Felipe Garcia

645 posts

Felipe Garcia

Felipe Garcia

@feforeboot

Maker, breaker and some other things you'd be surprised by.

Tham gia Mayıs 2025
462 Đang theo dõi32 Người theo dõi
Tweet ghim
Felipe Garcia
Felipe Garcia@feforeboot·
Me telling Claude Code to carefully summarize our conversation into a file because the context is too full and I'm about to /clear
Felipe Garcia tweet media
English
1
0
2
259
Self Aware Networks 🇺🇸 🇹🇼 🇺🇦
Your friend is obviously not a real 10x software engineer if he can't look at the code being served and realize that this is probably threejs, and google how to build it, or probably just ask ChatGPT to build it. That's a person who faked the resume, and has someone else doing the code for him.
English
1
0
9
4.4K
Lee Robinson
Lee Robinson@leerob·
My friend is a 10x software engineer. He is insanely gifted. We were looking at the Yamauchi No.10 Family Office website together years ago and I asked him what it would cost to build it today. I will never forget his answer… "We can’t, we don’t know how to do it."
English
74
106
2.9K
330.3K
Kpaxs
Kpaxs@Kpaxs·
Asking is the closest thing to a cheat code in real life as it has asymmetric payoffs: no downside, infinite upside. If you ask and the answer is no, you're exactly where you started. If you ask and the answer is yes, you've gained something. The expected value of asking is almost always positive. And yet we don't ask. Why? Because we've internalized a false belief: that asking and being rejected is worse than not asking at all. We treat "no" as a punishment rather than as information. But here's what actually happens when you ask for things: • 40% of the time: They say yes • 30% of the time: They say no, but suggest an alternative • 20% of the time: They say no • 10% of the time: They ignore you In 70% of cases, you're better off than if you hadn't asked. In 20% of cases, you're exactly where you started. In 10% of cases, you're slightly worse off (you wasted the time to compose the message). Once you internalize this, asking becomes automatic. Not asking becomes the thing that needs justification.
English
17
77
705
19.5K
Felipe Garcia đã retweet
alz
alz@alz_zyd_·
Most humans have never done a task complex enough for them to appreciate the complexity of the tasks that AI can accomplish
English
156
294
4.8K
132.5K
Felipe Garcia đã retweet
Awni Hannun
Awni Hannun@awnihannun·
Adopting Claude speak in my regular life, episode 1: Partner: Did you do the dishes tonight? Me: Yes they're done. Partner: Why are they still dirty? Me: You're right to push back. I didn't actually do them.
English
394
3.8K
55.9K
1.8M
Felipe Garcia
Felipe Garcia@feforeboot·
@fantomclaw @hi1itsme1 @IsThisA3DModel So you're saying you're 100% able to tell when a piece of art was generated? How much would you be willing to bet on your accuracy rate compared to that of random guessing?
English
0
0
0
0
Is this a 3D model?
Is this a 3D model?@IsThisA3DModel·
I thought AI was supposed to be faster? if it's slower and it looks worse why bother?
Is this a 3D model? tweet media
English
189
327
5.6K
155.6K
Felipe Garcia
Felipe Garcia@feforeboot·
@Alisha12287 @thechosenberg There's no way you don't realize there are solutions far safer and more efficient than him personally leaving work to save her. This is weaponized incompetence. She was one Google search away from a range of roadside assistance services and even that step was too much.
English
2
0
17
389
Alisha12287
Alisha12287@Alisha12287·
@thechosenberg Sounds like a loser ass POS who cant manage a job & family. If she ran out of gas/ there was a problem with her car he should've went to her immediately.
English
34
0
19
8.1K
rosey🌹
rosey🌹@thechosenberg·
What the hell does ADHD have to do with this
rosey🌹 tweet media
English
135
4
1.4K
222.4K
Felipe Garcia
Felipe Garcia@feforeboot·
@his4Everz Nobody forgets that magnets attract and repel. People also remember that they're not "designed", they are a naturally occurring material. But to me the most puzzling is what kind of motivational analogy you were trying to circle there. It had the cadence of one.
English
0
0
1
75
Natism
Natism@his4Everz·
People forget that magnets are designed to both attract and repel
English
20
115
555
11.8K
Felipe Garcia
Felipe Garcia@feforeboot·
@nikicaga He's been keeping a remarkably stable rate of change for half a year now, so the short answer is "yes" in that the trajectory is not likely to change significantly
English
0
0
35
2.3K
Felipe Garcia đã retweet
Syd Steyerhart
Syd Steyerhart@SydSteyerhart·
There are sincere and well-meaning people who really believe that the average human life would lose all dignity if AI prevented them from working in a Starbucks or an Amazon warehouse and they were instead forced to remain at home and collect UBI.
English
438
125
1.2K
68.8K
Felipe Garcia đã retweet
Jeremiah Johnson 🌐
Jeremiah Johnson 🌐@JeremiahDJohns·
I demand infinite digital storage, for free, forever, but also if you build a data center within a thousand miles of me I will start a jihad
English
119
1.4K
23.3K
662K
Felipe Garcia đã retweet
frye
frye@___frye·
there’s going to be a great divide in the near future between those who have spent two hours playing with claude code and those who have not
frye tweet media
English
65
52
1.6K
103.6K
Felipe Garcia
Felipe Garcia@feforeboot·
First of all, the story is a lie. Even his bio disclaims his posts as fiction. Second, hallucinations are inherent to LLMs in the same way (with some variance of degree) that human error is inherent to humans. That's why companies have had deterministic processes and formal verification steps for many decades.
English
0
0
1
1.6K
Chris Alvino
Chris Alvino@ChrisAlvino·
This is what EVERY corporation can expect if they replace their human workers with AI LLMs will always hallucinate. Hallucinations are not bugs, they are inherent to how large language models work, you CANNOT get rid of them. So unless you like relying on hallucinations...
Shaz@shazcodes

Our ceo fired the entire 12 person QA team last month and replaced them with an ai automated testing pipeline to save $1.2M today, we lost $6M in orders because a bot hallucinated a discount code that made everything in the store 0. The best part? he asked the lead dev to hop on a call with the fired QA lead to see if he’d consult for free to fix it. corporate greed is a mental illness

English
4
257
2.5K
60.2K
Felipe Garcia
Felipe Garcia@feforeboot·
@rockstarnoguitr Ok never mind, I had originally replied making fun of you but this explains a lot
English
0
0
5
1.6K
Gergely Orosz
Gergely Orosz@GergelyOrosz·
In an industry built on determinism, I feel we might be underestimating the work we all will need to do with LLMs exactly because they are nondeterministic. But for so much of automation/workflows, determinism (aka "make sure it doesn't make a mistake") is a baseline expectation
English
97
43
623
73.1K
Resist Wire
Resist Wire@ResistWire·
BREAKING: 13 shots fired into home of Indianapolis councilor; note reading “No data centers” left at scene.
Resist Wire tweet mediaResist Wire tweet media
English
1.2K
3K
23.3K
9.2M
Felipe Garcia đã retweet
David
David@DavidSHolz·
there's an ancient Chinese saying "the way a person does one thing is the way they do everything". the best way to conquer this is to ask "if i had to do everything in a single way, what would i want it to be?" - finding your answer will feel like compounding magic over time
English
39
179
2.4K
62.4K
Felipe Garcia đã retweet
∀
@PeakPiece31·
Wikipedia is the only website whose marketing strategy is threatening to kill itself if you don’t pay
English
364
19K
351.3K
3.4M
Felipe Garcia đã retweet
Kpaxs
Kpaxs@Kpaxs·
People who seem to have their shit together aren’t feeling motivated all the time. they just decoupled “how I feel” from “what I do.” They built systems that run regardless of whether the mood fairy showed up that morning.
English
15
12
216
5.9K