laxman

2.8K posts

laxman banner
laxman

laxman

@llmluthor

19 | It is our moral obligation to make an impact in the world proportionate to our potential | shippin @vektorimemory prev: cognitivelab, bhindiai(upsurgelabs)

가입일 Eylül 2022
432 팔로잉162 팔로워
고정된 트윗
laxman
laxman@llmluthor·
We built an AI that remembers like a brain, not a database. Vektori builds a living graph of every conversation you've ever had. Fresh concepts glow bright. Old ones fade, unless you reinforce them. 20+ daily users trusting us with their entire digital memory. No venture backing. Just pure engineering spite :)
English
6
4
16
1K
abhinav
abhinav@AbhinavXJ·
It's crazy that most of us leave our home one random day after 12th class, and since then we only get to see our parents few days a year
English
28
14
425
10.9K
laxman
laxman@llmluthor·
"agentic payments is the future" stop. please stop
English
0
0
1
42
laxman 리트윗함
Neelmani
Neelmani@NeelmaniBagaria·
So, @suhasasumukh and @heettike are cooking this weekend - $1000 in 48 hours, locked in at the HQ @localhostIND X @noicedotso wasn’t on my cards for this march. We’re wrapping Day 1 of the 48 hours and here is the rundown of who’s doing what! 1. @Muskanjain0401 and @aashatwt are building gamified prediction market for friends to dare 2. @10KRotator is building AI agents for expense reports for treasuries onchain. @myStableCorp is a compliance wrapper 3. @notcodesid is building a hyper liquid Algo-trading bot that bets on 5/15 min plays 4. @17Vardani is building a tool that summarises website content visually (think flow charts and mind maps) and auditoryly 5. @7613Perfect and @DsouzaJovian are building an AI video editor with taste. 6. @llmluthor multi agent framework for orchestration and context management 7. @AlexQHunterz Your AI ghostwriter that never sleeps and posts wherever you don’t 8. @vzy010 and @prshbt are building a platform where a token(coin) is minted for a clanker🤖 by typing a vibe and the internet does the pumping - @rotdotrun 9. @Th3lazykid is building a trading bot for @HyperliquidX 10. @itsnishu is building a personalised temogachi assistant 11. @developvthayush is building systems to replace telephones from hotels. 12. @technosh_ does launch vids for start-ups. 13. @PrakharKhatri3 is building a CLI tool to trace & audit autonomous code 14. @vikings_ace and @notacadia are building a no-code node based editor to fine tune AI models 15. @Prem__Mali is pixel perfecting figma to code 16. @probablyaayushi is building an agent to analyse social profiles 17. @hrdktwt is building a chrome extension for bookmarking links and making it intelligent and interactive 18. @anshdixit123 , @Ta_nush & @projektkush are building a creative intelligence tool for D2C/marketing teams 19. @Thevirofficial is building a platform to automate and post AI avatar content for founders. 20. @ArnavvSharmaa & his team are vibe coding and pumping websites. 21. @swarajb is building a Social media for comments to DM 22. @dipanshuhappy is building AI agents that hack for bug bounties (White hat penetration-testing) 23. @AyushSagar31980 mines social media platforms to predict what software people will pay for 24. @whotanish is building an AI pipeline for AI UGC creation Stay tuned for day 2’s updates! We’re at T-37 hours.
English
6
21
96
5.8K
laxman 리트윗함
ManIT
ManIT@AlexQHunterz·
spent 2 hours setting up OpenClaw from scratch at the $1,000™ hackathon @ localhost HQ Bengaluru - Telegram bot: running - custom skills built + installed: 4 - prior OpenClaw experience: zero building AI agents that actually do things > talking about building AI agents $1,000™
English
0
1
3
147
Adithya S K
Adithya S K@adithya_s_k·
Who else coming , would love to connect !!
Adithya S K tweet media
English
31
0
124
5.8K
laxman
laxman@llmluthor·
let’s go! got into yc’s first startup school in india! Excited!
laxman tweet media
English
2
0
9
184
laxman
laxman@llmluthor·
@interitionai the graph shape problem is really a trust boundary problem in disguise lol
English
1
0
0
17
INTERITION AI
INTERITION AI@interitionai·
@llmluthor That's cool. Triples not always the answer for asking ‘what graph shape?’ but shapes could help agent memory scope, permissions, revocation, clean boundaries between task memory and stuff. Otherwise the structure gets smarter while still failing us.
English
1
0
1
36
laxman
laxman@llmluthor·
built voice agent memory from the ground up ditched knowledge graphs- not everything fits subject object predicate > 4 edges: corrects, causes, resolves, confirms > collapse entire convos into causal graphs > deep BFS traversal for retrieval demo 👇
English
2
1
10
128
laxman
laxman@llmluthor·
@mufasaYC They acquired traction and popularity. Acquisition is based on either of them: Team Revenue Traction
English
0
0
0
52
Mustafa Yusuf
Mustafa Yusuf@mufasaYC·
I don’t get it. Why would Facebook acquire Moltbook? Are their engineers too busy recording a day in the life of a meta engineer and cannot build it in a week or so?!
English
97
5
801
81.2K
laxman
laxman@llmluthor·
every voice agent has the same problem. your customer remembers the last call. your agent doesn't. building the fix.
English
0
0
0
48
Paras Chopra
Paras Chopra@paraschopra·
My dear young person, Don’t succumb to mediocrity. There’s enough of it going around. Aspire for craftsmanship, as that is what leads to joy and beauty. The world needs more people who’re proud of what they make, and less of those who couldn’t care less.
English
62
468
4.2K
90.3K
laxman
laxman@llmluthor·
@sanghvian @riverline_ai cool, so do minions get better over time or someone has to manually update them? like engineers write them manually?
English
0
0
0
15
Ankit Sanghvi
Ankit Sanghvi@sanghvian·
Every engineering team has their own patterns and process of coding that the agents should be following. @riverline_ai has internal skills called minions, that ensures engineering consistency across our team. The new IDE that'll win will be the one that enables 30+ agents' management while still taking into account - personalization of skills + personalization of process (eg: create linear, make plan doc, push PR).
English
1
0
3
96
laxman
laxman@llmluthor·
Proud to have contributed to this! 🚀 Omnidocs is live - unified visual document processing, 15+ models, runs on consumer GPU/Mac. We built something real here. Go check it out!
Adithya S K@adithya_s_k

Introducing Omnidocs - Unified Visual Document processing toolkit ✅ 6+ document processing tasks ✅ 15+ Model supported ✅ Runs on consumer GPU/ Mac ✅ Supports multiple backend - Pytorch, vllm, mlx, open responses API Get started → pip install omnidocs✅

English
0
0
9
100
laxman
laxman@llmluthor·
@striver_79 Decisions driven thru emotions are rarely right though
English
0
0
0
17
Nayrhit B
Nayrhit B@NayrhitB·
The exact pitch deck that helped us raise a $9M Seed Round copy whatever you want VCs that invested: → @SusquehannaVC (led) → @LightspeedIndia@BCapitalGroup → Seaborne Capital → @beenextVC@sparrowcapvc@2point2club joined. fundraising is hard enough without guessing what investors want to see. so - I'm making our deck public. if you're raising right now, take it and make it yours. Reply 'deck' + follow (so I can DM it over)
Nayrhit B tweet media
English
2.3K
113
1.7K
191.1K
laxman
laxman@llmluthor·
take: "everyone's doing this" is a good sign means the market exists means people are willing to pay for solutions means you are not too early you just need to be 10x better at ONE thing
English
0
0
1
40
laxman
laxman@llmluthor·
hunger is the thing. skills can be learned, hunger can't.
English
0
0
0
46
laxman
laxman@llmluthor·
@paraschopra system, infra level is where the moat lies
English
0
0
0
15
Paras Chopra
Paras Chopra@paraschopra·
I’m bearish on software-only startups / products. The first rule of business is that success comes from differentiation, and building software is no longer a differentiation. The alpha has shifted to whatever you can’t vibe code - the messy / boring / unsexy parts like building an on-ground logistics network, nurturing customer or vendor relationships, investing in brand or distribution and so on. So if you’re building a startup, ask yourself: what part of it isn’t replicable in one or few Claude code sessions?
English
99
40
895
46K