Ha Tran Nguyen Phuong

black cat w green tea energy

[Ha Tran Nguyen Phuong @sherlockieee]

At this point I just want to be part of a drama-free nerd club.

[Ha Tran Nguyen Phuong @sherlockieee]

@aiDotEngineer ins & outs for ai engineering
(observation NOT endorsement)

ins: memory, auto-research, knowledge graphs, open models, vertical ai
outs: embeddings/ RAG, mcp, token counts as metric, prompt engineering, code reviews, public benchmarks
evergreen: evals, skills, permissions, governance

[Ha Tran Nguyen Phuong @sherlockieee]

@geoffreylitt Loved the meme

[Ha Tran Nguyen Phuong @sherlockieee]

@chrislakin @LighthavenPR Most conferences: Way too focused on talks ; hard to meet people organically; app doesn’t prefill your profile so hard to find ppl to talk to; also no food or drink.

[Ha Tran Nguyen Phuong @sherlockieee]

wow going to LessOnline really ruins other conferences for me

[Ha Tran Nguyen Phuong @sherlockieee]

@AaronBergman18 retinol & sunscreen are the only ones that are proven to work anyways

[Ha Tran Nguyen Phuong @sherlockieee]

@andyhsuco but can you really find sf in nyc tho

[Ha Tran Nguyen Phuong @sherlockieee]

the final layer of software is: claude, github, and slack?

[Ha Tran Nguyen Phuong @sherlockieee]

lol this was the push for me to get ticket for AI Engineer world fair. Hit me up if you’re around!

[Thariq @trq212]

I'll be giving the the Day 2 opening keynote at AI Engineer World's Fair on July 1st at 9am.

Hope to see you there, here's a quick preview

[Ha Tran Nguyen Phuong @sherlockieee]

@chrislakin @archived_videos soft cute cuddly

[Ha Tran Nguyen Phuong @sherlockieee]

@chrislakin my forgetting curve is 1 day

[Ha Tran Nguyen Phuong @sherlockieee]

Apparently from evolutionary biology humans are biologically evolved to be serial monogamists. My armchair theory is that both in polyamorous and monogamous relationships you keep falling in love over and over, it’s just with polyamory it’s with different people and with monogamy it’s the same person again and again.

[Vacha @TVachaW]

When done well, a monogamous relationship can feel like having a polyamorous relationship with one person.

The key to unlocking this is developing a specific type of skill in romantic imagination and creative perception.

When we’re first talking in love with someone, our imagination effortlessly goes into overdrive.

All our fantasy and limerence naturally casts our partner in a romantic light.

There’s a sense that we get to fall in love with them once for free.

But to keep the relationship maximally alive, in my experience, we must fall in love with them over and over again.

This repeated falling in love is a kind of skill.

We can constantly look at our partner anew, notice how they are growing and evolving, and learn how to fall in love with each of these new versions of them as they arrive.

This is how a monogamous relationship can start to take on the flavour of polyamory over time.

There are so many different versions of my partner that I’ve fallen in love with upon meeting them.

There are also subtle aspects of her that were always there but only embolden themselves into visibility as familiarity grows.

Each of these aspects is exciting in a different way, and each is nested within one other.

It’s what for me, keeps the relationship fresh and allows the puppy-dog flavour of love to stick around long after the honeymoon phase is over.

[Ha Tran Nguyen Phuong @sherlockieee]

does anyone else find it strange that the US is AI pilled and China isn't?

Is it more likely that in all of China there is no one who thinks deeply enough about implications of self-improving ai, or that we collective are in psychosis about machine that can kill us all?

[Ha Tran Nguyen Phuong @sherlockieee]

@chrislakin Shhhhhh

[Ha Tran Nguyen Phuong @sherlockieee]

anxiously waiting for my claude to response like waiting for my crush to text me back

[Ha Tran Nguyen Phuong @sherlockieee]

@hamedinsf Boba is S tier sir

[Ha Tran Nguyen Phuong @sherlockieee]

@chrislakin Badge of honor tbh

[Ali Woods @AliWoodsGigs]

I’ve longed for Knicks to win a championship ever since I watched them for the first time on Monday

[Ha Tran Nguyen Phuong @sherlockieee]

My learning as an AI engineer is that most people trust the model w too little, not too much.

[Walden @walden_yan]

My take 24 hours after Fable 5:

Your organization will likely not scale with the exponential curve of AI.

I'l just come out to say: This should be a wakeup call for engineering teams.

Set up your cloud software factories. Now.

Models can now fix impossible bugs, UI-test the hardest flows, writing extremely good code, etc. I have't opened Datadog manually as far as I can remember.

AI should be the first-line defense for bugs and feedback. Humans should only look at PRs after an AI has already reviewed it. AI should generate screen recordings of any PR before a human eye even reaches it. The agent should just prompt itself most of the time.

Ex. (pictured) our ui feedback channel manages itself, creates tickets, assigns itself automatically

You might also be worried about cost. Anthropic, OpenAI, and other labs will likely continue to put out bigger and more expensive models. But, we will also continue to get more capable small models. Not everything will need the smartest models. It's about having the organizational harness in place to continue taking advantage of this rising tide.

Moreover, if you use Devin, we've already optimized our harness a bit, and Fable is actually only ~40% more expensive in practice (vs the 2x people assume). I'm honestly pleasantly surprised - it might be higher ROI than you think.

Anyway, if you take anything away, engineers shouldn't be manually picking up tickets, humans shouldn't be digging into logs themselves, rethink what you do with your time that shouldn't just be an AI. We need to rethink what humans spend their time going.

[Ha Tran Nguyen Phuong @sherlockieee]

Twitter is like a slot machine except you can make money out of it

[Ha Tran Nguyen Phuong @sherlockieee]

I have learnt that most people do not optimize for their careers, even if they say they do

[zach @swe_zach]

moving to SF and working on AI seems like the obvious best high level career path

I’m kinda surprised more software engineers aren’t doing this

Most of the people I know and most of my coworkers seem completely fine not doing this which seems odd