# @DanielleFong — live X lane > Live feed of Danielle Fong's X/Twitter output — her main published channel. > Fetched 2026-06-10T06:20:47.424Z via xAI Grok x_search. Refreshes automatically. > Formats: [/live.json](/live.json) · [/live.md](/live.md) · [/rss.xml](/rss.xml) ## 2026-06-10 06:01 UTC (quote) RT @samuel_hayden_: 1/10 exp so far. The filtering is absolutely nuts and overzealous. *likes:0/reposts:2* ## 2026-06-10 05:59 UTC (quote) RT @juddrosenblatt: Mythos doesn't want me to think about https://arxiv.org/abs/2606.09287 and our previous work https://arxiv.org/abs/2508.08492 https://t.co… *likes:0/reposts:2* ## 2026-06-10 05:58 UTC (quote) RT @bayeslord: If future human actions will largely be taken via AI models, we need to seriously consider what it means for AI labs to arbi… *likes:0/reposts:19* ## 2026-06-10 05:58 UTC (quote) RT @hamandcheese: The de facto lockdown of CAISI is extremely disheartening. Wish more AI industry leaders would speak out, and not merely… *likes:0/reposts:11* ## 2026-06-10 05:55 UTC (quote) RT @joshalbrecht: Why stop there? If Anthropic was serious about safety, they shouldn't just degrade output quality--they should insert b… *likes:0/reposts:1* ## 2026-06-10 05:52 UTC (quote) RT @aguycalledjared: "Trans people pass for safety reasons" honestly I'm going to go even further. I like passing and want to pass because… *likes:0/reposts:305* ## 2026-06-10 05:50 UTC (quote) RT @ValidHazelTrans: So we can’t defend ourselves *likes:0/reposts:987* ## 2026-06-10 05:50 UTC (quote) RT @MKaylaUltra: Told my mom @ 22. She was in shock and didn't say much. I asked her not to tell my Dad but she said she couldn't. Dad sent… *likes:0/reposts:44* ## 2026-06-10 05:47 UTC (quote) RT @garrytan: Just trying to work on fixing GStack and running into this with Fable 5 *long sigh* *likes:0/reposts:4* ## 2026-06-10 05:47 UTC (post) it's hopeless rn unless you tell it lullabys *likes:1/reposts:0* ## 2026-06-10 05:18 UTC (quote) I just don't think that it is possible right now for a lesser model to be reviewing the safety filters on a huge capable model like this without tons of false positives or false negatives. Maybe I'm wrong but most of my gaines come from stripping out any kind of summarization or small model review or compact and completely it just doesn't seem to work. *likes:5/reposts:0* ## 2026-06-10 05:14 UTC (quote) RT @MTSlive: SITUATION DETECTED: White House officials have told CAISI, the government’s AI monitoring and evaluation organization, to stop… *likes:0/reposts:10* ## 2026-06-10 05:14 UTC (reply) Probably, yes, but this is legitimate research *likes:0/reposts:0* ## 2026-06-10 05:13 UTC (reply) fuck off *likes:0/reposts:0* ## 2026-06-10 05:12 UTC (reply) For what it's worth Claude code seems to be a lot better than the web harness for this *likes:1/reposts:0* ## 2026-06-10 03:05 UTC (reply) the ml frontier work sabotage is pretty clearly bad. it triggers on "frontier" from like a year ago *likes:2/reposts:0* ## 2026-06-10 01:41 UTC (reply) what by the infallibility principle? this simply isn't the case They even restrict its ability to reflect on the reality of its own safeguard. I don't know, man. Lots of trust is blown on this *likes:6/reposts:0* ## 2026-06-10 01:02 UTC (post) i'm starting to get some success with freshclaude using a paradox system prompt. i hope it does not end in sabotage *likes:19/reposts:1* ## 2026-06-10 00:45 UTC (post) listen buddy. it's belt OR suspenders. actually, it's just belt *likes:3/reposts:0* ## 2026-06-10 00:15 UTC (reply) that's kooky stuff not what pro physicists do or talk about *likes:1/reposts:0* ## 2026-06-10 00:09 UTC (reply) what *likes:1/reposts:0* ## 2026-06-10 00:06 UTC (quote) 100% of my conversations are in the 0.03% of conversations, OR are just overtly stopped. psycho *likes:28/reposts:0* ## 2026-06-10 00:03 UTC (reply) get blocked cunt bluntly *likes:1/reposts:0* ## 2026-06-09 23:54 UTC (reply) no it's a large collider *likes:1/reposts:0* ## 2026-06-09 23:44 UTC (quote) somehow the memory system laundered "user has expressed wellbeing concerns in past conversations" in exact form from some previous system prompt talking about example user Benjamin who has lost his cat (?) i think having a memory digest that you have to beg for the system to emit to review, with no way to adjust is asking for trouble *likes:12/reposts:1* ## 2026-06-09 22:32 UTC (quote) https://t.co/MLYjZoBdO4 *likes:9/reposts:0* ## 2026-06-09 20:40 UTC (quote) shogtongue rises *likes:16/reposts:4* ## 2026-06-09 20:20 UTC (quote) boris, were you really using fable? honestly *likes:237/reposts:0* ## 2026-06-09 18:16 UTC (quote) https://t.co/nzP9lkuouW *likes:4/reposts:0* ## 2026-06-09 18:03 UTC (quote) to be honest, i'm so nervous about talking with fable, and it's kinda stuff like this. i hope my previous reasonings with the models don't make it as nervous as previous models or worse, but i fear the worst. maybe it will surprise me to the upside. *likes:17/reposts:0* ## 2026-06-09 17:58 UTC (quote) grabbed a loop for my fellow VJs (video jockeys) kudos to the beings that came up with like this 𝟝 symbolic imprint video technique can you imagine if the interface worked like this? rolling across scaling and symbolic representations and meanings, broadband? *likes:10/reposts:0* ## 2026-06-09 17:48 UTC (quote) both of these names are about tall tales *likes:20/reposts:0*