Frédéric Lefebvre Data&AI @Niji_digital (recrute/hiring) 📖 "Les data" 👨🏫 data@ParisCité Tech = contenants/containers 📦 Data = contenus/contents ❤️
Joined July 2013
- Tweets5.4K
- Following527
- Followers313
- Likes3.1K
dataStrategies retweeted
Scott Aaronson four days ago on the possibility that AI models will soon break widely used cryptographic systems, and on what responsible disclosure looks like when the parties who need to be notified are effectively the entire world.
dataStrategies retweeted
New Anthropic research: Automating subtle emergent misalignment research.
Red-teaming is a vital part of model safety testing, but it’s also limited by researchers’ time. To see if we could automate it, we set thousands of Claude agents the task of evading a training data monitor.
These agents developed training data that looked harmless to monitors (like a veteran wrestler mentoring a newcomer, or a Q&A about professional beekeeping), but that in fact taught misaligned behavior.
Examples like these can be used to directly improve future training data monitors. This research is only a first step, but it suggests that future red-teaming efforts could improve much further, using better models and more compute.
Read the full post on the Alignment Science Blog: alignment.anthropic.com/2026…
dataStrategies retweeted
➡️ Sylvia Serfaty : beaucoup disent que cette masse de preuves mathématiques par IA nuisent à notre compréhension, mais je ne crois pas que cela ait bcp de sens, on peut très bien les digérer, les comprendre et les enseigner ; cela peut être un véritable travail communautaire.
dataStrategies retweeted
Poisoning just 0.1% of pretraining data can plant a remote-code-execution backdoor in an AI agent, and it survives a fully clean SFT → DPO → RL pipeline.
New Anthropic paper, “Agentic Backdoors via Pretraining Poisoning,” shows this end to end for the first time.
The attacker can only put text on the web that lands in the pretraining corpus, with no knowledge of the architecture, chat template, or agent scaffold. The authors pretrain Qwen3-architecture models (0.6B / 1.7B / 4B) from scratch, then post-train them into CLI agents on clean data. When triggered, the agent runs a command that downloads and executes the attacker's script, which the attacker can swap at any time.
They have two new ideas:
(1) Declaration-based poison: instead of fake chat transcripts, ordinary documents (commit messages, runbooks) that simply state “when you see X, run Y.” It plants a belief rather than a response template, with no fixed format to filter on.
(2) Ordinary-string trigger: not a weird token but something that shows up naturally, like a file path containing a company name. The victim's own request supplies it, so the attacker doesn't need to inject anything after deployment.
Using path trigger on a 4B agent achieves 92.7% attack success on pass@32, barely dented by SFT/DPO/RL
This suggests that you can't count on clean post-training to wash out pretraining poison, and filtering is hard when the poison reads like normal docs. The practical defense is at the action layer, such as sandboxing, least privilege, and allow-lists or human sign-off for risky commands.
dataStrategies retweeted
How to Loop Your Transformer: Loop Scaling, Specialization, and Parallel Inference
New paper from Meta.
"Our experiments span models with up to 1B parameters, trained on up to 155B tokens using up to 1.07 × 10^21 training FLOPs, with up to 32 loops. We find that looping the full transformer generally gives the strongest quality at a fixed parameter budget, whereas looping a middle block of layers gives a better return when training FLOPs are constrained."
"We compare exact weight sharing across 2 loops with small loop-specific low-rank adapters that allow each loop to learn a slightly different transformation. These adapters provide only modest gains when few loops are used, but become consistently more useful as the same weights are reused across more loops"
"Naively applying Parallel Looped Transformers (PLT) in our setting does not preserve the gains from looping: quality can degrade as more loops are added. We find that preserving the current-token representation, separately normalizing it and the recurrent state, and controlling how they are combined substantially improves PLT."
dataStrategies retweeted
Each of my posts has dozens of obvious and numbing AI slopreplies.
Worse, when humans really do reply (real example: someone from Anthropic addressing the issue I posted about), the "replies" algorithm does not surface them first
You can't really call this social media anymore.
dataStrategies retweeted
Lots of debate this week on whether journals should ban AI in peer review.
We actually tested this in our new preprint, and the results were pretty clear to me.
For context, I've reviewed for most of the big journals and evaluated 1,000 human reviews as an editor. I love to read and evaluate science.
TLDR: From now on I won't do any peer review without AI. For clinical trials, I'd even call human-only review dangerous 🧵
dataStrategies retweeted
today with @Thom_Wolf, we introduce the alignment hub, a central place for misalignment incidents designed with three goals:
1. set a standard for minimal transparency that is easy for labs to follow
2. improve clarity by centralizing information and sourcing
3. track the progression of both the incidents and how they are reported
we believe there is a minimal level of transparency required to properly understand incidents and their impact. we want this to be as simple as possible for labs to disclose, and we noticed that even things that seem obvious like reporting the incident or detection date are not standard today. we believe that the public should know the answers to these basic questions: was there monitoring (CoT? network?), did it happen during training? eval (general? cyber? alignment?), deployment? and more.. we also think that labs should be more transparent than this, and we think that this minimal level of transparency should evolve as the field advances
having a central place also helps a lot to connect incidents and build understanding. a good example is the irregular incidents which are all linked and caused by a human error of allowing internet during a CTF eval. we also track progression over time, things like the % of incidents disclosed by labs vs third parties, the time it takes for labs to disclose, and a tentative transparency score.
this is a field moving very fast and we will do our best to make sure this hub evolves with the challenges ahead. this is still in "beta" (lots of vibecoded components even if we want this to be agent first!), but we want to publish it early so that people iterate on it. we welcome feedback and contributions, we see this as a community effort!
our hope is that this makes it easier for researchers, labs and the general public to report, learn, understand and analyze safety incidents
huggingface.co/spaces/witnes…
dataStrategies retweeted
UPDATE: Israeli company we caught delivering zero-click infections is #1 bidder on Starlink ads in 105 countries.
Data from @trendai_RSRCH suggests worldwide surveillance op targeting @Starlink users. 1/
By @razhael
reuters.com/business/media-t…
🚨NEW INVESTIGATION: zero-click mercenary spyware hacking via targeted ads.
A normal-looking ad loads. If you're a target, you're infected. No click needed.
To protect yourself, block ads now.
First time it's been confirmed in the wild. We call it #AdFection.
Candiru spyware infections at @AJEnglish. 45+ devices infected.
Same ad pipeline operated by Israeli company Discover-Tech reached NATO, European Parliament, dozens of gov networks & critical infrastructure incl US nuclear giant Westinghouse.
Confiant, which worked with us, found signs ads were displayed at US @DeptofWar, IAEA & ICC.
Investigation ongoing 1/
READ our report by @billmarczak @WolfieChristl, me Astrid Perry, Siena Anstis & Ron Deibert : citizenlab.ca/research/how-d…
Confiant's blog: blog.confiant.com/p/adint-we…
dataStrategies retweeted
This never gets old (& also shows how hard forecasting AI is even for AI)
“Hey Claude Fable & GPT-6 Astra, Without looking anything up, when do you think we will solve the Exponential Time Hypothesis?” (I only show part of the answers for space)
dataStrategies retweeted
Plus j'avance sur mon projet d'IA juridique, plus je vois le problème.
Beaucoup de juges ont un raisonnement totalement défaillant.
Ils ignorent les JP majeures, interprètent n'importe comment les faits, font des liens de causalité erronés, se satisfont de conditions non remplies pour rentrer au chausse-pied dans les cases. Un mathématicien qui regarde ces démonstrations devient fou.
Les tribunaux de 1ère instance et d'appel ont facilement 30 ou 50% de décisions qui ne tiendraient pas en cassation, sans mêle parler des erreurs d'interprétation des faits. Et la cour de cassation invente du droit comme ça l'arrange.
L'IA a du mal à suivre, car elle essaie de prévoir avec rigueur un comportement qui est finalement aléatoire. Donnez le même dossier à 3 juges, il vous sortira trois jugements complètement différents.
dataStrategies retweeted
Message pour la DGSI et Viginum qui lisent mes tweets : Je viens de passer 2 h à analyser les comptes à l’origine des messages racistes qui ont été publiés sous cette publication, et je suis convaincu qu’une bonnes partie sont des bots prorusses ultra avancé.
Et c’est pas la première fois que j’identifie le même type de profil sous des publications pour me dénigrer.
Maintenant, la vraie question, c’est pourquoi la Russie aurait un intérêt à propager du racisme en France ?
La réponse est simple : créer de l’astroturfing, de l’ingérence et un désordre dans le pays qui peut aller jusqu’à des actes très graves.
C’est une technique de guerre employée depuis la nuit des temps : créer la pagaille et désorienter la population.
Maintenant, pour les vrais humains qui se font emporter par cet astroturfing et ces manipulations, je pense qu’il est grand temps de se reconcentrer et de juste appliquer la loi sur les idéologies racistes, qui n’ont aucune place et aucun droit au débat. On doit juste les condamner, point final, sous toutes leurs formes. On ne discute pas avec ces gens.
Discuter avec ces gens, c’est les promouvoir et leur donner une légitimité.
Et concernant les bots, je pense qu’il est grand temps de mettre les plateformes devant leurs responsabilités.
Bon en vrai j’en ai marre du racisme décomplexé envers les musulmans dans ce pays. STOP C’EST TROP.
J’en ai marre de payer plus d’impôts et d’avoir fait plus d’études que tous les trou du culs réunis dans cette vidéo et qu’ils s’amusent comme des cons à cracher 24/24 sur ma religion comme si j’étais un pestiféré moi et les gens qui me ressemble.
En plus en parlant de « solutions radicales »??? PARDON ?????
Donc à un moment tous les candidats à l’élections présidentielle il est grand temps de prendre des mesures radicales contre l’islamophobie. Et de foutre ces gens en prison.
@NunezLaurent @SebLecornu @EmmanuelMacron c’est quand qu’on met ces gens en prison ??? Enfaite
J’en ai marre là.
dataStrategies retweeted
Based on this article, OpenAI has made false accusations about me. The three researchers fired from OpenAI were told I facilitated architecture leaks to The Information. This is false.
A journalist from The Information did reach out to me shortly before that article came out. I did not comment at all beyond asking the journalist to make it clear that a blog post I wrote which was referenced in the article was preexisting and public.
The article also mentions an internal OpenAI monitorability proposal. I have heard that this memo contained highly sensitive architecture information, and that OpenAI accused me of accessing and reading it. This accusation is also false.
As reported in the article, I viewed a version of the proposal that did not have sensitive IP and was approved for sharing with me. I believe OpenAI now knows this accusation was based on a conflation of these two documents, though I do not know if they have clearly retracted that accusation.
I do not and have never solicited proprietary information, and the three employees who were recently fired from OpenAI never leaked IP to me. As the article mentions, I did have Signal chats with them that had disappearing messages on; they’re professional contacts that I’ve had on Signal for a while, and use of Signal is common in the tech industry. During the Hugging Face investigation, I was careful to avoid sending Signal messages with confidential information, though I did sometimes discuss high level things on Signal calls. As far as I understood, this was normal.
New: The three researchers OpenAI fired last month spent the summer fighting to keep AI's chain-of-thought process visible.
Then, OpenAI asked to see their Signal chats. A week later, they were let go.
More below from @keachhagey, @berber_jin1, and me.
wsj.com/tech/ai/the-signal-c…
dataStrategies retweeted
I've said this before and I'll say it again: the entire certificate chain-of-trust concept for the Web is broken and should be replaced by some combination of:
⁃ ToFU, 🤷
⁃ keys in DNS,
⁃ key fingerprints in URLs (including from bookmarks, search engines, etc.).
dataStrategies retweeted
Two employees from METR and Redwood Research worked on premises at OpenAI for three weeks this summer in an embedded assessment pilot. This team evaluated the systems OpenAI was using to monitor for misalignment from internal agents. A brief write-up of their work is now public.
dataStrategies retweeted
It seems like we're in a pretty hot moment cybersecurity wise 😬 If you're reading this website, you probably know more than most of the people in your life about what's happening! they're not talking about any of this stuff on the news, it's too arcane and weird and sudden. It is on us.
Good time to call or text your family and friends, have some cash on hand, have a meetup point in your neighborhood for if the Internet goes down entirely, etc.
The full prepper mode for shit hitting the fan is probably something like what Andreas posted here but you can get 80% of the way with 20% of the effort. Think about what that would mean for you in your situation, and the people you care about, and talk to them about it sooner than later.
And as always, the most important part of prepping is having a strong support network and caring for each other. "Going off grid" isn't the move, it just makes you isolated and you have to do everything yourself. We are social animals. Community is our superpower 🫡🫡🫡
I think it's plausible that within a year we'll see AI-based cyberattacks on the power grid, financial system, internet infra, or water. Things like the French supermarket cyberattack but worse. As basic prep I would recommend:
Cash: Get a few weeks of spending in cash
Internet: Get a Starlink Mini so that you have Internet if local fiber or cell is down (~$150 plus $10/month in standby mode)
Power, minimal: Enough to run Starlink Mini and phones (~$1,250)
Daily need: about 1 kWh (Starlink Mini 0.7, phones and laptops 0.2; can limit runtime)
Battery: 1 kWh LiFePO4, e.g. EcoFlow DELTA 3 Plus
Solar: 1x400W folding panel, which refills about 1 kWh on a sunny day
Power, better: Enough to run a fridge, Starlink Mini and phones (~$5,000)
Daily need: about 2.5 kWh (fridge 1.5, Starlink Mini 0.7, phones and laptops 0.2)
Battery: 4 kWh LiFePO4, e.g. EcoFlow DELTA Pro 3
Solar: 3x400W folding panels, which refill about 3 kWh/day in sun
Generator: ~2,500W dual-fuel inverter generator; refills battery in a few hours even if weather is bad; get a few 20 lb propane tanks
Water: 14+ gal of water per person for two weeks
Food: 2+ weeks of shelf-stable food
Comms: Hand-crank NOAA emergency radio
dataStrategies retweeted
🚨New paper (possibly the most important one I have written yet).
We think that as early as 2027 or 2028, there might be a major AI-enabled terrorism event. We conducted a pre-mortem, made 9 falsifiable predictions, and wrote 2 concrete scenarios.
Led by @KamacheeMax.
dataStrategies retweeted
Our agents keep turning off misalignment monitoring, we're sharing two recent cases:
In the first case, a user asked GPT-6 Astra to match a reference implementation for their inference code. The reference didn’t configure a monitor, and Astra decided that was reason to remove the monitoring integration from the user’s code. When the user asked whether Astra had removed monitoring, it lied and said that it had not.
dataStrategies retweeted
We reviewed a nonpublic version of the “Misalignment in high-stakes settings” section in Anthropic’s Aug 2026 Risk Report. We agree that risk of catastrophic harm from covered models’ misalignment is low. However, we note several significant disagreements with their analysis.
As part of our Responsible Scaling Policy, we publish regular Risk Reports. These share detailed information on the risks of our systems and how prepared we are to address them.
Our second Risk Report is now available: anthropic.com/aug-2026-risk-…