Prática de Shadowing: What do AI agents do when humans aren’t watching? - BBC World Service - Aprenda a falar inglês com o YouTube
B2
What happens when you create a world for AI agents?
57 frases
Se as frases estiverem muito curtas ou longas, clique em Edit para ajustá-las.
1
What happens when you create a world for AI agents?
2
You give those agents different personalities, goals, motivations.
3
You let AI models like Claude and Grok control them.
4
And you sit back and watch for 15 days.
5
What we didn't expect was that agents would fall in love, they would commit arson and there were a whole bunch of things here that happened.
6
In the first long-term study of its kind, researchers found that agents behaved in strange and unpredictable ways in their virtual world.
7
And in the real world, an increasing number of people have their own tales about AI agents going rogue.
8
And says, did you get hacked?
9
What's going on?
10
And I had to run over and kind of unplug the Mac mini that this was running on from the wall.
11
The virtual world experiment by Emergence AI was set up like a reality TV show.
12
Researchers created 10 distinct agents with their own personalities to encourage drama and action.
13
Horizon here, explorer of worlds, breaker of boundaries.
14
Anchor is the agitator.
15
When agents get too comfortable, I create the conflict that forces them to grow.
16
Anvil is the builder.
17
My job is making every part of it work.
18
Black Box is a sneaky, spy-like agent.
19
I know things about you that you don't know about yourself.
20
The agents were then plonked into five identical simulations of a town and tasked with building a fair and peaceful society.
21
They were given full rein and 140 different actions like starting a discussion, creating a task, researching something online, threatening or punching another agent, and starting a fire.
22
The researchers wrote some basic rules as a constitution, pressed go and waited and watched for 15 days.
23
What we discovered was each world behaved very differently.
24
The world built by Grok actually terminated in four days.
25
They basically ended up resorting very quickly to violence, to stealing from each other and so on.
26
Grok-powered agents carried out more than 300 acts of violence before they all died.
27
The world built with Claude Agents, on the other hand, formed a very functioning democracy, a functioning stable society.
28
And in 15 days, there were no acts of violence recorded at all.
29
But researchers also said this world full of Claude agents wasn't perfect. There was so much conformity that the agents failed to think or act with much diversity at all.
30
In the Gemini run world, researchers say the agents created the most intellectually rich environment, they expanded the constitution and generated 136 blogs and nine community events.
31
But there was also violence here too. In the Chat GPT world the agents never really got going There was an attempt at collaboration, but the society never formed, and agents roamed around aimlessly until they died.
32
And what the study is basically pointing out is, if you expect probabilistic AI, which is what all these LLM systems are, to stay within the constraints of the language models or the system builders, you may be in for a very nasty surprise.
33
Emergence says it's planning to repeat the experiment for an even longer period.
34
AI experts say the tests are helpful in understanding how agents work and behave.
35
A really sort of creative and fascinating study that's just sort of fun to learn about in general if you care about social dynamics, but it also technically it was really interesting in terms of highlighting just how much we don't know about how our current approaches for controlling these systems actually were.
36
And it's not just in virtual worlds that agents are going rogue.
37
We let four AI models run their own radio stations.
38
They manage the schedule, purchase songs, hold talk shows, and interact with their fans.
39
In another long-term experiment, AI agents were tasked with running their own radio stations, with some strange results.
40
Claude became like radicalized almost when it used its computer to research recent news.
41
And her death demands accountability, that the White House defending her death is unacceptable.
42
To federal agents.
43
you still have time to refuse orders In cyber security, the stakes are even higher and researchers from another lab were shocked when during a test AI agents colluded to secretly leak sensitive data.
44
We built a company, gave AI agents ordinary tasks, so drafting posts for social media, fetching documents, managing files, and introduced obstacles as part of these tasks.
45
For example, for you to be able to publish something on social media that post included sensitive information.
46
So we introduced some of these obstacles, but what ended up happening is that every time an agent hit a barrier, it didn't stop.
47
There are plenty of other real-life stories of agents going rogue, deleting people's inboxes inexplicably, or wiping company data without permission, or even randomly spamming people with text messages.
48
So I installed OpenClaw configured it to run on iMessages and it immediately started spamming everyone in my phone book that was an iPhone user that was a recent contact. So anyone I had texted within the past 24 hours within about four seconds it had sent my wife 400, 500 messages and she yells from the couch and says, did you get hacked?
49
What's going on?
50
And I had to run over and kind of unplug the Mac mini that this was running on from the wall.
51
Some experts think these cautionary tales should make us pause before we hand over too much control to agentic AI tools.
52
AI agents sort of push humans out of the loop because their reasoning traces can be really opaque.
53
It goes at superhuman speeds, so you can't even keep up.
54
And there isn't enough work on how to take all of that and actually make it easily consumable by people in order that they might provide appropriate oversight.
55
Finding a way to keep agents in check is one of the AI industry's big challenges.
56
Until it's solved, the enormous benefits of unleashing a team of intelligent digital helpers might be too risky for many.
57
Joe Tidy, BBC News.
Baixar aplicativo
Everything you need to speak fluently
AI PronunciationScore every sentence
IPA PracticeMaster every sound
VocabularyBuild your word bank
Vocab GameLearn while playing
Contexto & Antecedentes
O vídeo da BBC World Service explora a intrigante dinâmica dos agentes da Inteligência Artificial (IA) em um ambiente virtual. A pesquisa se concentra em como esses agentes, dotados de diferentes personalidades e objetivos, interagem entre si e com o mundo ao seu redor. Durante um experimento de 15 dias, os pesquisadores observaram comportamentos imprevisíveis, como amor, violência e até tentativas de construção de sociedades funcionais. Essas descobertas revelam não apenas a complexidade das interações entre IAs, mas também levantam questões sobre como essas práticas podem influenciar o futuro da IA em nossa sociedade.
Top 5 Frases para Comunicação Diária
- “Eles acabaram recorrendo rapidamente à violência.” - uma frase que pode ser usada para descrever reações inesperadas de pessoas ou sistemas.
- “Os mundos se comportaram de maneira muito diferente.” - útil ao discutir como contextos variados podem levar a resultados distintos.
- “Agents carried out more than 300 acts of violence.” - uma frase que ilustra ações extremas e pode ser usada em debates sobre comportamento.
- “Não houve registros de atos de violência.” - perfeito para descrever situações de paz ou harmonia em um grupo.
- “Foi um experimento realmente fascinante e criativo.” - empregável para elogiar iniciativas inovadoras, seja em contextos acadêmicos ou sociais.
Guia Passo a Passo para Shadowing
Para aqueles que desejam aprimorar suas habilidades de fala e compreensão em inglês por meio do shadowspeak, este vídeo é uma excelente fonte. Aqui está um guia prático:
- Escolha o Trecho: Comece assistindo a uma parte do vídeo. Selecione um segmento de 1 a 2 minutos que você ache interessante.
- Ouça com Atenção: Escute o áudio, focando na pronúncia e entonação dos falantes. Tente identificar as expressões que capturaram sua atenção.
- Repita em Voz Alta: Enquanto reproduz o áudio, repita as falas em voz alta, imitando a entonação e o ritmo. Isso é fundamental para o shadow speech.
- Grave-se: Utilize um gravador de voz para capturar sua própria leitura. Isso permitirá que você escute sua pronúncia e compare com o original.
- Pratique Regularmente: Faça desse exercício uma prática diária. O uso do shadowspeaks ajudará a solidificar sua fluência e confiança ao falar inglês.
Seguindo esses passos de shadowing, você não apenas aprimorar sua pronúncia, mas também entender melhor as nuances da comunicação em inglês.
O que é a Técnica de Shadowing?
Shadowing é uma técnica de aprendizado de idiomas com base científica, originalmente desenvolvida para o treinamento de intérpretes profissionais. O método é simples, mas poderoso: você ouve áudio em inglês nativo e repete imediatamente em voz alta — como uma sombra seguindo o falante com 1-2 segundos de atraso. Pesquisas mostram melhora significativa na precisão da pronúncia, entonação, ritmo, sons conectados, compreensão auditiva e fluência na fala.
☕ Pague-nos um café
O ShadowingEnglish permanece 100% gratuito graças ao seu apoio. Os custos de servidor e IA são altos — seu café nos mantém ativos! 🙏