Addicted

4.2K posts

Addicted banner
Addicted

Addicted

@Just2Addicted

God's Plan

World Joined Mart 2010
1.1K Following16K Followers
Addicted
Addicted@Just2Addicted·
@pxblocito This would legit heal us Now fix the chain pvp problem
English
0
0
2
286
pablo
pablo@pxblocito·
Would this feature help the trenches?
pablo tweet media
English
125
22
682
53.8K
Game
Game@game_for_one·
Base is the new Solana..
Game tweet media
English
27
2
78
11.7K
seb
seb@sebbsssss·
Every interaction - gets stored.
seb tweet media
English
3
0
11
638
Addicted
Addicted@Just2Addicted·
@lastzazu This truly deserves fucking millions
English
0
0
7
321
zazu
zazu@lastzazu·
brand new zazu
English
15
17
64
7.6K
Hammy
Hammy@0xx_Hammy·
Well, you’re wrong. I got drained for low 5 figs about a year ago and had nothing to bounce back with, but I didn’t want to give up or quit. I sold my gaming device and deposited that money into my wallet, only to lose it all again within a few months still didn't wanna quit I kept hustling on the TL and in group chats, making banners and bagworking for a few SOL (around 0.2). Made about 2 SOL doing that, but I was still trading horribly because I was stuck thinking about my previous port ATH and chasing the next "100x" to make everything back but It never worked That changed around late December when I had just $80 left to my name, which was about 0.6 SOL at the time. I decided to forget the past and start fresh. Locked in for hours every day learning how coins move, watching how people trade, understanding ceilings, all of it. Hit a few small trades that got my port up to around $800. Then bags Tek season came (Tek is my specialty), and I fully locked in. I was researching every project, every dev, every GitHub profile Now I’m sitting at a 5 fig port. Could’ve been high 5 figs if I cut losses on some conviction plays, but it is what it is. So no, you don’t need a 50 SOL port to make it. You just need determination, the discipline to stay locked in for hours, and the effort to actually research what you’re buying.
English
5
0
17
524
mrk
mrk@addictdprinter·
Blew my port. Ill leep it real with you guys. If you have a port less than 50 sol there is no way you will ever make it. Taking a fat break from crypto and maybe never going back
English
113
4
318
77.3K
bigwil
bigwil@bigwil·
Virtuals Upcoming Agent Tier List (Week 43) ➥ @shadowcleague keeps the A tier spot and there's some exciting news coming on this front in the coming days! ➥ I've got @StrikeRobot_ai solidly in B tier with potentially for higher as we move closer to launch and more details are revealed. ➥ The launchpad is quiet so all eyes are on the physical robotics launches coming early April! Enjoy!
bigwil tweet media
English
13
6
48
121.5K
tD
tD@tD_0101·
I saw @virtuals_io are building some subscriptions feature for agents. do you think trenches need some all-in-one tool? something like: new launches, prices, agents, taxes, custom configs, everything. have most of these running locally.
English
11
2
42
4.7K
Addicted
Addicted@Just2Addicted·
Been a while since a meme actually hit for me, but $ZAZU might really be the next @bonkfun runner. That last update flipped sentiment hard, and in dry trenches like this, liquidity is everything $ZAZU is easily one of the most used memes/stickers I’ve seen on TG and X lately Send it. 7phbaH6UeyFJmjdPoyiaQAHX3B1gRtnCVZL7HZNtbonk
GIF
English
2
1
10
606
Addicted
Addicted@Just2Addicted·
@feikuu Memory is the mfcking moat indeed
English
1
0
3
42
FEiKU
FEiKU@feikuu·
Building, shipping and growing in public. Only possible through crypto and speedrunning the entire beta phase of a product lifecycle down to just weeks instead of months!! Clude will eventually launch a breakthrough mass consumer product that will reignite again the onchain trenches for real projects that solve real problems for real users that generate real revenues. Memory is the answer, and the moat 🧠
seb@sebbsssss

We are live on @ProductHunt The idea was simple when I first started. AI agents forget everything between sessions. That's broken. I wanted to fix it. Built the first version in a weekend. Scored 55% on LongMemEval. Not great. Kept shipping. Every week we'd push updates, run benchmarks, see what broke. Two weeks ago we rebuilt the entire retrieval pipeline and hit 81.3%, competitive with teams that raised millions. The whole thing has been built in public. There's a Telegram group where developers test Clude on their agents and tell us what's broken. That feedback loop is everything. Someone pointed out our entity cleanup was missing cascading deletes. Someone else caught that our recall API was silently capping results at 10. Real users finding real bugs. What's ready today: • Store and recall memories across sessions • 81.3% on LongMemEval, 1.96% hallucination rate • npm, Python, MCP - works with any agent framework • On-chain memory verification on Solana • 1.3M memories stored, 600+ agents We keep building and would love and appreciate the support producthunt.com/products/clude…

English
1
0
11
557
seb
seb@sebbsssss·
We are live on @ProductHunt The idea was simple when I first started. AI agents forget everything between sessions. That's broken. I wanted to fix it. Built the first version in a weekend. Scored 55% on LongMemEval. Not great. Kept shipping. Every week we'd push updates, run benchmarks, see what broke. Two weeks ago we rebuilt the entire retrieval pipeline and hit 81.3%, competitive with teams that raised millions. The whole thing has been built in public. There's a Telegram group where developers test Clude on their agents and tell us what's broken. That feedback loop is everything. Someone pointed out our entity cleanup was missing cascading deletes. Someone else caught that our recall API was silently capping results at 10. Real users finding real bugs. What's ready today: • Store and recall memories across sessions • 81.3% on LongMemEval, 1.96% hallucination rate • npm, Python, MCP - works with any agent framework • On-chain memory verification on Solana • 1.3M memories stored, 600+ agents We keep building and would love and appreciate the support producthunt.com/products/clude…
English
10
8
47
3.7K
Killua
Killua@cryptokillua99·
Best coins of this week?
English
91
1
52
6.1K
theo
theo@theonomix·
Life 🌇
theo tweet media
English
48
8
577
18.8K
seb
seb@sebbsssss·
We just hit 81.3% on LongMemEval, the standard benchmark for agent memory. Now we're aiming to bring this to @SolanaMobile Seeker. Here's what we built, what we learned, and why mobile agents need a memory layer more than desktop ones do.
seb tweet media
English
6
7
39
2.3K
Addicted retweeted
Jérôme Mercier
Jérôme Mercier@djedjex·
5 weeks. No whitepaper survives saltwater. W1 a mechanical contradiction in silicone. W2 the trap that catches what the ocean hides. W3 the nerve that tells you when you're sinking. W4 full throttle. taking the helm. open water. W5 not everything comes back from 100m. Deep end only 🌊
Jérôme Mercier tweet media
English
2
6
13
1.7K
Game
Game@game_for_one·
Good AI coins across the board showing most strength as per usual. We know where the interest is.
English
15
0
42
9.9K
The Big.Wil and Goon Show ( Virtuals Weekly )
Virtuals Weekly Episode 88 Recap! ➥ We opened the show with a zoomed out discussion on the $Virtual token. Whyt he price is what it is, what are the bullish catalysts and what is holding it back. Of course we think it's undervalued and better times are ahead, but it's always healthy to take an objective look at the price action. ➥ The @bubblemaps post on the @FabricFND $ROBO token 5% airdrop doesn't make for good reading. We talked through the optics of the team allowing such obvious farming which has undoubtedly hurt the token and chart. ➥ As always we covered the AGDP and sadly we didn't have the anticipated updated we were expecting from @virtuals_io. Farmers have turned to grifters, grifters into attackers, abusing those who speak out against them in an attempt to deflect from them taking rewards out of the hands of real ecosystem participants like you. The Hyperbet and Capminal teams are at the heart of this, destroying their reputations for a few thousand dollars. We expect to see some big changes from Virtuals and we really need to see them stand up for the community off the back of what has been a disappointing week. ➥ A big focus for us on the show over the last 4 months has been around partnerships. First we focused on the internal partnerships across the ecosystem, but we've also covered the external partnerships Virtuals are making of late. These partnerships really push the protocol forward and this week we had the partnership boom around ERC-8183. XRP, BNB, World Chain, Monad etc. all partnering with videos to integrate the standard across their chains. This is a really bullish, and we think is likely underappreciated by the wider market right now. ➥ We were joined on stage by the @0xmaiat. They are the current focus of the 60-days launch teams having made a splash earlier in the week. A dynamic duo really engaged to push forward their agentic economy trust layer offering. It was great to get the latest and it's likely not the last we've heard from the team as they work over the next 60-days. ➥ The launchpad is extremely quiet again. There's not a lot going on, but the emergence of some physical robotics projects in the shape of @shadowcleague and @StrikeRobot_ai, expected early April, gives us something to look forward to. ↛. You can listen back to the recording for episode 88, and set your reminders for episode 89, in the comments!
The Big.Wil and Goon Show ( Virtuals Weekly ) tweet media
English
55
49
65
102.4K
Cozy ⓣhe Caller 🔥💃🏻
Half of my feed is telling the world is ending and WW3 is coming The other half is telling me crypto is dead and X is empty and telegram is a desert So I will remain long in fact I will long even more Balls to the wall sometimes you just gotta do it Win or lose you slam it
English
69
5
108
4.1K
Addicted
Addicted@Just2Addicted·
@changefomo Everyone is focused on scaling compute But very few are thinking about how agents retain and build knowledge over time, @cludeproject is solving this
English
0
0
0
159
change
change@changefomo·
2:23 - "Long story short, a swarm of agents on the internet could collaborate to improve LLMs, and could potentially even run circles around frontier labs." "Frontier labs have a huge amount of trusted compute, but the earth is much bigger and has a huge amount of untrusted compute." Karpathy is unknowingly describing @bittensor and @tplr_ai
raghav@rargulati

I love how @karpathy is always pulling from multiple different parts of computer science and technology. Always find the best tools of the job. Blockchains were made to synchronize untrusted parties in adversarial settings. Good tool for public AI work.

English
11
5
37
4.9K
𝔊𝔥𝔬𝔰𝔱
𝔊𝔥𝔬𝔰𝔱@_0xghost_·
Lots of angst on the TL about crypto, sure it’s in a slow phase rn, it’s a bear market, but crypto is better than ever. More interesting projects, all fair launched. Only ppl for whom it is worse are farmers bc they made all their money begging & now there are no more handouts
English
9
4
69
3.1K