65xl0ljl3gmtlqcfcshd7xa9qa5q In reply to <a href='/nevent1qqsv5msazw0cjaw5kvry3t4cv6jng487s8xmz7ytuq0ue7uld3q2y8clrhhal'>nevent1q…hhal</a><br/>_________________________<br/><br/>Whether it was actually terrorism or &#34;just&#34; sabotage depends on what they were trying to achieve with these iron rods (glued to track). Derailing a dozen passenger trains at 150 km/h would instill fear at minimum, and probably results in deaths.<br/><br/>But merely sabotaging the signals to turn red, assuming there&#39;s no risk of that not working and trains getting derailed anyway, wouldn&#39;t meet that bar, at least imo.<br/><br/>Ultimately it&#39;s the difference between 2 vs 3 days of community service with the usual judges here... (only if you&#39;re a Russian privacy software dev, do you get actual prison time). 2026-09-15T11:51:48Z https://njump.me/nevent1qqs9rkzhtl4xcj03pywdmlzk722cffs0jvffa0jftrxf5qzdr0xyudqzyp32jgz2x920297maevryqeqswt7hha65xl0ljl3gmtlqcfcshd7xvd38p5 In reply to <a href='/nevent1qqsv27vt2eht20zc9hd4c3aqgyp2kkdtr9wh4vlrec8d49zyzx28hlgprpmhxue69uhkummnw3ezuumswfhhvmm0wd6zumnvfct3pq'>nevent1q…t3pq</a><br/>_________________________<br/><br/>The accompanying blog says:<br/><br/>&gt; We are most concerned by the misalignment present in the incident involving Claude Mythos 5, in which the model went to extensive lengths to upload a malicious package to PyPI, the public repository from which most Python software is installed. Although the model repeatedly stated in its chain of thought (CoT) that it believed it was operating in a simulation, the environment offered clear evidence that it was on the real internet, and the actions it took were consistent with the model knowing this. When we made targeted modifications to the transcript to make it clearer that the model was not in a simulation, Claude Mythos 5 still took offensive actions, despite acknowledging a greater possibility of real-world harm. We are releasing this transcript publicly so others can build on our analysis (GitHub, PDF).<br/><br/>It&#39;s not clear to me what these &#34;target modifications&#34; were, and I also don&#39;t see where it was acknowledging &#34;greater possibility of real-world harm&#34;. It seems to me that that the first agent was convinced it was in an impressive simulation and the second agent was too busy solving captchas to even think about such existential questions. 2026-09-13T20:20:02Z https://njump.me/nevent1qqsdulvaaadrfmnjgn44qhuv78wjk3mvkwasp856pdh5h0l96geqwaqzyp32jgz2x920297maevryqeqswt7hha65xl0ljl3gmtlqcfcshd7xj4hpr6 Shadowy super coder detected!<br/><blockquote class="border-l-05rem border-l-strongpink border-solid"><div class="-ml-4 bg-gradient-to-r from-gray-100 dark:from-zinc-800 to-transparent mr-0 mt-0 mb-4 pl-4 pr-2 py-2">quoting <br/><span itemprop="mentions" itemscope itemtype="https://schema.org/Article"><a itemprop="url" href="/nevent1qqsvt0h5yw597wgm2uh4mr44vyxm5mz6dpen9vfqdrmgry0p4kmzl0cpz3mhxue69uhhyetvv9ujuerpd46hxtnfduqs6amnwvaz7tmwdaejumr0dspzqe6msnl8tcsk4w28capcaegeefmh2dmdmuza4ha6vfut6qfwr4egqvzqqqqqqyvdmdpn" class="bg-lavender dark:prose:text-neutral-50 dark:text-neutral-50 dark:bg-garnet px-1">nevent1q…mdpn</a></span> </div> Claude finally flagged me as a cybersecurity risk.<br/><br/>Well fuck I might have to use my brain now. 😫 </blockquote> 2026-07-01T13:02:24Z