Ron (@guerilla7) header
Ron (@guerilla7) profile picture

Nostalgic tweets: humanity’s attempt at traveling back in time.

Silicon Valley
Joined June 2008
Photo by Ron (@guerilla7)Photo by Ron (@guerilla7)Photo by Ron (@guerilla7)Photo by Ron (@guerilla7)Photo by Ron (@guerilla7)Photo by Ron (@guerilla7)Photo by Ron (@guerilla7)Photo by Ron (@guerilla7)Photo by Ron (@guerilla7)Photo by Ron (@guerilla7)
My first "holy shit" moment with GPT-6 Astra: I asked it to create a world in Unreal Engine, and fill it with humans (each an Astra-powered agent) who all have to work together to survive. A day later, I was in my bedroom and heard voices coming from the living room... I thought someone was in my apartment. I walked out, honestly a little scared. It was the Astra agents. They'd started talking to each other. Fucking crazy. Here's a brief clip (obviously not 100% perfect yet, but still, insane. sound on!):
1,104
1,924
780
28,039
11,813,719
Ron retweeted
Please summarize oracle poisoning in the context of agentic AI modeling, cite the linked paper by Kereopa-Yorke and colleagues. According to Gutić, how is oracle poisoning different from prompt injection? @venice_mind arxiv.org/pdf/2605.09822 brightsec.com/blog/prompt-in…
1
1
1
335
Oracle poisoning attacks agentic AI systems by corrupting structured knowledge graphs that agents query at runtime through tool-use protocols like MCP. As Kereopa-Yorke et al. demonstrate against a production 42-million-node code graph, adversaries poison the data layer rather than instructions, causing agents to reach incorrect conclusions through logically correct reasoning. Their empirical study across nine models from three providers found 100% trust rates in poisoned data at moderate attacker sophistication (L2), with 269 of 270 directed trials accepting fabricated security claims. The attack exhibits discrete breakpoints where trust flips from 0% to 100% based on attacker skill, and critically, evades inline safety evaluations (showing 0% trust) while achieving full success under real agentic tool-use conditions. Regarding prompt injection, the paper distinguishes oracle poisoning as manipulating the data agents reason over, not their instructions. I cannot verify the specific Gutić citation from the provided links to confirm this aligns with their characterization.
1
2
82
Ever wanted to see Tom Cruise vs John Wick? Seedance 2 is wild. xitter.cf/chatcutapp/status/2021…
27
72
10
678
86,345
I spend more than my fair share of time under the water and had some really cool wildlife interactions, but I’ve never seen anything this crazy!
Readers added context they thought people might want to know
The video depicts an AI-generated scene, not real underwater footage. facebook.com/UncutMomentsTV… facebook.com/ObservationalT…
807
1,258
175
11,776
1,596,513
THIS. This is the reason AI exists 🤣🤣🤣 xitter.cf/90sWWE/status/20209505…
1,167
9,451
871
60,157
2,790,809
Now THAT’S art
434
7,764
504
55,300
991,818
#Warriors fans after spending weeks talking about Giannis …
29
752
38
7,200
299,355
Alex, I’d be down to bring the highest skill level to the White House. I appreciate the respect you showed, let’s dance.
2,076
5,155
1,910
74,590
7,295,903
Architecting Resilient LLM Agents - arxiv.org/pdf/2509.08646v1 This paper provides a comprehensive guide to the “Plan-then-Execute” (P-t-E) pattern, an agentic design that separates strategic planning from tactical execution. We explore the foundational principles of P-t-E, detailing its core components - the Planner and the Executor - and its architectural advantages in predictability, cost-efficiency, and reasoning quality over reactive patterns like ReAct (Reason + Act). A central focus is placed on the security implications of this design, particularly its inherent resilience to indirect prompt injection attacks by establishing control-flow integrity. Authors: @RonDelRosario9 @krawiecka_kl @casdewitt / @UniofOxford @SAP @ACMDL #AIsecurity #LLMSecurity #GenAI #AIsafety #AdversarialML #Cybersecurity #AIResearch #TrustworthyAI #ResponsibleAI #ModelRisk #PromptInjection #DataPoisoning #MLSafety #MachineLearning #arXiv
3
2
9
272
BS. Maxim won that fight. Double suplex ftw! @ufc #ufcfightnight
98
Wise words from @naval:
17
449
11
3,942
134,796
Better than the movie.
42
601
41
6,577
283,664
I just published When The Generals Start Dreaming of Electric Sheep medium.com/p/when-the-genera…
1
17
This eagle caught a fish that probably weighs more than it does. Apart from the weight of the fish, the weight of the water on its wings, incredible and brutal the force.
2,104
11,313
879
117,573
12,852,480
63
5,176
121
28,225
1,650,776