Yan Dao

Evil genius

[Zlatan Ibrahimović @Ibra_official]

From another planet

[OptaJoe @OptaJoe]

1 - This is the first time in World Cup history that three different players have scored 7+ goals in a single edition of the tournament

🇫🇷 Kylian Mbappé: 7 goals
🇦🇷 Lionel Messi: 7 goals
🇳🇴 Erling Haaland: 7 goals

Legendary.

[Gearoid Reidy リーディー・ガロウド @GearoidReidy]

Toshifumi Suzuki, the "father of the conbini" and the man who created the modern Japanese convenience store, has died at the age of 93.

He set up the 7-Eleven chain of convenience stores in Japan in the 1970s and came up with the idea of selling onigiri, before being ousted in a power struggle in 2016.

[BoA Official @BoA_Official]

You still our No.1 BoA

https://t.co/fbbVJeARTF

#BoA #보아
#You_still_our_No_1_BoA

[Yan Dao @yandao]

LOL, 3000

[GitHub Projects Community @GithubProjects]

Grab your own sweet-looking '.is-a.dev' subdomain

[Carlos E. Perez @IntuitMachine]

Someone figured out a surprisingly simple way to make AI agents better at their jobs: just give them a personality.

I just read a paper on "Psychologically Enhanced AI Agents," and it's a fascinating look at how we can steer AI behavior without any complex or expensive retraining.

Here's the context: Normally, if you want an AI to be good at a specific task (like creative writing vs. strategic analysis), you have to do costly and time-consuming "fine-tuning."

The problem is that a generic, one-size-fits-all AI often isn't the best fit. A model optimized for factual recall might not be great at generating an empathetic, emotional story.

The key finding is a framework called MBTI-in-Thoughts. By simply telling an LLM to adopt a specific Myers-Briggs (MBTI) personality type in its prompt, its behavior changes in predictable and useful ways.

For example, in a strategic game:

"Thinking" (T) type agents chose to defect nearly 90% of the time.
"Feeling" (F) type agents were more cooperative, defecting only about 50% of the time.
This was achieved with just a prompt, no fine-tuning needed.

What makes this so interesting is its unexpected simplicity. The ability was there all along, latent within the model. The prompt just acted as a key to unlock it.

To make sure it wasn't just a fluke, the researchers had the primed AI take the official 16 Personalities test. The AI's answers consistently matched the personality it was assigned. It truly "became" that type for the task.

This completely changes how I think about prompt engineering. It’s no longer just about what you ask the AI, but who you ask the AI to be.

The practical applications are immediate:

Need an AI for empathetic customer support? Prime it as an ISFJ ("The Defender").
Need one for ruthless market analysis? Try an ENTJ ("The Commander").
You can match the agent's "aptitude" to the task at hand.

The broader implication is a future where we move away from monolithic AI models. Instead, we could build diverse teams of AI agents, each with a personality tailored to its specific role.

Imagine a creative "ENFP" agent brainstorming with a logistical "ISTJ" agent to plan a complex project. It raises a new question: what's the optimal personality mix for solving a given problem?

Ultimately, this research points toward a future of more versatile, capable, and aligned AI. We're learning that we can shape not just an AI's output, but its entire cognitive and affective style for a task. A simple prompt can unlock a whole new dimension of behavior.

[ふも @fumokmm]

日本語 の一人称がやばい

[FFmpeg @FFmpeg]

It's important to remember that "technology influencers" can be bad role models. Many encourage people to be "fans of technology" instead of actual developers of technology.

Hot takes are easy, writing good code is not.

[石野理子 @yoooutopia]

Fenderのオフィシャルメディア「#FenderNews 」の連載企画『Life with FENDER』に参加させていただきました！

中野敬久さんに撮っていただいています✶⋆.
暗い紫のテレキャスかっこよかった🌚

下記サイトにたくさん写真が掲載されているで、ぜひチェックしてみてください🎸
https://t.co/8WhQh8X53r

[Tyrese Haliburton @Hali]

Man. Don’t know how to explain it other than shock. Words cannot express the pain of this letdown. The frustration is unfathomable. I’ve worked my whole life to get to this moment and this is how it ends? Makes no sense.

Now that I’ve gotten surgery, I wish I could count the number of times people will tell me I’m going to “come back stronger”. What a cliche lol, this shit sucks. My foot feels like dead weight fam. But what’s hurting most I think is my mind. Feel like I’m rambling, but I know this is something I’ll look back on when I’m through this, as something I’m proud I fought through. It feels good to let this shit out without y’all seeing the kid ugly cry.

At 25, I’ve already learned that God never gives us more than we can handle. I know I’ll come out on the other side of this a better man and a better player. And honestly, right now, torn Achilles and all, I don’t regret it. I’d do it again, and again after that, to fight for this city and my brothers. For the chance to do something special.

Indy, I’m sorry. If any fan base doesn’t deserve this, it’s y’all. But together we are going to fight like hell to get back to this very spot, and get over this hurdle. I don’t doubt for a second that y’all have my back, and I hope you guys know that I have yours. I think Kobe said it best when in this same situation. “There are far greater issues/challenges in the world then a torn achilles. Stop feeling sorry for yourself, find the silver lining and get to work with the same belief, same drive and same conviction as ever.” And that’s exactly right. I will do everything in my power to get back right.

My journey to get to where I am today wasn’t by happenstance, I’ve pushed myself every day to be great. And I will continue to do just that. The most important part of this all, is that I’m grateful. I’m grateful for every single experience that’s led me here. I’m grateful for all the love from the hoop world. I don’t “have to” go through this, I get to go through this. I’m grateful for the road that lies ahead. Watch how I come back from this. So, give me some time, I’ll dust myself off and get right back to being the best version of Tyrese Haliburton.

-0

Proverbs 3:5-6 “Trust in the Lord with all your heart, and lean not on your own understanding; in all your ways acknowledge Him, and He will make your paths straight."

[elvis @omarsar0]

LLMs Get Lost in Multi-turn Conversation

The cat is out of the bag.

Pay attention, devs.

This is one of the most common issues when building with LLMs today.

Glad there is now paper to share insights.

Here are my notes:

[石野理子 @yoooutopia]

久しぶりに菜穂さんにも会えました(ᐡ ᵕ ̫ ᵕ̩̩ ᐡ)♪

[matt palmer @mattyp]

The Google Maps MCP server is a hidden gem.

I used it on a trip to Madrid earlier this month to plan an entire itinerary. I just gave it the address of my hotel and some interests.

Along with search (Exa, I believe), I got a full daily itinerary with relevant locations within walking distance.

This could be a product on it's own.

[大塚 明夫 @AkioOtsuka]

ひさしぶりだな、少佐…

[新海誠 @shinkaimakoto]

ちょっと久しぶりに通りました！

[Dirk Nowitzki @swish41]

😳

[AC Milan @acmilan]

Sorry for the delay, the graphic designers were a bit busy... 😇

#MilanParma #SempreMilan
Brought to you by @Bitpanda_global

[藤🎧ふじ🥷🔥 @hujimari]

赤ちゃんペンギン🐧の食事😍

[That Milan Podcast @ThatMilanPod]

Players in AC Milan History with at least 60 Goals and 50 Assists:
Gianni Rivera
Clarence Seedorf
Kaká
Rafael Leão