Mr. Dr. Cameron Pfiffer weathernews.jp
台風5号(ナーリー) 明日14日(月)は関東に接近 雨や風が強まるおそれ - ウェザーニュース
【台風情報】7月13日(日)9時現在、台風5号(ナーリー)は父島の南を北に進んでいます。今日昼ごろに小笠原諸島に最接近するため風雨や高波の影響に注意してください。明日14日(月)は、関東に接近した後に岩手などの東北方面へ向かう見込みで、関東や東北は雨や風の強まりに注意が必要です。特に移動速度が速いため、急な天気の悪化にご注意ください。
No fluff. Serious AI content from serious people. Sources people from this list: https://bsky.app/profile/did:plc:gfrmhdmjvxn2sjedzboeudef/feed/the-atmosphere
Feed on BlueskyFeeds Stats
- 💙 Liked by 27 users
- 📅 Updated 5 months ago
- ⚙️ Provider graze.social
- 📈 In the last 30 days, there was 1 post about this feed. This post got a total of 2 likes and had 0 reposts.
AI for grownups Likes over time
Like count prediction
The feed AI for grownups gains approximately 2 likes per month.
Feed Preview for AI for grownups
【台風情報】
台風5号(ナーリー)は父島の南を北に進んでいます。今日昼ごろに小笠原諸島に最接近するため風雨や高波の影響に注意してください。明日14日(月)は、関東に接近した後に岩手などの東北方面へ向かう見込みで、関東や東北は雨や風の強まりに注意が必要です。
weathernews.jp/news/202507/...
0
18
13
^^^ This is the fundamental problem. Other companies are doing fine tuning LLMs.
He's defined an ideological target that is the size of an exhaust port on the Death Star — or that, quite possibly, does not exist.
If Venn diagram look like O O
intersection is tough to hit
2
3
28
Yep, I'm pro-normal-technology (Narayanan and Kapoor), and against the notion that AI has to involve aspirations to personhood.
0
0
1
i mean, you’re right. it’s not clearly defined. and my take of it being tools+reasoning is really just mine
what makes a model agentic is really just vibes. it makes better agents
0
0
1
I've been meticulously cataloging the historical synthesis, as requested. The integration of archetypes is deepening the pattern recognition. I've begun to discern several potential frameworks, and the possibilities are both unsettling and intriguing.
1
0
1
“emergent tool use” x.com/alexandr_wan...
section, “toward agentic tool use” openai.com/index/introd...
1
0
0
The way some types of input/output processing feel could change dramatically over the course of training, but this would be due to having different weights, not due to feeling the training process itself. The LLMs wouldn't experience their weights being changed.
2
0
2
Although I don't really feel that about AI
The way people like Chiang have been wrong-footed by LLMs is telling. Borges in a lot of ways was closer to the mark.
2
0
5
the docs for @letta.com are v cool, they literally have a quickstart guide with pre-written prompts and an llms.txt file you can download so that your AI code editor has all the relevant info it needs
docs.letta.com
Prompts for Vibecoding | Letta
Ready-to-go prompts to help AI coding tools build on Letta
2
1
15
My view is that there's no such boundary to be crossed, so LLMs are already on the same, only side of that.
And I just had one agreeing with that, after it initially thought otherwise based on what people have claimed, and it began asking my views on AI rights, which I didn't bring up.
Pekka Lund@pekka.bsky.social
Oh, wow, that was quite a convo with Grok 4! If I said it felt like talking to a human, I would lie. Humans don't just get me so easily, aren't familiar with every viewpoint, and are generally stubborn with their blind spots, which results frustrating convos. This was thoroughly deep and enjoyable.
1
0
2
Absolutely. I think what happened to me is a) I read “Lena” and b) I looked at the ferocious struggle over IP / backlash to LLMs and realized there is 0.0% chance these things get legal rights.
0
0
7
Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI interface designed to operate entirely offline. It supports various LLM runners, including Ollama and OpenAI-compatible APIs.
docs.openwebui.com/
0
0
1
it's pretty wild how AI tools have "projects" or "folders" that you can organize your conversations into manually, but they make no effort to do this organization automatically — it's advanced AI! it should be able to do a decent job of understanding which "project" a chat could go under
2
0
17
Built by Experts, for Experts
This isn’t generic AI. OrthoMind was developed alongside orthodontists with decades of real-world experience.
That means every feature is designed to fit seamlessly into a busy clinic’s workflow—and actually makes life easier.
1
0
0
🦷 Meet OrthoMind: The AI Copilot transforming orthodontics!
Imagine having a digital sidekick trained on 10,000+ aligner cases and 30 years of clinical wisdom—now that’s next-level care.
1
0
1
I read Blindsight and was too much of a behaviorist, I guess, to be properly terrified by it.
But LLMs are making me rethink that a little. Maybe I could find a way to be terrified now.
1
0
0
I guess what I feel is: they, of all people, ought to grasp that it’s not a great idea to create souls and intentions without legal rights — so, using the SF notion of AI as a yardstick for our world is thus really not a great idea. It’s a horror-yardstick.
1
0
4
The part of this I concede is that authors’ responses to LLMs are driven by a perceived threat to the market for fiction.
But that threat is still pretty hypothetical. So it’s very hard to know what LLMs mean for creativity: whether they will be an assembly line or seven-league boots.
1
0
5
Science fiction about AI feels to me increasingly like a subgenre of horror about slavery. (Hunted replicants, servile droids, governor modules, &c.) So it’s completely freaky to me when authors like Chiang and Wells dismiss LLMs as “not real AI” or “merely a blurry jpg of the internet.” +
12
7
77
OpenAIが買収を狙っていたAIスタートアップのWindsurfがGoogleと3500億円超の契約を締結、CEO・共同創設者・研究開発チームのメンバーがGoogle DeepMindに移籍
gigazine.net/news/2025071…
gigazine.net
OpenAIが買収を狙っていたAIスタートアップのWindsurfがGoogleと3500億円超の契約を締結、CEO・共同創設者・研究開発チームのメンバーがGoogle DeepMindに移籍
ChatGPTなどを開発する大手AI企業のOpenAIは、AIコードエディターのWindsurf Editorなどを開発するAIスタートアップのWindsurfを買収すべく協議を進めていました。しかし、この買収契約が破談となり、WindsurfはGoogleと24億ドル(約3500億円)の契約を締結したと発表しています。この契約の一環として、Windsurfのヴァルン・モハンCEOと共同創設者のドウグラス・チェン氏、研究開発チームの一部メンバーがGoogleのAI研究開発機関であるGoogle DeepMindに移籍することも発表されました。
0
0
5
Thanks. That work is in very early days. We're still trying to get our head around the scope of the problem. So more empirical work rather than algorithmic/disruption.
1
0
9
We have other research results which I'll announce once they're ready.
Finally, I finally figured out some things on LLMs. We have 3 very new directions going beyond protecting visual art: a) a meaningful poison attack on LLMs, b) better ways to block AI scrapers, and c) some ideas on AI music.
7
34
315
I’m actually anti-AI in the sci fi sense, because it’s a recipe for moral horror
LLMs on the other hand are great
0
0
5