2026年8月19日のHacker News レーダー

“My coworkers continue to dump hundreds of lines of AI documentation in every PR and every other line of code has between one and ten lines of AI generated comments, talking about the real unlock and how things are byte for byte identical on the load bearing…”

“I think the main reason many people (including me), very often, lack the motivation to read content that is likely generated by AI is the suspicion that it comes from a place of intellectual laziness. Another reason, based on personal experience, is that AI…”

“The part that astonishes me is that in the year of our common era two thousand twenty-six that it's not universally offensive and reviling to post an AI-generated response to another person. If I'm reading something on the internet, I'm either reading it to…”

“I really like the point I read somewhere the other day; instead of sending me the AI output, just send me the prompt you used to generate it. That is the only part that contains only the information you are trying to convey. The rest is just guesses flowery…”

“> I think it is fundamentally a crisis of trust. I think that ordinary people don’t trust companies, governments, or the tech industry and always suspect that we are cooking up some new way to screw them over. [...] > I don’t think that a glitzy marketing…”

“> We are however doing our best to fix this: Anthropic is ramping up its efforts very quickly in biology and medicine, and we hope to have incredible results in the coming years and some early glimmers in the coming months. When we’ve actually accomplished…”

“I genuinely think Dario is a well intentioned, intelligent dude, but I think him and Anthropic have a huge PR problem and are really out of touch with how they're perceived. Anthropic in particular has developed this almost Orwellian like veil of…”

“> Overall my view is that AI is structurally a technology that tends to concentrate power, for reasons that have nothing to do with regulation (more to do with the extreme implications of the scaling laws). Open-weights do help some with this but are nowhere…”

““The fact that a 17GB file can do all of this stuff on my home machines is a miracle. Once again, I’m delighted and amazed at how much progress local models have made this year.” I think that should be the blinking headline - this shows what can be done with…”

“I run mine on an M5 Max with just 48GB of (V)RAM, and it fits nearly twice in Q4. Works perfectly. I'm kinda glad I didn't spend the extra $2400 to get 128. We don't really need more... and that's a good thing (tm). God knows I thought about it in store. But…”

“This is true, but I think it understates the problem. I did a task I've done with a bunch of small models lately (https://github.com/swelljoe/flar/pull/17), and it did an excellent job, the best of any self-hostable model. But, it took eleven (11!) hours on…”

“The big problem with overthinking on a dense model is obviously the speed hit you take. Going from Qwen 35BA3B to 27B for me is about 7-8x slower (should be ~9x?). This makes me a lot less patient for useless thinking tokens. I’d want to compare this to the…”

“I forked llama.cpp and added some crude mechanism to keep exactly this behavior under control - essentially guiding the reasoning process by injecting text strategically at specific thresholds. This was mainly put together to rein in Qwen3.6-27B, but I'd…”

“I feel like the current “reasoning” that LLMs are doing has got to be a dead end eventually. Every time I have to read another answer with “but wait” and “Actually,” as they “reason” their way to a (sometimes) better answer, I feel like there’s got to be a…”

“Crazy how a smart person like this fails to understand the gumbel softmax technique. It does not affect writing quality at all, provably. The very fact that there is generally no "best next token" with 100% certainty is precisely why the trick works (you…”

“> “By definition it must make text worse … because the nature of the watermarking algorithm requires it to sometimes increase the probability of selecting a worse word choice and decrease the probability of selecting the model’s best choice.” Gruber made an…”

“My biggest concern is that checking any text for watermarks requires sending the entire text to Anthropic. And even that is not sufficient, as the text might have been generated with ChatGPT, Gemini, Grok, Mistral, ... So every check requires sending the text…”

“Gruber shows here that he really doesn’t understand the basics of how LLM text generation works. It’s weird he picked this battle about the quality of writing in LLMs. Was he planning to use LLMs to write his articles? Well, not that weird actually. He just…”

“> "The exact words we choose when writing matter." Then write your own damn text if you care about the exact wording so much”

“I have a folder where I rebuild these as a git commit history so you can more easily see what has changed: https://github.com/simonw/research/commits/main/extract-syst... For example here's what changed between Opus 4.8 and Opus 5:…”

“> A prompt implying an image is present doesn't mean one is (the person may have forgotten to upload it), so Claude checks for itself. Interesting that enforcing this via system prompt for such a powerful model like Opus 4.8 doesn’t feel like the Anthropic…”

“Those are remarkably longer than I would expect, or think is warranted. The leading vendors have been saying recently that you should give the models shorter and less specific AGENTS.md (or whatever) files, and in my experience, that's good advice. The models…”

“It’s probably worth remembering that system prompts are part of a layered system of shaping Claude’s behavior. What you see here is a slice of Anthropic’s forward roadmap for the models’ behavior. > When a person is in crisis or expressing distress, Claude…”