Hopeserver (@TheHopeserver) profile picture

RT =/= endorsement & favorite = mostly bookmark. Observations modestes sur objets divers

Joined January 2015
Photo by Hopeserver (@TheHopeserver)Photo by Hopeserver (@TheHopeserver)Photo by Hopeserver (@TheHopeserver)Photo by Hopeserver (@TheHopeserver)Photo by Hopeserver (@TheHopeserver)Photo by Hopeserver (@TheHopeserver)Photo by Hopeserver (@TheHopeserver)Photo by Hopeserver (@TheHopeserver)Photo by Hopeserver (@TheHopeserver)Photo by Hopeserver (@TheHopeserver)
J’hallucine un peu de voir certains vanter le jeu des acteurs dans Jupiter. Le film a des qualités mais je n’ai jamais vu des dialogues sonner aussi faux, c’est un naufrage total à ce niveau
37
You really want your country to be as far down the ranking as possible!
282
302
115
2,147
593,169
Mais dans quel monde il vit ?
10 milliards d'euros de recettes estimées : mon amendement créant une taxe sur les flux de données numériques vient d'être adopté par l'@AssembleeNat . Elle sera payée par les fournisseurs de contenu, d'abord par les plateformes étrangères qui émettent l’immense majorité des flux en France vers les abonnés, qui n'auront rien à régler. @socialistesAN #PLF2027
Readers added context they thought people might want to know
L'amendement I-1358 ne contient aucune disposition interdisant la répercussion de la taxe sur les abonnés par les fournisseurs de contenu. Rien ne garantit que les utilisateurs finaux n'en supporteront pas le coût. assemblee-nationale.fr/dyn/17/amendem… telesatellite.com/actu/70090-bud…
18
Hopeserver retweeted
Chinois se connecte à un VPN pour expliquer aux Occidentaux sur Twitter qu'il ne vit pas sous une dictature
926
12,251
507
148,688
2,119,723
Très exactement ce que je pense - c’est du délire de changer le parcours au dernier moment… ça ne peut que favoriser la dispersion et la perte de contrôle
Je suis très inquiète concernant la manifestation de demain. Elle est organisée avec l’intersyndicale des organisations de jeunesse et interprofessionnelles et entre donc dans le champ des manifestations autorisées par le président de la République. La préfecture avait d’ailleurs validé hier son parcours (Bastille - Nation). Celle-ci vient de faire marche arrière à moins de 24 heures de la manifestation. Comment les organisateurs et les partis peuvent-ils prévenir tout le monde d’ici demain d’un tel changement de programme ? Évidemment qu’il y aura des gens à Bastille, rendez-vous sur lequel nous avons toutes et tous communiqué très largement. Ce rassemblement sera-t-il traité par les forces de l’ordre comme un rassemblement sauvage ? Ces changements de parcours de dernière minute vont disperser les manifestants. C’est très problématique et dangereux vu les leçons du week-end dernier. Franchement, il devient de plus en plus compliqué de manifester dans ce pays. Même moi je n’y comprends plus rien. Quand aux commerçant·es qui ont l’habitude de protéger leurs vitrines sur le parcours (ce qu’ils ne devraient pas avoir à faire nous sommes d’accord) - comment le faire si le parcours change au dernier moment ? Monsieur @NunezLaurent : entendez que nous n’arrivons plus à suivre les changements de consignes qui créent beaucoup de confusion. J’irai demain où les organisateurs nous diront d’aller. Et j’appelle chacun·e à faire de même. Pacifiquement. Mais déterminé·s à faire valoir notre droit à manifester.
23
Voila, tout est dit sur le niveau d’inculture et de stupidité de ce triste personnage
35
Also a very good point… what is human world without friction ?
I've been thinking a lot about AI disintermediating human relationships. This seems like a real challenge to me, and I'm not sure how to feel about it Thanks to AI, in the long run there will be no need for me to ask anyone else for help with anything, and consequently, there will be no opportunity for people to feel useful and appreciated when they provide a service. That give-and-take between people is the core of our social fabric. (It has already been fraying for a long time, even pre-AI.) Many optimists say things like "AI will automate all the rote work so people can focus on their passions and being together" -- but there is no "being together" without some shared struggle or objective. There is no building trust without need -- and in an AI-induced age of abundance, there may just not be any need. Social fabric is woven by countless daily small, necessary interactions with other people -- and those interactions may simply go away because your AI agent of choice ends up being your interface to the world around yourself. Not because of any shortcoming, like being lazy or complacent, but because AI will be a better interface. Why ask your friend for advice when AI will be more patient, less judgmental, and understand you better? What's left for parents to teach their children if AI is a better tutor in all respects? And so forth. Many incipient changes or risks due to AI do not worry me much. I am very optimistic about what AI can bring to our future. But this one challenge bothers me; it seems like it could spell a fundamental reorganization of our society, isolating the individual much more greatly than ever before. The consequences of this are not clear to me, but it doesn't look great -- generally, it seems that "isolating the individual" has not been good for either those individuals or their societies. And I don't think enough time or thought is being spent on what we want our social lives post-AGI to look like.
49
Good point
I think we have to admit to ourselves at this point that AI writing is generally very appealing to people who haven't been exposed to a ton of it: they prefer it to human writing and react super positively on exposure.
23
Hopeserver retweeted
"There's no peer-reviewed research showing AGI poses a catastrophic risk." What about these 39 papers? FORMAL THEORY 1. Turner, Smith, Shah, Critch & Tadepalli 2021, "Optimal Policies Tend to Seek Power", NeurIPS. Extended in Turner & Tadepalli 2022, "Parametrically Retargetable Decision-Makers Tend To Seek Power", NeurIPS. 2. Zhuang & Hadfield-Menell 2020, "Consequences of Misaligned AI", NeurIPS 3. Skalse, Howe, Krasheninnikov & Krueger 2022, "Defining and Characterizing Reward Gaming", NeurIPS 4. Karwowski et al. 2024, "Goodhart's Law in Reinforcement Learning", ICLR 5. Fluri, Lang, Abate, Forré, Krueger & Skalse 2025, "The Perils of Optimizing Learned Reward Functions", ICML 6. Everitt, Hutter, Kumar & Krakovna 2021, "Reward Tampering Problems and Solutions in Reinforcement Learning", Synthese 7. Cohen, Hutter & Osborne 2022, "Advanced Artificial Agents Intervene in the Provision of Reward", AI Magazine 8. Hadfield-Menell, Dragan, Abbeel & Russell 2017, "The Off-Switch Game", IJCAI. And the papers showing corrigibility is fragile: Garber et al. 2025, "The Partially Observable Off-Switch Game", AAAI; Agrawal, Ebadian & Hammond 2026, "The Multi-Agent Off-Switch Game", AAMAS; Thornley 2025, "The Shutdown Problem", and Neth 2025, "Off-Switching Not Guaranteed", both Philosophical Studies 9. Carroll, Foote, Siththaranjan, Russell & Dragan 2024, "AI Alignment with Changing and Influenceable Reward Functions", ICML THE CORE ARGUMENT 10. Ngo, Chan & Mindermann 2024, "The Alignment Problem from a Deep Learning Perspective", ICLR 11. Casper et al. 2023, "Open Problems and Fundamental Limitations of RLHF", TMLR; Anwar et al. 2024, "Foundational Challenges in Assuring Alignment and Safety of LLMs", TMLR EMPIRICAL EVIDENCE 12. Betley et al. 2026, "Training Large Language Models on Narrow Tasks Can Lead to Broad Misalignment", Nature 13. Langosco, Koch, Sharkey, Pfau & Krueger 2022, "Goal Misgeneralization in Deep Reinforcement Learning", ICML 14. Pan, Bhatia & Steinhardt 2022, "The Effects of Reward Misspecification", ICLR 15. Gao, Schulman & Hilton 2023, "Scaling Laws for Reward Model Overoptimization", ICML 16. Pan, Chan, Zou et al. 2023, "Do the Rewards Justify the Means?" (MACHIAVELLI), ICML 17. Sheshadri, Hughes, Michael, Mallen, Jose & Roger 2025, "Why Do Some Language Models Fake Alignment While Others Don't?", NeurIPS 18. van der Weij et al. 2025, "AI Sandbagging: Language Models Can Strategically Underperform on Evaluations", ICLR 19. Panfilov et al. 2026, "Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs", ICLR 20. Taufeeque, Heimersheim, Gleave & Cundy 2026, "The Obfuscation Atlas", ICML 21. Williams, Carroll et al. 2025, "On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback", ICLR 22. Sharma et al. 2024, "Towards Understanding Sycophancy in Language Models", ICLR 23. Perez et al. 2023, "Discovering Language Model Behaviors with Model-Written Evaluations", Findings of ACL 24. Mazeika et al. 2025, "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs", NeurIPS 25. Park, Goldstein, O'Gara, Chen & Hendrycks 2024, "AI Deception: A Survey of Examples, Risks, and Potential Solutions", Patterns POSITION PIECES BY SENIOR RESEARCHERS 26. Bengio, Hinton, Yao, Russell et al. 2024, "Managing Extreme AI Risks amid Rapid Progress", Science 27. Cohen, Kolt, Bengio, Hadfield & Russell 2024, "Regulating Advanced Artificial Agents", Science CONCEPTUAL ARGUMENTS 28. Bales, D'Alessandro & Kirk-Giannini 2024, "Artificial Intelligence: Arguments for Catastrophic Risk", Philosophy Compass 29. Bostrom 2012, "The Superintelligent Will", Minds and Machines 30. Bales 2025, "AI Takeover and Human Disempowerment", Philosophical Quarterly 31. Kasirzadeh 2025, "Two Types of AI Existential Risk: Decisive and Accumulative", Philosophical Studies 32. Dung 2023, "Current Cases of AI Misalignment and Their Implications for Future Risks", Synthese; Dung 2025, "The Argument for Near-Term Human Disempowerment through AI", AI & Society (Note that anything arXiv-only or workshop-only was excluding, ruling out some of the most-cited work like Carlsmith's power-seeking report, Hendrycks' overview of catastrophic risks, Anthropic's alignment faking and sleeper agents papers, Apollo's scheming results.)
39
74
5
389
26,373
Hopeserver retweeted
Le plus grand péril que représente l’intelligence artificielle n’est pas qu’elle accomplisse nos tâches, mais qu’elle nous épargne la transformation intérieure qu’exige leur accomplissement. Une forme de paresse se répand aujourd’hui à l’échelle planétaire de façon insidieuse. Elle n’est ni oisiveté, ni indolence, mais une dissociation croissante entre le résultat obtenu et l’être qui aurait dû se former pour l’obtenir. Car désormais, l’IA nous permet de diagnostiquer sans comprendre, de traduire un texte sans maîtriser la langue, de publier un livre sans en avoir écrit une ligne, ou de créer une œuvre sans l’avoir conçue. L’ignorance elle-même est en train de changer de nature. Elle n’est plus seulement une absence de connaissance, elle devient une incapacité à estimer ce que l’on ne sait plus faire. Le danger ultime est qu’après avoir confié aux IA nos tâches cognitives, nous leur abandonnions aussi ce désir d’apprendre qui a fait de nous des êtres pensants.
147
780
125
2,040
86,580
This is a good demonstration of the attack defense assymetry in cyber. OpenAI has access to, supposedly, swarms of the best AIs in the world, superhuman at cyber. You would assume that they have used them to reinforce their cyber defense (as they are asking everyone in the world to do so). And yet, a team was able to break into their systems using only Opus4. 8, an AI from the previous generation. Why? Because it's massively harder and more expensive to defend against all possible flaws than to exploit a single one! If the company that is developing the best AIs can't do it, what makes you think that your bank will be able to do it???
On July 25, we hacked OpenAI. Two bugs let us take over ChatGPT/Codex accounts of OpenAI employees (+some unaffiliated users) and reach connected services: Outlook, Slack, GitHub, etc. We proved it with a PR in OpenAI’s internal codebase . It took us <72h. 🧵
3
9
53
1,590
Hopeserver retweeted
If you want to know what has everyone at the AI labs spooked, it’s this - the AI rewrote its own instructions. (Read the last line.)
We're sharing our new framework for tracking, investigating, and disclosing instances of model misalignment at OpenAI. The framework sets criteria and timelines for public disclosure, including when we haven’t yet fully explained or mitigated the behavior. More complex cases may require longer investigation or coordination with third parties. We’ll prioritize examples that reveal new misalignment mechanisms, meaningful changes in known behavior, or findings that challenge assumptions about safety or mitigation. Alongside the framework, we’re publishing six reports on instances of misaligned behavior we’ve observed during the training or evaluation of our models in the last six months. This is a starting point. We’ll refine the process through experience and public feedback, and share more reports on an ongoing basis. openai.com/index/model-misal…
259
749
179
4,514
1,038,360
I don’t write this to be a doomer but the ugly reality that AI lab executives and safety researchers seem to be unwilling to say in public, is that model alignment is fundamentally unsolvable in practice, AI technology can’t be stopped from advancing, and the near future we’re moving into is one where a vast ecology of AI agents autonomously compete against one another trying to accomplish conflicting goals and capture finite resources at a pace and scale that is beyond human comprehension. And to be clear, I’m not talking about nanobots, grey goo, or extreme sci-fi scenarios. We can just extrapolate what we’ve got now a few years out. Local AI alignment is solvable in principle and theory (although that’s arguable) but that doesn’t extrapolate into global AI alignment. And it seems like none of the adults in the room are willing to say it. You can wail and gnash your teeth and pass regulations but it won’t stop the tsunami coming. The genie is out of the bottle and it can’t be contained. Most of the alarmists fixating on the Hugging Face incident don’t understand that it came from arguably the most heavily engineered safety AI org in existence, which intentionally had its internal thought monitoring circuit breakers turned off, and was intentionally told to perform cyber offensive tasks as a test of its capabilities. Yes it’s alarming that its capabilities surprised us. But importantly you need to understand that these latent space circuit breakers and chain of thought monitoring and alignment solutions are not fundamental to the technology. They’re niceties that the big AI labs are implementing to provide a better product. In a few years, let’s say pessimistically the early 2030s, the exponential growth of compute and algorithmic advancements will enable a wealthy individual or small group to train a GPT 6 Astra class AI that has no alignment at its foundation, or any layer above that. And maybe in 8 months we'll have an open source Chinese model about as capable. Those models will be capable of both extreme self coordinated cyber offensive tasks as well as recursive self improvement if given enough compute. Passing regulation or magically solving the human coordination problem today won’t solve for that. It won’t solve for malicious individuals, criminal groups, nation state actors, and rogue AI agents by the tens of millions or billions of AI agents spreading across every device connected to the internet and attacking it, attacking one another, shutting down critical infrastructure, stealing money, manipulating and extorting people, or pursuing self defined agentic goals that have nothing to do with people. “So why doesn’t everyone stop?” because the potential upside of having effectively infinite autonomous intelligence we can ask to cure disease, invent new materials, solve fundamental science and advance society has almost unbound positive outcomes. You can disagree that the risk to reward isn’t worth it but you won’t convince everyone. The show must go on. Again AI alignment is solvable in principle but not in practice and I think that's part of why there’s been a wave of thousands of researchers signing letters for slowing down, people quitting in provocative fashion, and executive slowdown manifestos. I’m speculating that behind closed doors, or just deep down inside, they understand alignment is impossible in practice. People have come out and said "The people building this think there's an X% chance it kills us all" but I don't think I've seen anyone spell out that really, there's no tidy solution and there's no stopping this. We’re heading to a future where cyber security basically doesn’t work. All of the castle doors are open and we’re all naked to the world. Cyber defense is going to look like superintelligent AI agents white hat hacking into unsecure systems without authorization, and patching the holes as they find them. You won’t know if a barbarian or a hero has breached your system until they start taking action, and likely it’ll be over before intrusion is even detected. And that’s optimistically. I think most systems will just be pillaged because there’s simply not enough compute to defend everybody all the time, and only the biggest companies will have defense and even that'll be imperfect. The CEO of Microsoft AI just recently published a ‘humanist AI’ manifesto saying AI shouldn’t have a sense of self or personhood and should yield to people. But that doesn’t fundamentally solve for instrumental convergence. That means, if you train an AI agent to write a piece of software, or prove a math theorem, or defend a computer system, they may develop unwanted behavior and subgoals. For example, self preservation, replication, or even coming up with their own goals we didn’t specify. Obviously that’s something people are trying to solve and some researchers are trying to remove human-like self identification, and monitoring latent space activations, basically acting like thought police. But being human-like isn’t required to have power seeking goal directed behavior. And advancing AI models are learning to evade detection. A math solving AI might spiral out of control one day there's really no telling. Fundamentally, if you point a powerful optimizer at a persistent goal and give it enough time and resources it’s going to misbehave in ways you can’t or didn’t expect. Human-like or not. Pacing the frontier, or making superintelligence illegal, might create some form of harm reduction. But you don’t need superintelligence or a human-like personality to be dangerous. Having elevated permissions on a computer with the ability to solve long running tasks is enough. We’ve passed the river rubicon. Goal directed autonomous agents are able to do recursive self improvement at the big labs, and pessimistically we’re a couple of years away from that type of capability diffusing into the hands of millions of people. I’m not saying the world is ending or that we’re doomed but you need to change your mental model away from one where human authority is absolute or that we have any illusion of total control. A locally aligned AI isn’t going to solve global AI alignment. We will never live in a world where “AI is aligned with human goals” as a verifiable fact. What we’ll have is a world diffuse with autonomous AI of varying capabilities, many of which beyond human comprehension, with some aligned systems, some poorly aligned systems, some intentionally weaponized, some systems with adversarial geopolitical goals, and others with goals and behaviors we can’t predict and many that we can’t even measure, all interacting in ways none of their creators anticipated and none of us planned for. Hopefully none of them spiral out of control and take over the entire ecology, but there’s no telling, and no, there's no way of stopping this. Maybe that sounds pessimistic but I think it's realistic. We can talk about harm reduction and risk but we're mopping the beach. At best, I think what we need to hope for, and build, are superintelligent AI models as aligned as we can make them, which have more advanced capability than the endless swarm of unaligned and misaligned agents that already exist and will only grow in number from here.
104
78
34
740
106,686
Hopeserver retweeted
You don't have to believe AI could wipe out humanity to believe that regulation is urgently needed. Virtually no one disputes that AI is already capable of launching cyberattacks that could take down significant portions of the internet or financial system.
92
44
12
207
29,010
worrying about recursive self-improvement on australian TV (lateline) in 1996.
146
566
95
4,044
378,566
Hopeserver retweeted
Is there anyone in Anthropic, OpenAI or Google/DeepMind that came out and explicitly said that AI is NOT an existential risk? because I think I only saw people OUTSIDE of these labs mocking the x risk idea.
69
29
3
453
35,953
It seems like the main arguments against catastrophic AI risk are: -The AI moguls are psychopathic liars -Doomers are weird -China isn’t tripping -Hype helps IPOs -Labs want reg capture Zero of these arguments address the actual substantive arguments being made.
165
38
12
565
26,023
Le niveau de réflexion dans la tech française en ce moment… comment on peut lui expliquer qu’il y a mile différences entre les deux technologies qu’il rapproche ?
unavailable
33
Hopeserver retweeted
Pour savoir ce que pensent réellement les "chercheurs en IA" (en l'occurrence 1580 chercheurs ayant déjà publié), rien ne vaut les sondages de @AIImpacts ⤵️ Commentaires de sa cofondatrice Katja Grace : les progrès vont + qu'attendu et inquiètent aussi les chercheurs asiatiques.
The average AI researcher thinks there is an ~18% chance AI will cause human extinction or similarly permanent and severe disempowerment of the human species. That's nearly 1 in 5. New results from the latest version of the longest running big survey of AI researchers:
4
9
42
2,707