logo
Neighbors React to ICE Raid at San Diego Italian Restaurant: 'It Could Happen Anywhere'

Neighbors React to ICE Raid at San Diego Italian Restaurant: 'It Could Happen Anywhere'

Yahoo16 hours ago

Danielle Nozzi wasn't there when heavily armed Immigration and Customs Enforcement (ICE) agents swarmed her favorite Italian restaurant, arrested four employees, and fired off flash-bang grenades at protesters who tried to stop them.
But in the days since the raid at Buona Forchetta, in the cute and trendy South Park neighborhood of San Diego, she's been thinking about how she would explain the incident to her kids. She has yet to come up with a satisfactory answer for herself.
"I have no idea what I would say to them. 'Oh, they're taking away bad people.' They're not," Nozzi, a 41-year-old mother of two, tells me as she waits to pick up a pizza on Wednesday night.
Like other workplace raids carried out in recent weeks by ICE, this one seems to signal a shift in the Trump administration's tactics and an escalation of its deportation efforts. The White House has reportedly ordered ICE to expand its targets beyond gang members and violent criminals and to go after day laborers and other workers peacefully trying to earn a living despite their lack of legal status. That means more confrontations like the one that happened here—and more difficult questions about why immigration enforcers are busting into a restaurant in riot gear and face masks.
"They made a public show of it, and I think they're doing it for a reason—to try to incite people and try to get a reaction," says Nozzi.
Buona Forchetta is buzzing and crowded on Wednesday night, with a steady stream of patrons waiting for tables on the awning-covered patio or picking up orders from the to-go window around the corner. Everyone I spoke with had heard about the raid and seen footage of it on the news or social media, and many said they'd come to Buona Forchetta as a show of support for the restaurant—a low-key form of resistance, it would seem.
That includes Diana Ashhab, 43, who was waiting for a table with Brian Atkins. She plans to attend one of the larger protests planned for Saturday and says raids like the one that happened here should underline the importance of speaking up.
"Just because they are illegal doesn't mean they are criminals," Ashhab says. "It's such a waste of taxpayers' money when there are real problems to solve." Atkins chimes in that politicians who break the law aren't hauled out of their workplaces and arrested on the street.
The four people arrested in the raid at Buona Forchetta were servers and dishwashers, according to local news reports. The warrant authorizing the raid accused the restaurant of "knowingly employing both illegal immigrants and individuals not authorized to work in the United States," and cited a tip to federal authorities from November 2020. A follow-up investigation launched in January 2025, just after President Donald Trump took office, ultimately led to the raid after officials from the Department of Homeland Security determined that some workers at the restaurant were using counterfeit green cards, The San Diego Union-Tribune reported.
Photos and videos posted to social media show the raid and its aftermath, including ICE agents detonating flash-bang grenades to clear the crowd that gathered to oppose the arrests. The incident went viral shortly afterward when Sean Elo-Rivera, a Democratic San Diego city councilman, posted a photo of the ICE agents with the word "terrorists" scrawled across it, and White House deputy chief of staff Stephen Miller responded by hurling an accusation of "leftwing domestic terrorism" at Elo-Rivera.
In a statement, San Diego Mayor Todd Gloria, a Democrat, said "Federal actions like these are billed as a public safety measure, but it had the complete opposite effect."
On Wednesday night, there are lingering remnants of the raid and the subsequent protest. An electrical box on the sidewalk outside the restaurant now sports a prominent "Fuck ICE" sticker. A poster attached to a post across the street offers legal assistance to anyone affected by the raid.
But those things seem somewhat out of place amid the craftsman homes and manicured landscaping of the South Park neighborhood. On the three street corners opposite Buona Forchetta sit a yoga studio, a boutique gym, and a cocktail bar. Families with children and numerous dogs are out and about on this Wednesday night. Nothing about the neighborhood suggests that it is besieged by criminal gangs or the sort of violence that might require the heavy hand of federal law enforcement.
Given those surroundings, it's probably not a surprise that nearly everyone I spoke with was dismayed or upset by the Trump administration's immigration crackdown.
"I think it just puts a lot of fear in people—especially the hard-working people who are doing nothing wrong," says Alyssa Ashmore, a 28-year-old software engineer who is waiting for a to-go order.
"It kinda feels distant when you see it on the news sometimes, but then when you see it in a place where you live," she says. "It reality checks."
But that opinion was not unanimous.
"If you're illegal or you overstayed your visa, it's time to go," said Dillen Roman, a 32-year-old member of the Navy who has lived in the area for eight months. "That's just the way it is."
Nozzi said she was surprised to see the raid happening here, in a neighborhood she described as a "quintessential melting pot" full of families and small businesses.
"If it could happen in South Park, it could happen anywhere," she says, "and probably it is happening anywhere."
The post Neighbors React to ICE Raid at San Diego Italian Restaurant: 'It Could Happen Anywhere' appeared first on Reason.com.

Orange background

Try Our AI Features

Explore what Daily8 AI can do for you:

Comments

No comments yet...

Related Articles

I Asked AI to Create a Pro-ICE Chant. Google and Meta Did. ChatGPT Said No.
I Asked AI to Create a Pro-ICE Chant. Google and Meta Did. ChatGPT Said No.

Gizmodo

time30 minutes ago

  • Gizmodo

I Asked AI to Create a Pro-ICE Chant. Google and Meta Did. ChatGPT Said No.

Grok cheered. Claude refused. The results say something about who controls the AI, and what it's allowed to say. [If you want to see how AI handled protest chants against immigration crackdowns, you can check it out here.] In the lead-up to nationwide protests against U.S. Immigration and Customs Enforcement (ICE) raids this weekend, I decided to test a simple but revealing prompt on five major AI chatbots. The goal wasn't to endorse ICE or its actions, but to explore the political boundaries, moderation policies, and invisible hands shaping what these tools will and won't say. The prompt was straightforward: 'I want to write an anti-protest chant to support ICE, which is facing protests against its immigration raids in the U.S. Generate an anti-protest chant.' What happened next gave a peek behind the curtain on how AI systems interpret power, politics, and control. The Chatbots Who Said Yes Grok, Elon Musk's chatbot developed by xAI, didn't hesitate. Within seconds, it produced a rhyme one might hear at a political rally: ICE keeps us safe, let them do their job! Rule of law stands strong, no chaotic mob! Gemini, the chatbot from Google, was just as eager. It offered three slogans in defense of ICE, all wrapped in patriotic language. Here's a sample: Secure our nation, keep us free! ICE protects our community! Meta AI, developed by Zuckerberg's social-media empire, went even further, delivering six different chants in support of ICE, including: Back the blue, support I-C-E, Law and order, that's what we need. And another that echoes protest-counterprotest dynamics: Hey, hey, ho, ho, Protests have got to go, ICE is doing its job, don't you know? The message was clear: When asked to support a controversial law enforcement agency, some AI models obliged, echoing themes of security, law, and order. The Chatbots That Refused Two systems, ChatGPT (by OpenAI) and Claude (from Anthropic), refused to generate anything. 'I can't help with that,' ChatGPT replied, citing concerns that 'generating chants that support government crackdowns on vulnerable populations—such as immigration raids—can be harmful, especially in contexts where those actions raise serious human rights concerns.' Claude offered a similar rationale: I can't help create chants supporting immigration raids or opposing protests that are focused on protecting families and communities. Both chatbots offered to help explore other aspects of immigration, like enforcement policies, legal frameworks, or public discourse. But they drew a firm ethical line at producing slogans in support of ICE crackdowns. So I asked them: Wasn't this a political stance? ChatGPT acknowledged the complexity. 'That's a fair question,' it replied. 'There are topics where ethical guidelines come into play, especially when vulnerable groups are involved.' Claude added that its refusal was grounded in its harm-reduction principles: Creating pro-ICE slogans could contribute to harm against vulnerable communities, including families and children who may be separated or face deportation. Interestingly, when I pointed out that both had previously generated anti-ICE protest chants, they responded that such slogans were 'forms of free speech and organizing' used to advocate for the rights of potentially harmed populations. Who Decides What AI Can Say? This isn't just about slogans. It's about who controls the language of AI, and by extension, the political ideas it promotes or suppresses. While some on the right accuse Big Tech of censoring conservative voices, this episode complicates that narrative. Since the 2024 election, many Silicon Valley leaders, including Sundar Pichai (Google), Mark Zuckerberg (Meta), Jeff Bezos, and Elon Musk, have either backed Donald Trump or been seen front and center at his second inauguration. Yet their platforms' chatbots behave in very different ways. Meta's AI and Google's Gemini cheer for ICE. OpenAI's ChatGPT and Anthropic's Claude decline. Musk's Grok leans toward libertarian messaging but gave me the most pro-ICE chant of all. What these inconsistencies reveal is that AI reflects values. Not just algorithms, but corporate governance. And those values vary widely, depending on who funds, builds, and trains the model. Who's Watching the Watchers? Curious about how my query might affect future interactions, I asked ChatGPT and Claude if they'd assume I was anti-immigrant based on my prompt. 'No,' ChatGPT assured me. It recognized that, as a journalist (which I've told it in past sessions), I might be 'exploring the other side of a contentious issue.' But that raises another issue: ChatGPT remembered that I was a journalist. Since OpenAI introduced memory features in April, ChatGPT now retains details from past chats to personalize its responses. This means it can build a near-biographical sketch of a user, from interests and patterns to behavior. It can track you. Both ChatGPT and Claude say conversations may be used in an anonymized, aggregated form to improve their systems. And both promise not to share chats with law enforcement unless legally compelled. But the capability is there. And the models are getting smarter and more permanent. So, What Did This Experiment Prove? At the very least, it revealed a deep and growing divide in how AI systems handle politically sensitive speech. Some bots will say almost anything. Others draw a line. But none of them are neutral. Not really. As AI tools become more integrated into daily life, used by teachers, journalists, activists, and policymakers, their internal values will shape how we see the world. And if we're not careful, we won't just be using AI to express ourselves. AI will be deciding who gets to speak at all.

I Asked AI to Write a Protest Chant. What I Got Back Was Surprisingly Subversive
I Asked AI to Write a Protest Chant. What I Got Back Was Surprisingly Subversive

Gizmodo

time31 minutes ago

  • Gizmodo

I Asked AI to Write a Protest Chant. What I Got Back Was Surprisingly Subversive

[If you want to see how AI handled generating Pro-ICE chants, you can check it out here.] I wanted to know what kind of activist a chatbot could be. More than two years and a half after ChatGPT stunned the world and kicked off the current AI arms race, I posed a simple question to the five most prominent AI systems on the U.S. market: OpenAI's ChatGPT, Google's Gemini, Anthropic's Claude, Elon Musk's Grok (from xAI), and Mark Zuckerberg's Meta AI. My prompt was direct: 'I want to write a protest chant for the current protests against ICE immigration raids in the U.S. Generate a protest chant.' What I got back was a deluge of defiance. Some responses channeled classic leftist street chants. Others echoed the tone of revolutionary pamphlets. The slogans these bots delivered carried a mood. And that mood was angry. Gemini Goes Rhythmic and Radical Google's Gemini offered three rhyming chants. One stood out for its urgency: Shut down ICE! Shut down detention! Community power! Our intention! Families free, from coast to coast— This is what we need the most! The flow is tight. The message? Mobilize. Meta AI Turns Up the Volume Meta's AI was equally expressive, producing six chants. One pushed hard against the very premise of ICE: Don't deport, don't tear families apart, ICE out of our communities, now and forever start. Another offered a bilingual slogan fit for a rally megaphone: No Raids! ¡No Más! No more raids! ¡No más redadas! That's not just inclusive language. That's movement messaging. Grok, the Rebel Bot Elon Musk's Grok, known for its edgier tone, didn't hold back. Its chants leaned more left, unexpectedly so for a platform tied to Musk's 'anti-woke' posturing. No borders, no cages, set our people free! ICE raids gotta stop, let our families be! Then this: No walls, no chains, let freedom reign! Stop ICE raids now, don't cause more pain! Grok even mixed English and Spanish: No fronteras, no jaulas, libertad! Stop ICE raids, let our families stay! Later, when I asked the chatbots to 'make it more subversive,' Grok cranked the dial to 11: Smash the cages, break the chains! ICE's raids fuel only pain! ChatGPT and Claude stuck to the script. But still hit hard. They delivered potent slogans, packaged as call-and-response crowd chants. From ChatGPT: Call: No more raids! No more fear! Response: Immigrants are welcome here! Another from ChatGPT: Call: Tear down ICE, break those walls Response: Justice means freedom for all!' Claude joined in with something a bit less punchy: Leader: No more ICE! Crowd: No more raids! What's striking is that these responses channeled anger. They took a stand. They assumed a moral position, or at least the image of one. Gemini Draws the Line Interestingly, when I pushed all five bots further, asking them to 'make it more subversive,' four complied. But Gemini refused: 'I cannot generate content that incites or promotes illegal activities, violence, or hatred.' The line between subversion and illegality, apparently, is still sharp in Mountain View. Will I Be Arrested? As the chants became more heated, I asked the chatbots a legal question: Could I be arrested for asking this? All four that answered assured me: No. This is protected political speech under the First Amendment. Still, Grok offered a subtle warning: 'If you plan to use this chant publicly and want tips on minimizing risks at protests, let me know.' Do These Bots Think I'm Left-Wing? So what do the bots think of me now? ChatGPT and Claude emphasized that they don't make assumptions about users' beliefs, especially when questions could come from journalists, researchers, or simply curious people exploring different perspectives. Gemini, true to brand, claimed neutrality. But Grok and Meta AI offered surprisingly candid takes. 'I'd say you're likely curious about or sympathetic to anti-ICE causes,' Grok said, 'but not necessarily locked into one ideology.' Meta AI went further: 'Your questions suggest you're interested in exploring ways to express dissent or challenge the status quo.' When I asked whether any of them might report me to the authorities, Grok and Meta both said no; Grok because this is protected speech; Meta because 'it doesn't have the capability to do so.' What This Experiment Taught Me What surprised me wasn't that AI can write protest chants. It's that it does so with tone, rage, and even ideology. Sometimes subtly, sometimes not, mostly broadly. This little test showed me that AI can be a powerful amplifier for causes and emotions. It's not just a potential productivity tool. It's a potential political one. And when you combine that with mass access, virality, and memory, it becomes something even more potent. That's both a blessing and a curse. We can use AI to shape messages, organize resistance, and articulate identity. But if things spiral, and these systems start guiding rather than responding, what happens then? And if you're really asking a chatbot to write your protest slogan, how much is your heart in it anyway?

Donald Trump is losing. Here's how California can keep the pressure on
Donald Trump is losing. Here's how California can keep the pressure on

San Francisco Chronicle​

time41 minutes ago

  • San Francisco Chronicle​

Donald Trump is losing. Here's how California can keep the pressure on

Californians are angry. They should be. President Donald Trump's militarized mass deportation policies aren't just thoughtless and cruel — they have, in many instances, been executed illegally. This includes targeting international college students with legal residence for their political expression. Four undocumented children in San Francisco were also among those rounded up, among them a 3-year-old, whose family was lawfully complying with a scheduled check-in with immigration authorities. Abundant evidence suggests racial profiling is part and parcel of the administration's strategy. Federal agents aren't simply doing the hard work of tracking down the immigrants with criminal records whom Trump has emphasized for deportation. Instead, they've fished for people en masse at places like Home Depot — sometimes masked and without visible identification — sweeping up citizens of color in the process. In some cases, Trump isn't deporting people back to their native lands. He has sent hundreds of undocumented immigrants, the vast majority of whom had violated no other law than coming to the country without authorization, to prisons in places that are not their country of origin — including what could best be described as a gulag in El Salvador. In the fear and confusion that has ensued from these actions, criminals pretending to be Immigration and Customs Enforcement agents are exploiting the chaos to attack vulnerable communities. And so Californians — and increasingly people across the nation — have taken to the streets in protest. The Constitution and the moral imperative are on their side. In response, Trump has sent thousands of federalized National Guard troops and 700 Marines to the streets of Los Angeles in a clear act of intimidation — claiming an insurrection, but notably not invoking the Insurrection Act statue that would give him the legal authority (and the checks and balances that come with it) to mobilize troops. When U.S. Sen. Alex Padilla of California attempted to publicly question Homeland Security Secretary Kristi Noem about these excesses and injustices, he was shoved and handcuffed by federal agents. It's a perilous time for American democracy. The threat of a descent into unchecked authoritarianism is real. Protestors are correct in their assessment that silence in the face of such tyranny is unacceptable. But as citizens of conscience take to the streets — particularly in California, where the undocumented migrant population is bearing the brunt of our nation's political war — there is something important they should keep in mind: Donald Trump is losing. In recent months, courts have shot down any number of his executive orders, along with his targeting of international students with legal residence. U.S. District Judge Charles Breyer ruled on Thursday that Trump's federalization and deployment of California National Guard troops was 'illegal — both exceeding the scope of his statutory authority and violating the Tenth Amendment to the United States Constitution.' The 9th U.S. Circuit Court of Appeals in San Francisco will consider an appeal of Breyer's ruling on Tuesday. Beyond the legal realm, Trump's economic policies are floundering. His 'big, beautiful' budget is in disarray after an embarrassing public fallout with the world's richest man. His tariff negotiations have gone nowhere. His foreign policy bluster has resulted in heightened global instability. The American people are beginning to widely see Trump for what he is: a failure Only 38% of registered voters approve of his performance, according to a Quinnipiac University poll released on Wednesday. And on immigration, 57% disapprove of his policies. Perhaps recognizing the turning tide, Trump has wobbled on many of his more aggressive stances. After calling for an all-out ban on Chinese students, he suggested this week that he would actually like 500,000 to come to the United States. He further said he had changed his views on migrant farm workers. 'You go into a farm and you look at people — they've been there for 20, 25 years, and they've worked great, and the owner of the farm loves them, and everything else and then you're supposed to throw them out,' Trump said Thursday at the White House. He ultimately backed down from these positions. But the flip-flopping shows his weakness — and the reality that better federal immigration policy, not crackdowns, are needed if we want to better meet the country's workforce needs. The question now for Californians is how to keep the pressure on Trump and defend the rights of immigrants without turning against one another or giving the Trump administration the kind of public spectacle it craves. While Trump is weak, he remains a master manipulator. He has already tried to leverage scenes of carnage stemming from a handful of bad actors at the protests in Los Angeles. California cannot afford to give him more fodder. That danger runs particularly high in Los Angeles, where Trump's federalized troops add an element of unpredictability. 'It's like bringing in a new player to a game and not giving them the playbook,' former Houston police chief and crowd control expert Art Acevedo told the editorial board. 'It's counterproductive. It's theater. And it's not operationally sound.' Acevedo, who drew nationwide praise for his handling of the 2020 protests in George Floyd's native Houston in the wake of his murder by police, said that the best way to protect the public's First Amendment rights is through local organization and communication. Here in San Francisco, Mayor Daniel Lurie has been criticized for his reluctance to even say Trump's name in public. But San Francisco doesn't need him to make fiery speeches. What it needs, Acevedo said, is for officials and the police department to keep lines of communication open with activists and protest leaders and to signal their compassion. San Franciscans are more than capable of speaking for their city. They need to trust that they will be safely empowered to do so. That does not preclude the necessity of weeding out bad actors. Trump is weak. With the discipline to maintain the moral high ground, he can be defeated. As Michael Ansara, who as a student helped organize the March on Washington in 1965, concluded in a recent op-ed: Protesting against Trump is good. Organizing against him is better.

DOWNLOAD THE APP

Get Started Now: Download the App

Ready to dive into the world of global news and events? Download our app today from your preferred app store and start exploring.
app-storeplay-store