GenAI Engineer building AI systems & developer tools | RAG, Agents, LLM Apps & Automation | Building @tosdevelopers

Bengaluru, India
Mutual Respect For Everyone, Positivity In Mind, Hope In Thought, Promise In Ambition & Discipline In Life Is the recipe of greatness
1
1
23
1,620
day review | Sept 27 woke up at 7 am 1h workout & breakfast 4h of work split in 3 session 2+1+1 with 15m gap in between, mostly tested prototype and talk to 4 potential users having a similar pain point had lunch and cleaned my room entirely 2h of walk in the park with friends & chill catc up with x timeline had dinner & nice time with family probably will sleep now happines score 7/10 satisfaction score 8/10 improvement areas : i will prioritize chilling on weekends than work, try to have 1h learning session and minimize workout if it give me fatigue
1
1
18
happy sunday everyone hope you all got the chance to chill and relax with family and friends or any possible relaxing activities experience life as it's precious and worth living ✨️
30
day review Sep 26 woke up at 06:30 am work out for 2h (1st time in life at a gym and honestly I don't know what I did maybe just followed the trainer's advice) had shower and healthy breakfast slogged 4h works on my SLM project by 2h a session with 30m break for light lunch catch up with my X timeline 1h badminton with my boi had dinner and hopefully will sleep now will give myself a 8/10 on the effort to correct lifestyle hopefully I pivot to healthy living soon 🙏
2
2
61
recently my life has become very undisciplined, hope to get things back on track starting tomorrow wish me luck 🙏
2
4
89
can you suggest me a practical guide to learn SaaS distribution
2
2
130
thought profile picture needs an update and now my blue tick gone for few days 🤔 how insightful
1
94
stop going directly to distributed architecture first stay focused on monolithic architecture until scale/team functionality demands it
5
5
169
If you have to explain TypeSafe AI's new model Jev to a person who generally works using llm models how would you explain 🤔
2
161
Most devs are burning thousands of dollars using GPT-4 just to route an if-else statement. If your LLM call only decides which backend team gets a ticket, you are hiring a NASA engineer to flip a light switch. It is slow, expensive, and completely unnecessary. This is why Jev is blowing up. It is not here to write your code or draft essays. It is purely a System 1 decision engine. Because it does not generate text word by word, it runs around 200 times faster, and output tokens cost zero. You just get the choice, boolean, or score instantly. Stop making giant frontier models do basic triage. Save them for real thinking and let tiny evaluators handle the traffic.
2
6
132
for muse it will take time
𝗜 𝘁𝗲𝘀𝘁𝗲𝗱 @bot 𝗮𝗻𝗱 @Muse 𝘀𝗶𝗱𝗲 𝗯𝘆 𝘀𝗶𝗱𝗲, 𝗮𝗻𝗱 𝗱𝗿𝗲𝘄 𝗯𝗼𝘁𝗵 𝗵𝗮𝗿𝗻𝗲𝘀𝘀𝗲𝘀 𝗯𝘆 𝗵𝗮𝗻𝗱. One from @SpaceXAI, one from @AIatMeta under @alexandr_wang. Neither is open source, so I tried both and drew the architecture myself from whatever docs exist. Tbh I struggled quite a bit to find real use cases that can surprise me beyond what we have on Claude Code and Codex, but maybe we are just getting started on personal agent harnesses. 🌟 Github Repo (1.8k): github.com/ShenSeanChen/waku… 💻 Portable memory: waku.one ☕ Join our community: seanchen.io Some quick differences I found: Grok Bot gives your whole account one cloud VM where every Bot shares the browser, the /workspace, the terminal and the credentials, so a Bot is isolating a personality rather than a context. Muse gives each person one secure VM with a single agent, and a Sentinel sitting outside the container holding your tokens. Strip the branding off either one though and it's the same chain: one VM → connectors → routines → approval gate → memory What surprised me is that Muse ships a memory.md you can read, edit and download, but Grok Bot doesn't. I didn't find where it keeps memory at all. So I gave both of them @waku_agent memory over MCP instead, saved a fact in one harness, and the other one recalled it cold in a fresh chat. I also killed the shopping test halfway. I felt Amazon was built for humans to read and click, and I wasn't handing an agent my login username and password. Maybe the fast checkout use case is a better fit for software / AI product purchases. Watch it, then save both harness diagrams below. 🔖 You Can Build Anything. You Can Learn Anything. 💪
1
5
213
open source has higher risk 🙃 If someone releases a highly capable model with dangerous capabilities and the weights are freely downloadable, you can't realistically "take it back". publishing of open source llm models is fun as developers to experiment but it lacks ai safety
5
8
100
good morning let's catch up whatever missed 🐬
1
3
54
AI search is getting interesting. We’re used to checking Google rankings, SEO, backlinks, etc., but now there’s another question how does AI actually see your brand? Citex looks at that from a different angle, including which competitors and sources show up across AI search tools. Feels like this is going to become a much bigger part of marketing. trycitex.online
1
3
56
entire day was mess with bug in production that got resolved now hoping for peace now 😌
1
3
54
goat for a reason
Bernhard Riemann was born 200 years ago today. He died at the age of 39. Here is a list of things named after him: Riemann bilinear relations Riemann conditions Riemann form Riemann function Riemann–Hurwitz formula Riemann matrix Riemann operator Riemann singularity theorem Riemann surface Compact Riemann surface The tangential Cauchy–Riemann complex Zariski–Riemann space Cauchy–Riemann equations Riemann integral Generalized Riemann integral Riemann multiple integral Riemann invariant Riemann mapping theorem Measurable Riemann mapping theorem Riemann problem Riemann solver Riemann sphere Riemann–Hilbert correspondence Riemann–Hilbert problem Riemann–Lebesgue lemma Riemann–Liouville integral Riemann–Roch theorem Arithmetic Riemann–Roch theorem Riemann–Roch theorem for smooth manifolds Grothendieck–Hirzebruch–Riemann–Roch theorem Hirzebruch–Riemann–Roch theorem Riemann–Stieltjes integral Riemann series theorem Riemann sum Riemann–von Mangoldt formula Riemann hypothesis Generalized Riemann hypothesis Grand Riemann hypothesis Riemann hypothesis for curves over finite fields Riemann theta function Riemann Xi function Riemann zeta function Riemann–Siegel formula Riemann–Siegel theta function Free Riemann gas Riemann invariant Riemann–Cartan geometry Riemann–Silberstein vector Riemann-Lebovitz formulation Riemann curvature tensor Riemann tensor Riemannian graph Riemannian group Riemannian holonomy Riemannian manifold also called Riemannian space Riemannian metric tensor Riemannian Penrose inequality Riemannian polyhedron Riemannian singular value decomposition Riemannian submanifold Riemannian submersion Riemannian volume form Riemannian wavefield extrapolation Sub-Riemannian manifold Riemannian symmetric space Riemann's differential equation Riemann's existence theorem Riemann's explicit formula Riemann's minimal surface Riemann's theorem on removable singularities
1
3
56
good morning 🌅 hoping for a productive day
3
4
61
good night folks 😴
3
4
79
Joy Chakraborty retweeted
Jean-Pierre Serre turns 100. Youngest Fields Medalist ever: 27. First Abel Prize laureate: 2003. and still editing Wikipedia.
16
158
1,549
115,643
just so glad that i am able to connect with 200 awsome people who love talking about ai, it's implications, safety and also so many different genres such as crypto, trade etc honestly i learn a lot from different experiences and povs X is awesome and so is its people ❤️😇
4
6
123
i love open source, it gave me so much opportunity as a student and junior dev that i become capable of writing/understanding/debugging code, gave access to so many softwares otherwise i would not have the opportunity to learn, i am so greatful ❤️ but for that i cannot say that open source models are reviewed as aggressively as proprietary ones, they have dedicated team and mission statement, it's simply hard to match are we risking security issues at open source, im open to hear opinions irrespective of you agree/disagree with me
4
3
97