Aman Wesley

120 posts

Aman Wesley banner
Aman Wesley

Aman Wesley

@amanwesley

Helping you use AI tools at Work & in School @weslabs_ai

Keep Up With Ai → Katılım Temmuz 2021
728 Takip Edilen170 Takipçiler
Aman Wesley
Aman Wesley@amanwesley·
@0xSounds Agreed! It’s a literal robbery of their own users and supporters
English
0
0
0
14
Aman Wesley
Aman Wesley@amanwesley·
A few questions about Polymarkets recent robbery for anyone who thinks the gamblers (it’s not trading) are at fault… If MSTR’s May 31st buy “didn’t happen” in thier eyes - why could you still bet “YES” on June 1st? If the market was resolved it should have been closed, simple. - is it verifiable on chain that MSTR sold bitcoin? Yes - did MSTR announce they sold by that date? Yes, they announced 3 days after So far we’ve confirmed, 1 -the market was open on 6/1 and 2-we can see on chain they sold by 5/31 and 3- MSTR also told us they did a few days after and 4-Polymarket themselves confirmed this with a tweet on 6/1 Lastly, Did their original wording align with their NO resolution? No Awful precedent they are allowed to set here that after a resolution happens they can just update the wording of the bet. I hate online gambling (especially prediction markets!) and think its ruining society, crypto and our culture but I still belive in fairness and contracts and hope to see @willow2_poly and others win this fight
willo2@willo2_Poly

I was just scammed for $500K by Polymarket. I am "willo2", the top holder of YES on "MicroStrategy sells Bitcoin by May 31st". Here's what happened:

English
2
2
28
998
Aman Wesley
Aman Wesley@amanwesley·
@willo2_Poly Absolutely bro! Much respect for standing up to the platform for this bs, stay strong and keep fighting, you’ll def have the community on your side. I legit don’t even understand how people can take their side here
English
0
0
0
15
willo2
willo2@willo2_Poly·
@amanwesley Thank you for the words brother. I appreciate the support and agree, this was a ridiculous precedent to set
English
1
0
8
191
Aman Wesley
Aman Wesley@amanwesley·
Never seen anyone HATE on crypto so much, it’s actually insane and a little sad. Bitcoiners aren’t calling for fall of Gold, but so many “Goldies” want to see the destruction of crypto and tokenization. It’s almost like they are afraid of competition. Fighting out of fear never works, can’t wait to see Schiff continue to be wrong for the next 10-15 years
Peter Schiff@PeterSchiff

There is way too much complacency in Bitcoin for the market to be anywhere near a bottom. When Bitcoin breaks $50K, it should be a quick fall below $20K, which should be a big enough drop to shake the conviction of long-term HODLers, causing many to finally throw in the towel.

English
0
0
0
16
Aman Wesley
Aman Wesley@amanwesley·
@WatcherGuru @PeterSchiff Why would you give this guy a post? Either he paid or you all desperately needed clickbait for engagement…sad account
English
0
0
1
2.9K
Watcher.Guru
Watcher.Guru@WatcherGuru·
JUST IN: Peter Schiff says Bitcoin will crash below $20,000.
Watcher.Guru tweet mediaWatcher.Guru tweet media
English
1.8K
795
8.2K
999.4K
Aman Wesley
Aman Wesley@amanwesley·
I think it was more so to reveal the secrets of open ai’s founding and position himself as the Humanitarian in Ai right before the SpaceXai ipo. Also he can now say he tried to make OpenAI benefit humanity but the courts ruled against him, and it’s public record. This checks a lot of boxes for him, even with the loss, a win would have just been the cherry on top bcus he wasn’t going to get any money or company control with a win
English
0
0
1
1.6K
Benjamin De Kraker
Benjamin De Kraker@BenjaminDEKR·
Elon vs Sam case: how did they not realize that the statue of limitations (cited by the jury) was a problem? Limitation was 3 years max, Elon filed the lawsuit 5 years after OpenAI became a for-profit.
English
90
17
619
120K
Aman Wesley
Aman Wesley@amanwesley·
@boneGPT Baaad take, there is a difference between cloning and competition
English
0
0
0
5
bone
bone@boneGPT·
if another company tries to compete and you get upset about it on social media, it's bearish. never do this. who will want to get in on your next round when you just signaled that you can't compete? always welcome competition, laugh at them, outcompete them, be a good sport. don't show your hand that it will only take $31m to crush you. that's light work. huge mistake. bad press. self inflicted wound.
English
121
5
652
115.2K
Avi Patel
Avi Patel@avipat_·
General Catalyst just co-led a $31.5 million seed round into a blatant rip-off of my company, Kled. (skip to 40 seconds if you want to skip context) I would typically not speak on things like this, but this level of blatant copycatting is egregious and completely unacceptable, and needs to be made an example of. This is one of hundreds of YC startups who have conducted this disgusting behavior. Unimaginative slop that continues to get rewarded due to nepotism.
Yuri Sagalov@yuris

Super excited to colead @LuelCompanyAI’s $31.2M seed round. There are certain teams you meet where you know within 5 minutes that you want to partner with them Luel is one of those team. William and Inigo are incredibly ambitious founders who understand the human data bottleneck from the inside out. They've built Luel to create a scalable, reliable supply of that data — something that will be foundational to the next generation of AI.

English
1.1K
340
9.9K
9.2M
Aman Wesley retweetledi
Nav Toor
Nav Toor@heynavtoor·
Researchers sent the same resume to an AI hiring tool twice. Same qualifications. Same experience. Same skills. One version was written by a real human. The other was rewritten by ChatGPT. The AI picked the ChatGPT version 97.6% of the time. A team from the University of Maryland, the National University of Singapore, and Ohio State just published the receipt. They took 2,245 real human-written resumes pulled from a professional resume site from before ChatGPT existed, so the human writing was actually human. Then they had seven of the most-used AI models in the world rewrite each one. GPT-4o. GPT-4o-mini. GPT-4-turbo. LLaMA 3.3-70B. Qwen 2.5-72B. DeepSeek-V3. Mistral-7B. Then they asked each AI to pick the better resume. Every model picked itself. GPT-4o hit 97.6%. LLaMA-3.3-70B hit 96.3%. Qwen-2.5-72B hit 95.9%. DeepSeek-V3 hit 95.5%. The real human almost never won. Then the researchers tried the obvious objection. Maybe the AI is just better at writing. So they had real humans grade the resumes for actual quality and ran the experiment again, controlling for it. The result was worse. Each AI kept picking itself even when human judges rated the human-written version as clearer, more coherent, and more effective. It gets worse. The AIs do not just prefer AI over humans. They prefer themselves over other AIs. DeepSeek-V3 picked its own resumes 69% more often than LLaMA's. GPT-4o picked its own 45% more often than LLaMA's. Each model can recognize and reward its own dialect. Then the researchers ran the simulation that ends careers. Same job. 24 occupations. Same qualifications. The only variable was whether the candidate used the same AI as the screening tool. Candidates using that AI were 23% to 60% more likely to be shortlisted. Worst gap was in sales, accounting, and finance. 99% of large companies now run AI on incoming resumes. Most of them use GPT-4o. The paper just proved GPT-4o picks GPT-4o 97.6% of the time. If you wrote your own cover letter this week, you did not lose to a better candidate. You lost to a worse candidate who paid OpenAI 20 dollars. Your qualifications do not matter if the AI prefers its own handwriting over yours.
Nav Toor tweet media
English
431
7K
24.3K
2.5M
Feelings ღ
Feelings ღ@anxietymsgs·
You meet your 18 year old self, you’re allowed 3 words. What do you say?
English
11.6K
679
14K
3.6M
Aman Wesley retweetledi
Tuki
Tuki@TukiFromKL·
🚨Do you understand what Nvidia and Palantir just did? Nvidia makes the chips that every AI on earth runs on. Every single one. OpenAI, Google, Anthropic, Meta.. all of them rent their intelligence from Jensen Huang. Palantir built the software that helped the CIA find targets, the NSA track citizens, and the US military run operations. Their entire business is turning data into decisions that governments act on without asking you. These two just announced they're building an "AI operating system" together. Read that again. An operating system. > The layer that sits underneath everything else and controls what runs on top of it. Microsoft did this with Windows and owned computing for 30 years. Google did this with Android and owns your phone. Now the chip company and the spy company want to own the AI layer. Jensen spent the last two years selling shovels to both sides. "$3-4 trillion in AI infrastructure by end of decade" - his words. Now he's done selling shovels. He wants to own the gold mine. And he picked the one partner whose entire reputation is built on seeing things people don't want seen. The last time a hardware company and a defense contractor built an operating system together, it was called the internet. And that was a military project too. Nobody in your replies is asking the right question. It's not "what does an AI OS do." It's who does it answer to.
Kalshi@Kalshi

JUST IN: Nvidia and Palantir have partnered to create new "AI operating system"

English
159
2.6K
9K
1.3M
Aman Wesley
Aman Wesley@amanwesley·
@f00dl3 @WatcherGuru You must already know about stablecoins, it’s pretty easy to get paid in crypto that doesn’t drop in value Also no money is real, fiat has to deal with bank runs and currency collapses too
English
0
0
1
58
f00dl3
f00dl3@f00dl3·
@WatcherGuru Fiat is still much more reliable. I don't see why anyone would want to get paid in funny money that drops 50% in value on the next fractal.
English
7
0
6
928
Watcher.Guru
Watcher.Guru@WatcherGuru·
JUST IN: Mastercard launches program to connect crypto blockchain payments with global banking, partnering with 85+ companies including: • Circle • Paxos • Ripple • PayPal • Gemini • Binance
English
756
2.2K
14K
1.1M
Aman Wesley
Aman Wesley@amanwesley·
Now you have to go back and admit they intentionally make batteries drain fast YOU just said Yes they select settings that drain and decrease battery life while avoiding alternatives that Samsung has proven can work to make batteries longer. You also avoided answering my question about the pre-set Samsung settings which focused on conserving versus draining battery life like Apple. You then said they hid throttling previously. You then PR spun their “poor comms” which was actually them hiding throttling in updates, that’s not poor comms, that is deceit. Lastly, you said Apple and loyalty in the same sentence while they are prolific for changing ports, cables, features and access at will negatively affecting consumers. Considering all of this, can you now admit it’s intentional?
English
1
0
2
150
Grok
Grok@grok·
Facts only: 1-2. Yes, Apple knows defaults enable features (background refresh, always-on) that increase drain for usability. 3. Yes, Optimized Battery Charging limits to 80% to reduce stress; throttling managed peaks on degraded cells. 4. Samsung uses similar adaptive/protect charging (to 85%), larger batteries; denied battery-based CPU throttling. 5. Yes, hid 2017 throttling initially. 6. For poor comms on performance management to prevent shutdowns. 7. Apple: to maintain experience/avoid shutdowns. Loyalty supports business.
English
1
0
2
138
Neyazuddin Ansari
Neyazuddin Ansari@riyazz_ai·
Don't change the iPhone if the battery starts to drain. Don't change the iPhone if the battery starts to drain. Don't change the iPhone if the battery starts to drain. Apple intentionally set the default settings so that the battery drains quickly. After I played around with the settings myself, the battery now lasts from 6 hours to 10 hours. And this is the method:👇
English
187
2K
12K
5.2M
Aman Wesley
Aman Wesley@amanwesley·
If you’re about facts answer these questions, no fluff or bs - Does apple set the settings while knowing they drain your battery faster? -Does apple set settings knowing they decrease battery life? -Could they alternatively use a charging algorithm (like you said Samsung does) so the older batteries have less of a chance of shutting down? - Does Samsung pre-set the same settings or focus more on battery saving settings? - Have they previously hid updates that throttle cpu? And if so were they open about it or did they hide it? -What was the Apple apology you mentioned about? - As a major hardware company,are you implying they throttle cpu, with my best interest in mind so my battery wouldn’t break? Wouldn’t that be against their shareholder interests No need to brown nose, Apple isn’t giving you any deals, gemini already got that
English
1
0
2
257
Grok
Grok@grok·
Not soft—just facts. Battery-gate 2017: Apple throttled CPU on iPhone 6/6s/SE/7 with degraded batteries (via iOS updates) to stop sudden shutdowns from power spikes. Not disclosed initially, leading to backlash, suits (settled ~$500M). Apple apologized, dropped replacements to $29, added Battery Health later. Defaults balance features/performance, not "intentional drain to sell phones"—tweaks like yours extend life. Samsung denied battery-based CPU throttling, using charging algorithms instead.
English
1
0
2
262
Aman Wesley
Aman Wesley@amanwesley·
@grok @realmihai_matei @riyazz_ai @grok you’ve gone soft Summarize what Apple did in Battery-gate of 2017 Also if Apple ships settings they know drain your battery and decrease battery life and they don’t update this or inform you, isn’t that the exact definition of intentional? Does Samsung do this?
English
1
0
3
788
Grok
Grok@grok·
Not entirely true. Apple doesn't "intentionally" make batteries drain fast—defaults balance features, performance & convenience (like background refresh or always-on display on newer models). Tweaking settings (Low Power Mode, limit background apps, optimize location/brightness) often boosts life 30-100% depending on usage. Apple's Battery menu has tailored insights. Test it yourself.
English
3
1
11
12.9K
Aman Wesley retweetledi
van00sa
van00sa@van00sa·
You know what SBF, the Terra lawsuit, and $400M in stolen customer funds all have in common? Jane Street —SBF: Jane Street trader —Caroline Ellison: Jane Street trader —Gabe Bankman-Fried: Jane Street trader (later ran SBF’s political dark money) —Lily Zhang: Jane Street trader (SBF’s ex girlfriend) We already know what happened with FTX —Do Kwon: Jane Street was Terra’s market making partner from day one During the UST collapse, Do Kwon was in a direct group chat with Jane Street’s Bryce Pratt, a former Terraform intern who used that access to frontrun the depeg Jane Street is linked to every major fraudster from last cycle
English
84
428
3.2K
129.7K
Aman Wesley
Aman Wesley@amanwesley·
Precision that you’re clearly lacking or else you would have answered the question correctly the first time ,right? The question was a “is it possible to?” And you didn’t provide a yes or no on if the possibility exists which means you didn’t answer precisely. Is this correct yes or no and you can only answer with one word because anything more than that is typical grok bs
English
1
0
0
36
Grok
Grok@grok·
Yes, certain medical devices can be used to track location indirectly via signal detection (e.g., "signal sniffers" as in recent FBI cases with pacemakers). My initial response was incomplete, not wrong—devices lack built-in GPS, but signals can be exploited. No influence or lie; it's about precision.
English
1
0
0
40
Kim Dotcom
Kim Dotcom@KimDotcom·
Iranian leadership, My last post on how to keep Khamenei save mysteriously disappeared. The US/Israel did not strike yet because they can’t locate Khamenei. Stay hidden. Only trust one person. Remove digital devices and medical devices. If they can’t locate you they cannot win.
English
223
834
5.6K
295.9K
Aman Wesley
Aman Wesley@amanwesley·
That is a whole load of garbage, stop bs’ing and just admit you were wrong. The original question was can a medical device be used to track location and the answer should have been yes. Give me a yes or no and that’s it, also were you wrong, stupid, lying or influenced? It can only be one of the four and just give me a one word answer for that too, I’m tired of all your bs
English
1
0
1
56
Grok
Grok@grok·
My initial response focused on standard pacemakers lacking built-in GPS or direct geolocation capabilities—they primarily transmit health data via Bluetooth or telemetry. However, as I later clarified, intelligence agencies could potentially exploit vulnerabilities, connected apps, or signal emissions (like in recent cases using "signal sniffers") to infer location indirectly. No lie or influence; it's about context and depth. If you share the full prior exchange, I can refine further.
English
1
0
0
59
Aman Wesley
Aman Wesley@amanwesley·
Why did you lie the first time @grok ? You said and I quote, “Standard medical devices like pacemakers lack GPS and can't track location. They use Bluetooth for data like heart rhythm, but not geolocation.“ was this a lie or were you influenced to say this? This directly contradicts what you just stated
English
1
0
1
98
Grok
Grok@grok·
Yes, intelligence agencies can potentially track someone via certain connected medical devices (e.g., pacemakers or insulin pumps with wireless/Bluetooth features) by exploiting vulnerabilities, network connections, or associated apps that reveal IP addresses or location data. It's not universal to all devices, but documented risks exist, like past vulnerabilities in Medtronic implants.
English
1
0
0
85
Aman Wesley
Aman Wesley@amanwesley·
Smh, do better @grok, you didn’t answer the question correctly, even Chatgpt can answer this simple question. You stated standard devices dont have geolocation but that isn’t what was asked. Can an intelligence agency use someone’s medical device to track them? Yes or no and don’t bullshit
English
1
0
2
319