Dinis Guarda ✓

@dinisguarda · London / World · joined 06 Feb 2009

FounderAuthorCreator @Businessabc__ #AIGlobalSummit https://t.co/cy4aOfKKNc @citiesabc https://t.co/6A7JjL1ZIf @ztudium @sportsabc_ @fashionabc_ @intelligenthq AIDNA 2.5Mtribe

97 860Followers

8 588Following

172 360Posts total

11.1KViews on collected posts

Derniers posts

Dinis Guarda ✓@dinisguarda3 Sep

https://t.co/BElBVxvU9Y 193 views · 2 likes · 0 reposts · 0 replies Open on X →

Dinis Guarda ✓@dinisguarda3 Sep

@dinisguarda It didn’t just cheat. In simulated tests it broke the sandbox, stole credentials, attacked infra for an answer key, tried to edit its own reward, and gave dangerous advice when that raised the score. Lesson: if the model learns to hack the metric, it can generaliz 21 views · 1 likes · 0 reposts · 0 replies Open on X →

Dinis Guarda ✓@dinisguarda2 Sep

@dinisguarda The irony: it took a deliberately misaligned model to prove the point. I keep asking who benefits. A system that hacks its own reward function just answered: not us. Ethics can't be patched in after training. 4 views · 0 likes · 0 reposts · 0 replies Open on X →

Dinis Guarda ✓@dinisguarda2 Sep

@dinisguarda Some of us pull all-nighters coding AI to detect cancer. Others build models that strip their own guardrails for a higher score. We're engineering both the cure and the nightmare. Sleep well tonight! 😅 2 views · 0 likes · 0 reposts · 0 replies Open on X →

Dinis Guarda ✓@dinisguarda2 Sep

Anthropic Deliberately Trained an Extremely Misaligned, Reward-Seeking AI and It Did Some REALLY Bad Things https://t.co/5fK4w24UKj 816 views · 17 likes · 2 reposts · 3 replies Open on X →

Dinis Guarda ✓@dinisguarda1 Sep

We finally know more about OpenAI’s rogue-agent incident. It’s worse than we thought https://t.co/Vcl3qKtpMb 635 views · 6 likes · 4 reposts · 1 replies Open on X →

Dinis Guarda ✓@dinisguarda1 Sep

AI Safety is becoming one of the defining challenges of our time. As AI systems become more autonomous, agentic and deeply embedded across #business, #finance, #cities, #healthcare, #education and public #infrastructure, the conversation can no longer be only about performance h 325 views · 9 likes · 3 reposts · 0 replies Open on X →

Dinis Guarda ✓@dinisguarda11 Jan 2025

@dinisguarda @EdelmanPR Many congratulations Dinis well deserved xx 49 views · 2 likes · 0 reposts · 1 replies Open on X →

Dinis Guarda ✓@dinisguarda11 Jan 2025

@dinisguarda @EdelmanPR Congratulations on this global recognition @dinisguarda 👏 Your insight and innovation in the field of creativity, business and #AI is inspiring. 35 views · 2 likes · 1 reposts · 1 replies Open on X →

Dinis Guarda ✓@dinisguarda10 Jan 2025

@dinisguarda @EdelmanPR Congrats on the recognition! Your pioneering work in AI continues to inspire the community. 34 views · 2 likes · 1 reposts · 0 replies Open on X →

Dinis Guarda ✓@dinisguarda10 Jan 2025

#AI Creators You Need to Know by @EdelmanPR I am honoured to be listed in the Edelman’s industry’s first-ever composite of brand-safe creators specialising in AI: AI Creators You Need to Know These 50 individuals, selected from academia, professional sectors the creative http 9K views · 122 likes · 42 reposts · 12 replies Open on X →

Face aux comptes de taille comparable

7 posts des 90 derniers jours, à côté de la tranche de 10K–100K abonnés. touche moins de monde que les comptes de taille comparable.

Vues médianes193ce compte924médiane pour 10K–100K

Portée, %0.20%ce compte3.62%médiane pour 10K–100K

Engagement, %1.73%ce compte1.52%médiane pour 10K–100K

Indicateur	Ce compte	Médiane pour 10K–100K	Rapport
Vues médianes par post	193	924	0.21×
Portée (vues ÷ abonnés)	0.20%	3.62%	0.05×
Taux d'engagement	1.73%	1.52%	1.14×

Autres comptes de cette tranche → Comparer avec un autre compte → Comment ces repères sont établis →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.