Lippy | Linh 🅶 (@GAWMagic) profile picture

Former Tech Lead @ TikTok, Intuit, Google, Hibernates. Founder @langfi_ai

Joined April 2023
Photo by Lippy | Linh 🅶 (@GAWMagic)Photo by Lippy | Linh 🅶 (@GAWMagic)Photo by Lippy | Linh 🅶 (@GAWMagic)
I won't update daily this $LangFi every day like before as I'm mindful of X bots make strike randomly
8
6
804
I’m pumped just imagining what @langfi_ai will become. Honestly, I can’t wait to get my MacBook back in my hands every morning and start coding.
13
784
Let's make it count.
1
8
1,309
Building a multi-relational social database at the scale of millions of records is one of the biggest engineering challenges I’ve faced. In this kind of system, there’s simply no substitute for experience. Having previously built similar infrastructure at TikTok, operating at a scale involving tens of billions of relationships, gives me a strong chance for tackling this problem.
9
1
3
22
2,628
lets see how can we get these guys to invest. There is just only way. Unseat Frontrun.
🚀 INVESTORS 💼 Frontrun secures a massive $141M raise, backed by top-tier players 👇 🔥 @FrontrunPro — Raised $141M 🧩 @YZiLabs — #YZiLabs(ex Binance Labs) — Investor 🤖 @AnthropicAI — #AnthropicAI — Investor ⚡ A huge signal of confidence as institutional capital flows into next-gen trading & AI-driven infrastructure. #investors #cryptoinvestors #venturecapital #fundraising #ai #web3 ❓Is this the beginning of a new wave of AI-powered trading platforms dominating crypto markets? 👇💬
1
2
8
2,207
Launch LangFi
This quoted post is unavailable.
7
16
3,215
Doing some research on @RobinhoodApp
4
1,581
Some experiments worked. Some absolutely did not. The hardest lesson was probably the simplest one: Having an interesting AI product isn’t enough. You also need an economic model that can sustain the compute behind it.
1
5
1,857
Still here, still grinding.
1
4
1,264
Honestly, the hardest part about plugging AI agents into a root-level system isn’t getting them to work. It’s dealing with the damage they might cause.
3
1
7
1,705
What makes it worse is there’s often no safety net. No easy rollback. By the time you notice something’s off, it’s already spread.
4
585
Once you give an agent deep access, even a small mistake can spiral into a full-on system failure. And these aren’t your usual bugs you can trace and patch. It’s the system acting on its own, with partial context, making decisions that seem reasonable in isolation… but end up breaking everything.
3
974
The Bay Area is the best place to build tech products and meet tech people. period.
2
788
We fancied ourselves the creators of bots, oblivious to the fact that the bots were remaking their creators in their own mechanical image.
2
833
Clawdbot needs to improve big time in terms of security or users will risk their lives. Literally.
1
1
1
7
1,073
It’s great to see that a few former Hibernates partners are still using our custom LLMs. That alone is strong motivation to pick things back up, revisit those proven models, and make them even better.
7
827