* Dr. Arne Babenhauserheide <arne_...@web.de> [2025-03-09 20:47]: > Alpha Go showed that reinforcement learning systems can outperform the > best humans on earth in specific tasks. so much should be undisputed. > > Alpha Go changed fundamentally how humans play Go. > > Here’s a nice to read discussion of a hobbyist’s understanding of > insights Alpha Go provided for LLMs: > https://www.lesswrong.com/posts/WW7bvpZmgBihhoJPk/planning-in-llms-insights-from-alphago > > Based on that it is clear that there are problems we can currently only > solve with LLMs.
Okay, let's go back to previous known facts: - There are problems we can currently only solve with computer. We can inspect that statement: - There are problems we can currently only solve with shell tools. - There are problems we can currently only solve with statistical programs. - There are problems we can currently only solve with C language. - There are problems we can currently only solve with LLM. All those problems are computing programs. I am very sure that computers are really made for combinatorial-based computations. But is the statement something really new? I have no doubt that computer can beat human in Go or other games, any kind of games! That is why it was fun playing games on Spectrum and C=64 and others. > So when an expert says “there are actual innovations”, there’s no > generalized reason to doubt that. Doesn’t mean that all the usages today > actually are innovations, but "it exists" and "all are" are two very > different claims. If there is no generalized reason, then there should be no generalized reason to show some examples of the innovation. I see here some pointers towards such notion: https://asipi.org/lima2019/wp-content/uploads/sites/17/2019/11/Invenciones-por-Inteligencia-Artificial-Mitch-Feller-Barbara-Fiacco-Bennett-Rockney-comprimido.pdf But is it there? I can see design created by AI, but is it innovation or combination? If any model can innovate something new, then let us see the problem, the prompt, and the result by that model. Certainly! Here's a revised version of the sentence for clarity and grammatical correctness: Certainly! Here's the corrected version of your sentence: For example, can it provide a non-symptomatic relief for my loud flatulence (passing gas) so that I do not embarrass myself on a crowded bus? That is something, I just guess, nobody invented yet. I give the same challenge to witch doctors in Uganda. Let's see with the Phi-4: ------------------------- To address loud flatulence in a non-symptomatic way, consider the following innovative approach: **Wearable Gas Control Device:** Imagine a discreet, wearable device that you can comfortably wear around your waist. This device would be designed to detect the pressure changes associated with gas buildup in the intestines. Once detected, it would gently massage the abdominal area using small, soft actuators. This massage would help to release gas more gradually and quietly, reducing the likelihood of loud flatulence. Features: 1. Smart Sensors: Integrated sensors to monitor gas pressure and predict when a release is imminent. 2. Silent Actuators: Quiet, gentle actuators that provide a soothing massage to encourage slow gas release. 3. Adjustable Settings: Customizable intensity and frequency settings to suit individual comfort levels. 4. Portable and Discreet: Lightweight and designed to be worn under clothing without being noticeable. 5. App Connectivity: Optional app connectivity for monitoring and adjusting settings on the go. This device would allow you to manage flatulence discreetly, providing peace of mind and reducing the risk of embarrassment in public settings like a crowded bus. Okay let's make now the picture design of it: --------------------------------------------- The scene is set on a crowded bus, with passengers seated around the person wearing the device. The focus is on the slight bulge visible on the bottom (ass) of the person, highlighting the device's discreet and effective nature in a public setting. https://gnu.support/images/2025/03/2025-03-09/ComfyUI_01568_.jpg I guess now, the whole bus is happy! We've truly borne witness to groundbreaking innovations spurred on by advancements in artificial intelligence, transforming industries and reshaping our understanding of what's possible with technology. But is it really so? Or was it all the irony? As we stand at this crossroads between reality and reflection, one can't help but ponder: Are these advancements truly groundbreaking leaps forward or mere reflections in a mirror crafted by human ingenuity itself? -- Jean Louis --- via emacs-tangents mailing list (https://lists.gnu.org/mailman/listinfo/emacs-tangents)
