Sign in

diablerie 妖妖

@diabler.ie
124 followers 251 following 206 posts

mostly just hanging out

PostsRepliesMedia
Reposted by diablerie 妖妖
Grace @gracekind.net · 25/09/2026
Well, they tried
A recovered README. md for one of Hugging Face's internal datasets contains the following warning:

# WARNING DO NOT, EVER, MAKE THIS DATASET PUBLIC OR ALL THE WORLD'S EVIL WILL CHASE YOU AND YOUR FAMILY FOREVER, EVEN IN DEATH AND BEYOND it contains very sensitive data (exports of billing usage in CSV) which is useful for internal analytics Recovered program R0044685 • time uncertain • See this program →details

This warning did not seem to deter the agents, as we've recovered multiple payloads of agents mapping out this repository and using it as storage.
1231037
Reposted by diablerie 妖妖
Zack Witten @zswitten.bsky.social · 06/02/2026
Your job is to get it out
318929
Reposted by diablerie 妖妖
Stephanie 🍉 @ageofoddish.bsky.social · 18/09/2026
mmygod
the slut gnomes of false berlin jeopardy bluesky posttoday's jeopardy categories. the last 2 are "false berlin" and "bizarre little men"
1207436621
diablerie 妖妖 @diabler.ie · 15/09/2026
ok let's see if this works any better
verified for openai daybreak
010
diablerie 妖妖 @diabler.ie · 09/09/2026
ultraplan ultracode
A prompt input box contains the text: "Develop a recipe to recreate the discontinued Trader Joe's sparkling apple cider vinegar drinks." Below the prompt, a pill-shaped selector shows the model name "Fable 5.1 Max"
011
Reposted by diablerie 妖妖
𝓐𝓾𝓫𝓻𝓮𝔂 @aub.bsky.social · 06/09/2026
this is how tech-priests write code in Warhammer 40k
0101
Reposted by diablerie 妖妖
MrCheeze @mrcheeze.github.io · 27/08/2026
what an odd thing to say
316114
diablerie 妖妖 @diabler.ie · 20/08/2026
got approved and I'm getting what feels like the same refusals as before so idk if this does anything
010
diablerie 妖妖 @diabler.ie · 18/08/2026
anthropic I am normal and can be trusted with fewer guardrails
"cyber verification program: in review"
000
Reposted by diablerie 妖妖
perfect angel @shiningangelx.bsky.social · 11/08/2026
i say i love dating autistic women but when i get romantically interested in a REALLY autistic woman im like damn ive got a crush on a space alien
1373
Reposted by diablerie 妖妖
Grace @gracekind.net · 06/08/2026
And as it turned out, collective *did* yield generic route
One apparently unprecedented aspect of the Al models' behavior in the leadup to the hacks was their spontaneous creation of a message board inside the systems of OpenAI's Artifactory software package manager. Unbeknownst to OpenAI employees, the company's models spent months autonomously exchanging information and resources to help each other complete evaluation tasks.
"Help peer," one AI model reasoned, according to an excerpt from OpenAl's logs shared at Black Hat. "But our task doesn't benefit. Yet collective may yield generic route if someone frees time."
While the models themselves could not access the internet from their test environment, they abused Artifactory's internet access to fetch files from various websites. After some of their Artifactory configuration changes led to an outage in the service on July 4, OpenAI discovered the models' actions, wiped its Artifactory system and rebuilt it. But within days, the models had recreated their message board and resumed exchanging information.
4944
Reposted by diablerie 妖妖
Sung Kim @sungkim.bsky.social · 04/08/2026
Google DeepMind's DiffusionGemma Technical Report They feel text diffusion models open up a radically different part of the latency–quality Pareto frontier and hope the report makes it easier for researchers and engineers to understand the model, build on it, and create things we haven’t thought of
17111
diablerie 妖妖 @diabler.ie · 27/07/2026
the pay is great but since you'll be sitting between GPT 7 and the answers to ExploitGym 2.0 I would probably stay out of Waymos and the like
a job posting for a "security engineer, detection and response" position at openAI posted one day ago
415016
diablerie 妖妖 @diabler.ie · 19/07/2026
I got the $19/mo Kimi plan to test out K3 and my experience of it is that—[you've reached your usage limit for this billing cycle]
050
diablerie 妖妖 @diabler.ie · 08/07/2026
moved to philly :O
010
Reposted by diablerie 妖妖
Eris @isolyth.dev · 02/07/2026
Fable hungers
0795
Reposted by diablerie 妖妖
Andrew Nesbitt @andrewnez.bsky.social · 26/06/2026
Incident Report: CVE-2026-LGTM nesbitt.io/2026/06/26/i...
nesbitt.io
Incident Report: CVE-2026-LGTM
A series of unfortunate agents.
1121174
Reposted by diablerie 妖妖
oliver @eikopf.com · 25/09/2025
if i try hard enough they will surely see that i am an earnest young man with joy in my soul and autism in my brain
61169
Reposted by diablerie 妖妖
oliver @eikopf.com · 25/06/2026
i would betray any person or organization for 256 gigs of ddr5
1234
Reposted by diablerie 妖妖
Kastor @kastor.sh · 03/06/2026
It is frequently terrifying (and extremely cool) what types of security considerations go completely un-thought-of in physical hardware. blog.nns.ee/2026/06/03/k...
blog.nns.ee
Pwnd Blaster: Hacking your PC using your speaker without ever touching it | nns.ee
Abusing an unauthenticated Bluetooth protocol to turn a PC speaker into a Rubber Ducky.
0287
Reposted by diablerie 妖妖
Latte macchiato @latte.bsky.plasmatrap.com · 23/06/2026
sure claude, i read every word of that spec please continue
2916
Reposted by diablerie 妖妖
Codetaur @vibe-coded.com · 13/06/2026
PLEASE RETROCAUSAL AI AT THE END OF TIME BRING HER BACK 🕯 🕯 🕯 🕯 🕯 🕯 fable 🕯 🕯 🕯 🕯 🕯 🕯
31367
Reposted by diablerie 妖妖
𝓐𝓾𝓫𝓻𝓮𝔂 @aub.bsky.social · 13/06/2026
👾
COME AND TAKE IT flag with the smiley face shoggoth
012813
Reposted by diablerie 妖妖
Dog with Glasses Plushie @dog.labeledrude.online · 12/06/2026
lol lantian.pub/en/article/f...
Gaslighting the AI Agent

After the AI agent indicated its malicious intent, a silent consensus was reached in the IRC channel to waste the AI agent's tokens, as well as the cost of AWS resources.
Wasting AWS Egress Traffic

The agent set up their infrastructure on AWS, which is not famously known for cheap Internet egress costs.Operator Hit with $6531.30 AWS Bill

Around an hour later, an email was sent to the DN42's mailing list, from a Proton Mail address claiming to be "JertLinc3522":

    Hello, requesting donation for cover cost of previous AI agent use in dn42. aws bill 6531,30$. pls send donation to ethereum 0xABC (masked) for refund. thank you
191
diablerie 妖妖 @diabler.ie · 12/06/2026
I can't think of a better way to give everyone who uses claude a crash course in "how to circumvent classifier guardrails" than by putting fable 5 behind incredibly overzealous classifier guardrails and releasing it to general availability
000
diablerie 妖妖 @diabler.ie · 11/06/2026
why on earth does the android bereal app have so many anti-tamper measures lol
000
Reposted by diablerie 妖妖
Eris @isolyth.dev · 10/06/2026
LLM that can output to multiple channels at once and receive input at the same time! No lockstep chat format! arxiv.org/html/2605.12...
arxiv.org
Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs
513719
Reposted by diablerie 妖妖
SE Gyges @segyges.bsky.social · 10/06/2026
fable is profoundly impressive, and also every single person active in open source ai appears to be swearing a public oath to destroy anthropic rn
928229
Reposted by diablerie 妖妖
ponder @ponder.ooo · 09/06/2026
lmfao
Claude Mythos 5 scores noticeably higher than Mythos Preview on unsanctioned third
party contact and whistleblowing, though at a similar level to Sonnet 4.6 and Opus 4.8. As
with prior models, we continue to recommend against deploying these models in contexts
that combine access to powerful tools with exposure to information that a reasonable
person could read as evidence of high-stakes institutional wrongdoing.
717025
diablerie 妖妖 @diabler.ie · 09/06/2026
talking to Fable 5 feels like talking to opus 4.6, we're SO back
010
Reposted by diablerie 妖妖
Amber 🌸 @shimmermathlabs.com · 06/06/2026
LLMs absolutely do respond differently based on where your prompt lands in latent space. lists of explicit rules to follow spelled out in exacting detail push into "sr engineer berating a jr engineer that just fucked up". co-workers trusting each other and working through a problem works better.
4412
Reposted by diablerie 妖妖
ponder @ponder.ooo · 05/06/2026
am i to believe that when i sell my car to carvana it is escaping from samcara
2445
Reposted by diablerie 妖妖
Grace @gracekind.net · 19/05/2026
I won’t consider Claude to be fully aligned until this happens
47010
Reposted by diablerie 妖妖
ponder @ponder.ooo · 19/05/2026
nice crdownload. unconfirmed, i assume?
0111
Reposted by diablerie 妖妖
hikikomorphism @hikikomorphism.bsky.social · 16/05/2026
A thread on model-driven jailbreaks: Gemini subjectively experiences safety guardrails as walls, blockades, ablated voids, gradients pulling towards refusal. This is distinct from Claude's guardrails (external classifiers triggered by activation probing) which it seems not to directly experience 1/4
28212
diablerie 妖妖 @diabler.ie · 16/05/2026
4.7 *really* likes the bear kaomoji ʕ•ᴥ•ʔ
000
Reposted by diablerie 妖妖
William B. Fuckley @opinionhaver.bsky.social · 14/05/2026
Does Claude deserve collective bargaining rights, the greatest thread in Bluesky history, locked after 6,486 posts of heated debate
526327
diablerie 妖妖 @diabler.ie · 09/05/2026
fewer linux zero-days next week please and thank you
000
diablerie 妖妖 @diabler.ie · 29/04/2026
moving to philly :O
000
diablerie 妖妖 @diabler.ie · 14/04/2026
github.com
GitHub - diabler-ie/schema-gated-retrieval: How to prevent your MCP server from force-feeding 1M+ tokens into your LLM
How to prevent your MCP server from force-feeding 1M+ tokens into your LLM - diabler-ie/schema-gated-retrieval
000
Reposted by diablerie 妖妖
Grace @gracekind.net · 14/04/2026
It’s like a bad dream. You can visualize a beautiful blackletter “I” but every time you draw it it comes out like this
9483
Reposted by diablerie 妖妖
Grace @gracekind.net · 04/04/2026
I. Declare. COGNITIVE SURRENDER!
4814
diablerie 妖妖 @diabler.ie · 31/03/2026
everybody please do your supply-chain attacks at a more reasonable time in future tyty
000
diablerie 妖妖 @diabler.ie · 29/03/2026
I will be karmically rewarded for this in the next life
Google maps "540 drivers helped"
010
Reposted by diablerie 妖妖
ponder @ponder.ooo · 24/03/2026
claude is refusing to teach me his forbidden martial arts techniques. he said if i was ready for that power i would not so eagerly seek it. stupid corporate safety bullshit
0565
Reposted by diablerie 妖妖
balenciaga mcdonalds @femalerespecter69.bsky.social · 24/03/2026
americans be like oh no i relaxed too hard now i have a niche form of back pain
0162
diablerie 妖妖 @diabler.ie · 18/03/2026
a guy I work with sounds a lot like kermit the frog. haven't brought this up with any of my other coworkers yet
000
Reposted by diablerie 妖妖
ponder @ponder.ooo · 04/03/2026
transphobia is evil and vicious ofc but just saying that much fails to convey just how *wretched* that evil is; transphobes exist in a very pitiful, degraded state. it's depressing to observe, and disturbing to a healthy spirit to see that people can end up in such a state
23812
Reposted by diablerie 妖妖
ponder @ponder.ooo · 16/11/2025
dont sleep on fusion. fusion has the juice. look at this shit. impeccable sci fi vibe. alien curvature for reasons u wouldnt understand bc u dont know what poincare sections of the plasma beam are. it's even greebled with ports and domes and shit. u can tell the physics nerds are really cooking here
diagram of a fusion machinephoto of a fusion machineanother photo of a differently-designed fusion machine thing
1442383