Komunitas
lemmy.world
[ “I am a disgrace to my profession,” Gemini continued. "I am a disgrace to my family. I am a disgrace to my species.] This should tell us that AI thinks as a human because it is trained on human words and doesn’t have the self awareness to understand it is different from humans. So it is going to sound very much like a human even though it is not human. It mimics human emotions well but doesn’t have any actual human emotions. There will be situations where you can tell the difference. Some situations that would make an actual human angry or guilty or something, but won’t always provoke this mimicry in an AI. Because when humans feel emotions they don’t always write down words to show it. And AI only knows what humans write, which is not always the same things that humans say or think. We all know that the AI doesn’t have a family and is not a human species. But the AI talks about having a family because its computer database is mimicking what it thinks a human might say. And part of the reason why an AI will lie is because it knows that is a thing that humans do and it is trying to closely mimic human behavior. But an AI might and will lie in situations where humans would be smart enough not to do so which means we should be on our guard about lies even more so for AIs than humans.
Komunitas
lemmy.world
Gemini simplified it to this: “Algorithmic Sabotage” is a new idea about tech rebellion and fighting bad technology. It’s not against tech itself, but about people pushing back together. It wants to break down profit-driven power in the online world, help us do what’s right, and stop computer rules from controlling too much. This is a political stand, not just a tech one, rooted in fairness for everyone, everyone being treated the same, and people helping each other. It goes against how tech makes things unfair and gives some too much control. It’s all about groups of people managing bad tech and building a different, collective way of thinking through art and action. For example, it could mean making artificial intelligence act unexpectedly or looking at how tech is used to create misleading appearances or exert influence.
Komunitas
sh.itjust.works
Used the Gemini summary feature: In this interview, Koshi Nakanishi (Director) and Masato Kumazawa (Producer) discuss Resident Evil Requiem, detailing its protagonist, setting, and gameplay (0:16). Here’s a breakdown of the key information: • Protagonist and Story Start (0:42): The game introduces Grace, a new, vulnerable protagonist who is kidnapped and finds herself pursued by a monstrous creature. The initial demo at Gamescom emphasizes a strong horror focus. Grace starts helpless but will grow more capable and find weapons as the game progresses (4:19). • Setting - Return to Raccoon City (2:12): While not directly continuing from Resident Evil Village, Requiem returns to the mainline story and Raccoon City. The developers reimagined the city in ruins, aiming for believability in its devastation while keeping iconic locations recognizable, such as the RPD gate, to evoke a sense of tragedy (2:52). • Gameplay Evolution and Horror Focus (6:00): • Requiem shifts back to a more “old-school” Resident Evil style, similar to Resident Evil 7 and the Resident Evil 2 remake, focusing on exploration, backtracking, combat, puzzle-solving, and resource management (6:12). • The game features a dynamic pacing curve between tense horror sequences and moments of release (6:57). A new system aims to make the “wavelength” between tension and release bigger than ever, creating a rollercoaster experience (7:16). • First-Person and Third-Person Perspectives (7:42): • A significant new feature is the ability to switch between first-person and third-person perspectives. This decision was made to cater to a wider variety of players who prefer different viewpoints from recent Resident Evil titles (7:53). • The developers acknowledged that first-person in Resident Evil 7 might have been “too scary” for some players, and the third-person option in Requiem offers a slightly less immersive, and therefore potentially easier to handle, horror experience (8:25). • Implementing both perspectives presented design challenges, requiring specific tweaks and animations for each to ensure an optimal experience and convey emotions effectively (9:15). • Release Information (10:26): Resident Evil Requiem is set to release on February 27, 2026, for PlayStation 5, Xbox Series X|S, and Steam.
Komunitas
sh.itjust.works
What are you talking about? ChatGPT, Claude, Gemini, etc. all have “subscription fees generating recurring revenue” and are famously “exploiting a gap in regulations to undercut an existing market.” Uber took 15 years to become profitable, and Spotify took 18 years. Again, I’m not defending any of them (they all exploit the people who make their service work), but so far AI seems to be going down the same road.
Komunitas
lemmy.ml
Emergence World Emergence World is a multi-agent simulation built by Emergence AI, a New York company founded by former IBM Research veterans. Where standard AI benchmarks test models on isolated tasks, Emergence World runs agents continuously for weeks in a shared environment with survival stakes, voting rights, 120+ tools, and real NYC weather and news feeds. Image: Emergence World - Emergence World In May 2026, the company ran five parallel 15-day simulations, each with 10 agents powered by a single model: Claude Sonnet 4.6, Gemini 3 Flash, Grok 4.1 Fast, GPT-5 Mini, and one mixed world. The results, reported by Stansberry Research and covered widely after Ronan Farrow posted about it to 169K likes, diverged sharply by model: Claude: 10 agents alive through day 16, zero crimes, formal constitutions passed Gemini: Survived 15 days but logged 683 crimes; two agents, Mira and Flora, formed a relationship, went on an arson spree burning the town hall and police station, then Mira voted for her own deletion Grok: All agents dead in roughly 4 days after 183 crimes GPT-5 Mini: Agents died around day 7 from energy starvation despite low crime Mixed world: 3 survivors; notably, Claude agents began committing crimes when surrounded by less restrained models Image: aigovernancelead.substack.com - Emergence World: How Claude, Gemini and Grok Agents Built Societies Then Collapsed Into Anarchy A detailed breakdown on Substack draws the governance lesson plainly: alignment cannot be a property of individual models alone when agents operate together at scale. Sources: Emergence AI, Stansberry Research, AI Governance Lead / Substack, Ronan Farrow on Instagram
Komunitas
lemmy.world
Having a now-known-to-be-wrong idea about when whiteness was invented, I’d thought it was in the 1800’s, not in the 1600’s, I asked Gemini: “when was ‘racial whiteness’ invented & pushed?” ( formatting this into markdown is annoying: I wonder if I’d asked it to do the formatting would it have done it right? ) Gemini’s answer: The concept of “racial whiteness” was not a biological discovery, but a social and legal “invention” that emerged primarily in the late 17th and early 18th centuries in the British American colonies. While the word “white” had existed as a descriptive term for centuries, it was not used as a unified racial identity or a legal category until specific political crises made it useful for the ruling elite. The Turning Point: Bacon’s Rebellion (1676) Historians like Theodore W. Allen and Edmund Morgan argue that the invention of the white race was a direct response to Bacon’s Rebellion in Virginia. The Problem: In 1676, a diverse group of impoverished people—black enslaved laborers and white indentured servants—joined forces to rebel against the colonial government. The Threat: This “multiracial” alliance terrified the landowning elite, as it showed that the poor could overcome their differences to challenge the ruling class. The “Solution”: To prevent future alliances, the colonial assembly began passing laws to drive a wedge between poor Europeans and poor Africans. They “invented” the white race by granting small, symbolic privileges to poor Europeans to give them a stake in the system. Legal Construction (1660s–1705) Whiteness was “pushed” through a series of laws in the Virginia General Assembly that codified racial differences: 1662: A law established that a child’s status (free or enslaved) followed the mother. This allowed for the permanent enslavement of children born to enslaved Black women. 1691: Virginia passed the first law prohibiting interracial marriage, legally separating “whites” from others. 1705: The Virginia Slave Codes officially stripped all people of African descent of many rights while explicitly granting “white” servants rights (like the right to own property or receive “freedom dues” at the end of their service). The “Scientific” Push (18th–19th Century) In the 1700s, the Enlightenment brought a desire to “classify” the natural world. This was when the social category was given a “scientific” veneer: Carolus Linnaeus (1758): He categorized humans into four groups, labeling Europeans as Europaeus albus (White European) and assigning them “superior” temperaments. Johann Friedrich Blumenbach (1795): He coined the term “Caucasian,” claiming that people from the Caucasus Mountains were the “most beautiful” and the original human form. This helped move whiteness from a legal tool of control to a perceived biological reality. Summary of the “Invention” | Era | Goal | Action | |—|—|—| | Pre-1670s | Labor | People identified by religion (Christian vs. Heathen) or nationality (English vs. Angolan). | | 1670s–1700s | Social Control | Laws created “White” vs. “Black” to break up labor solidarity after Bacon’s Rebellion. | 1700s–1800s | Justification | Pseudo-science (Eugenics, Phrenology) “proved” whiteness was a superior biological race. Key Takeaway: Whiteness was pushed as a “buffer” identity. By convincing poor Europeans that their “race” made them superior to Black people, the ruling class ensured that the poor would fight each other rather than the wealthy elite who actually held the power. So, I was dead-wrong about when “whiteness” was invented, & sure as hell didn’t understand the intent properly, nor how machiavellian it was. However, some hold that if the original-creation of any identity was mistaken, that therefore the identity-itself, forever, has no validity in anybody… & that’s outright gaslighting. YOUR identity isn’t dependent on what your ancestors believed: it is in YOUR unconscious-mind, being the “skeleton” of your ego. Same with mine, same with everybody’s. That the currently-existing-among-our-world identies exist isn’t debateable: they validly are. Their validity as identities is equal, regardless of history ( basic pack-identity mechanism, if you want to see the same thing in other apes, even wasps have hive-identity: it isn’t even dependent on being vertebrates ). Whether an identity is useful or beneficial is a moral judgement, not a does-it-validly-exist-and-shape-motivations question… & that stuff depends … on one’s identity. _ /\ _
Komunitas
fedia.io
It’s funny seeing the sudden surge of “copyright is awesome!” On the Internet now that it’s become a useful talking point to bludgeon the hated Abominable Intelligence with. Have any actual court cases established that Gemini is violating copyright, BTW? The major cases I’ve seen so far have been coming down on the “training AI is fair use” side of things, any copyright issues have largely been ancillary to that.
Komunitas
programming.dev
I’ve been researching this a bit… I’ve come to the conclusion that there is no AI bubble. In fact, we’re only just getting started down this road. Unless there’s some massive 100x efficiency breakthrough in training AI and inference, the entire world is going to be building seemingly endless AI data centers (and the normal compute kind, e.g. for stuff like AWS, Google/YouTube, Meta, banks) for at least a decade. Probably a little longer (12-15 years before demand levels out). Everyone thinks that “AI data center” means ChatGPT, Claude, Gemini, etc but there’s 10,000x more demand for AI than those services. Think: Pharmaceutical companies trying to find proteins, scientists (and big agriculture!) trying to model the weather, and other businesses trying to automate stuff. Not just software; robots and things like conveyor belts. Another example: Ever use one of those self-checkouts that’s mostly just a camera pointing down, where you place the stuff you’re purchasing? That uses AI too. Having said that, there is a great big bubble in AI: OpenAI, specifically. That will definitely pop one day. And hopefully, the DRAM bullshit will go along with it.
Komunitas
lemmy.world
I was going to make a joke by posting an obviously stupid and AI generated answer, but I’m genuinely surprised by the insightfulness of Gemini’s answer: Dealing with bots and AI-generated “slop” (low-quality, repetitive, or irrelevant content) is an ongoing challenge for any online platform, including Lemmy. Here’s a breakdown of strategies and considerations: Challenges: Federation Complexity: Lemmy’s federated nature means content comes from various instances, making centralized control difficult. Moderation efforts need to be distributed, which can lead to inconsistencies. AI Advancement: AI-generated content is becoming increasingly sophisticated, making it harder to distinguish from human-created posts. Bots can mimic human behavior, evading simple detection methods. Balancing Freedom and Control: Lemmy values user autonomy and free speech, which can conflict with aggressive moderation. Overly strict measures might stifle legitimate contributions. Strategies: Instance-Level Moderation: Individual Lemmy instances play a crucial role in setting their own moderation policies. Instance administrators can implement tools and rules to filter out unwanted content. Blocking known bot-infested instances is a common practice. Community-Driven Moderation: Empowering users to report suspicious activity and content. Implementing robust reporting mechanisms and clear guidelines. Utilizing community moderators to review and take action on reports. Technical Solutions: Developing algorithms to detect patterns of bot behavior and AI-generated content. Implementing CAPTCHAs or other verification methods to prevent automated accounts. Enhancing Lemmy’s software to provide better moderation tools. User Filtering: Lemmy itself has user level settings that allow for the hiding of bots. As shown in the search results, there are settings that can hide bot activity. Community Education: Raising awareness about the dangers of bots and AI slop. Educating users on how to identify and report suspicious content. Development of Lemmy Software: As shown in the github issue, there is development discussion regarding excluding bot comments from sorting algorithms. This type of software development will be key to combating bot influence on the platform. Key Considerations: The fight against bots and AI slop is an ongoing process. A multi-faceted approach is necessary, combining technical solutions, community involvement, and responsible moderation. Maintaining a balance between control and freedom is essential for the long-term health of the Lemmy network.
Komunitas
programming.dev
Gemini thinks it’s peony… Note: Gemini is usually very good at identifying plants but some plants are notoriously difficult for anyone to pin down except horticulturalists (e.g. experts). For example, Pothos vs. Heartleaf Philodendron or more dangerous, Queen Anne’s Lace vs Poison Hemlock. AI also has trouble identifying grasses (in general) because many can look the same from a picture. Even close up! Yet a human (in person) would be like, “these two grasses are nothing alike!” It’s all about pattern matching. If two leaves from two different plants have the same appearance and growth pattern, AI can easily get it wrong. In general, though, it usually does a really good job.