April 2025 - cypherpunks - lists.cpunks.org

Re: [spam][crazy][fiction][random] Non-Canon MCBoss Spinoffs
by karl3＠writeme.com 03 Apr '25

03 Apr '25

> $ ./diff_xdiff > diff_main: Null case. > WINDOW RESIZE0=>2 > consuming rec ptr 0x7f966b000a00 > consuming rec ptr 0x502000000250 > WINDOW RESIZE2=>4 > consuming rec ptr 0x7f966b000a02 > WINDOW RESIZE4=>8 > consuming rec ptr 0x7f966b000a04 > diff_main: Equality. > diff_xdiff: diff_xdiff.cpp:1047: void {anonymous}::assertEquals(const char*, std::vector<Diff>&, const std::vector<Diff>&): Assertion `std::equal(expected.begin(),expected.end(),actual.begin(),actual.end()) || std::equal(alternative.begin(),alternative.end(),actual.begin(),actual.end())' failed. > Aborted ok chatgpt and traffick boss :s isn't it weird that it consumes three pointers to the file buffer and only one pointer to the stream window buffer? that's not the right behavior! lemme get you the stack trace from that error (gdb) bt #0 __pthread_kill_implementation (threadid=<optimized out>, signo=signo@entry=6, no_tid=no_tid@entry=0) at ./nptl/pthread_kill.c:44 #1 0x00007ffff6a9de2f in __pthread_kill_internal (threadid=<optimized out>, signo=6) at ./nptl/pthread_kill.c:78 #2 0x00007ffff6a49d02 in __GI_raise (sig=sig@entry=6) at ../sysdeps/posix/raise.c:26 #3 0x00007ffff6a324f0 in __GI_abort () at ./stdlib/abort.c:79 #4 0x00007ffff6a32418 in __assert_fail_base (fmt=0x7ffff6bb6ca0 "%s%s%s:%u: %s%sAssertion `%s' failed.\n%n", assertion=assertion@entry=0x555555691480 "std::equal(expected.begin(),expected.end(),actual.begin(),actual.end()) || std::equal(alternative.begin(),alternative.end(),actual.begin(),actual.end())", file=file@entry=0x55555568fa40 "diff_xdiff.cpp", line=line@entry=1047, function=function@entry=0x555555691400 "void {anonymous}::assertEquals(const char*, std::vector<Diff>&, const std::vector<Diff>&)") at ./assert/assert.c:96 #5 0x00007ffff6a42612 in __assert_fail ( assertion=0x555555691480 "std::equal(expected.begin(),expected.end(),actual.begin(),actual.end()) || std::equal(alternative.begin(),alternative.end(),actual.begin(),actual.end())", file=0x55555568fa40 "diff_xdiff.cpp", line=1047, function=0x555555691400 "void {anonymous}::assertEquals(const char*, std::vector<Diff>&, const std::vector<Diff>&)") at ./assert/assert.c:105 #6 0x00005555556171e3 in (anonymous namespace)::assertEquals (desc=0x5555556922e0 "diff_main: Equality.", expected=std::vector of length 1, capacity 1 = {...}, actual=std::vector of length 3, capacity 4 = {...}) at diff_xdiff.cpp:1047 #7 0x00005555556184bd in test_diff_xdiff () at diff_xdiff.cpp:1065 #8 0x000055555561f929 in main () at diff_xdiff.cpp:1102 and now check out the variables in the failed assertion (gdb) up 6 #6 0x00005555556171e3 in (anonymous namespace)::assertEquals (desc=0x5555556922e0 "diff_main: Equality.", expected=std::vector of length 1, capacity 1 = {...}, actual=std::vector of length 3, capacity 4 = {...}) at diff_xdiff.cpp:1047 1047 assert(std::equal(expected.begin(),expected.end(),actual.begin(),actual.end()) || std::equal(alternative.begin(),alternative.end(),actual.begin(),actual.end())); (gdb) p expected $1 = std::vector of length 1, capacity 1 = {{type = EQUAL, text = "abc"}} (gdb) p equal $2 = equal # oops here i output the wrong word (gdb) p actual $3 = std::vector of length 3, capacity 4 = {{type = EQUAL, text = "a"}, {type = DELETE, text = "bc"}, {type = INSERT, text = "bc"}} actual has the wrong content. expected is what it should have. after the first character, it started making weird diffs 💁 ! maybe how things change after the first thing is related to the extra consumed pointers !

3 408

Re: Morning Spam
by Undescribed Horrific Abuse, One Victim & Survivor of Many 03 Apr '25

03 Apr '25

> partial nice idea! sad that only partial >>> >>> the idea starts with context: some of us have the experience of being >>> manipulated by something like AI without regard to our wellbeing or >>> capacity, with no indication of how to communicate with where-ever the >>> influence comes from. >>> >>> so, then the idea: let’s train an influence AI on agents that have >>> _limited capacity_ and function poorly and then break if things that work >>> some in the short term are continued for the long term or excessively :D >>> >>> the AI would follow the familiar pattern of discovering influences that >>> work, and then using them, but then because we are doing the training we >>> would get to train it on the breaking period, and show it that it needs to >>> care for the agents for them to succeed, and nurture them to recover if it >>> broke them, and not repeat breaking any. >>> >>> one idea is then we could ask everybody to use the model as a baseline >>> to train other models! other ideas exist. >>> >>> but the idea of building comprehension of capacity and protection of >>> safety and wellness seems nice. sorry if it’s partial or stated badly :s >>> >>> i imagine an agent that has like a secret capacity float that reduces >>> when it does stuff, you could model it to different degrees, and when too >>> many things are influenced of it the capacity float reaches zero and the >>> agent breaks and can’t do things any more :/ >>> >>> a more complex model could involve the agent recovering capacity in ways >>> that the model has difficulty learning >>> >> >> there are a few ideas, mostly involving simple models, but disagreement >> around them. >> some like modeling non-recovering capacity and showing how the AI then >> maximizes reward by killing all the agents :s >> > > but! maybe we could do non-recovering capacity and teach the AI to engage > the agents slowly so their capacity lasts longer, by e.g. having the > capacity reduction be a function of recent use?? the project would need to > gently develop in order to help us in the long term, we’d need to include > the concept that we can succeed so that we use it to succeed in some > manner. because it’s an influence AI it could influence us, if it is > something we actually all like doing that. > mistake :/ some of my parts are maybe harmful to me and should be separated from helpful goals, unknown for certain >

3 147

Hooters Can Tap $5M Of Its $40M In Proposed Ch. 11 Loans
by Gunnar Larson 03 Apr '25

03 Apr '25

Hooters Can Tap $5M Of Its $40M In Proposed Ch. 11 Loans <https://www.law360.com/mergersacquisitions/articles/2320291?nl_pk=34b724c6-…> By Emily Lever Bankrupt restaurant chain Hooters of America LLC can access $5 million in interim financing from a $40 million debtor-in-possession package from its prepetition lenders as it transitions to a franchise-only model, a Texas bankruptcy judge said Wednesday. Petition attached | Read full article » <https://www.law360.com/mergersacquisitions/articles/2320291?nl_pk=34b724c6-…> | Save to favorites » <https://www.law360.com/mergersacquisitions/articles/2320291?nl_pk=34b724c6-…>

1 0

Justices Broaden RICO Reach To Personal Injuries
by Gunnar Larson 03 Apr '25

03 Apr '25

Justices Broaden RICO Reach To Personal Injuries <https://www.law360.com/cannabis/articles/2264334?nl_pk=a981d81f-1a94-4659-8…> By Sam Reisman The U.S. Supreme Court on Wednesday expanded the type of civil actions that can be brought under a federal racketeering statute, asserting that claims stemming from personal injuries are redressable if they can be shown to have caused economic harm. Opinion attached | Read full article » <https://www.law360.com/cannabis/articles/2264334?nl_pk=a981d81f-1a94-4659-8…> | Save to favorites » <https://www.law360.com/cannabis/articles/2264334?nl_pk=a981d81f-1a94-4659-8…>

1 0

'Snow White' Email Shows Staley's Ties To Epstein, FCA Says
by Gunnar Larson 03 Apr '25

03 Apr '25

'Snow White' Email Shows Staley's Ties To Epstein, FCA Says <https://www.law360.co.uk/financial-services-uk/articles/2319863?nl_pk=9aaa8…> By Christopher Crosby The inability of former Barclays boss Jes Staley to remember "now infamous" emails with Jeffrey Epstein undermines his credibility and his attempts to overturn his ban for lying about his ties to the sex offender, the Financial Conduct Authority said Wednesday. Read full article » <https://www.law360.co.uk/financial-services-uk/articles/2319863?nl_pk=9aaa8…> | Save to favorites » <https://www.law360.co.uk/financial-services-uk/articles/2319863?nl_pk=9aaa8…>

1 0

Watch "Azizam (pink heart video) out tomorrow, so excited. Official video comes in a few weeks, inabit x" on YouTube
by Gunnar Larson 03 Apr '25

03 Apr '25

https://youtube.com/shorts/0_jiyXspuzM?si=mEgk7eoIUQpkRbwP Watch "Azizam (pink heart video) out tomorrow, so excited. Official video comes in a few weeks, inabit x" on YouTube

1 0

Watch "President Trump Signs Executive Orders Imposing Tariffs" on YouTube https://youtu.be/z3OxZOEbDwQ?si=bgQopXj0CSUTalfA
by Gunnar Larson 03 Apr '25

03 Apr '25

https://youtu.be/z3OxZOEbDwQ? si=bgQopXj0CSUTalfA President Trump signs executive orders imposing sweeping tariffs on U.S. trading partners.

1 0

Australia! I can’t wait to see you in November! https://www.facebook.com/share/r/12AHysPZFZq/
by Gunnar Larson 03 Apr '25

03 Apr '25

https://www.facebook.com/share/r/12AHysPZFZq/ Australia! I can’t wait to see you in November!

1 0

Fwd: A Better and Stronger New York City.mov
by Gunnar Larson 03 Apr '25

03 Apr '25

---------- Forwarded message --------- From: Anonymousemail <noreply(a)anonymousemail.eu> Date: Thu, Apr 3, 2025, 1:17 PM Subject: A Better and Stronger New York City.mov To: <G(a)xny.io> Powered by *Anonymousemail* https://www.dropbox.com/scl/fi/1q8fsnvv41208zjw6jxfz/MEA-2.mov?rlkey=u6hxzn…

1 0

Watch ""We should always preserve the element of surprise."" on YouTube
by Gunnar Larson 03 Apr '25

03 Apr '25

https://youtu.be/7ux32riSIBU?si=_4GTJzzRYi8YXg_x Joint Chiefs of Staff Chair nominee Lt. Gen. Dan Caine (ret.) on Signal group chat: "That was a partisan political chat, so the joint force should not have been represented in there...We should always preserve the element of surprise."

1 0