harsh (@senbodev) header
harsh (@senbodev) profile picture

aspiring farmer, professional larper

Joined October 2023
Photo by harsh (@senbodev)Photo by harsh (@senbodev)Photo by harsh (@senbodev)Photo by harsh (@senbodev)Photo by harsh (@senbodev)Photo by harsh (@senbodev)Photo by harsh (@senbodev)
Introducing Chat0 - Blazingly Fast, Free, Open Source AI Chat App - Multi Model Support (Gemini, GPT, DeepSeek) - Privacy-first (all data stored locally in your browser) - BYOK / Unlimited Messages - Chat Navigator (easily navigate a large chat) beta available now
are there really no open source t3 chat app alternatives ?????
106
80
16
1,542
354,942
😂😂😂
JUST IN: Jim Cramer says stock market is going to "boom"
4
151
saw my last year tweets
1
11
394
guys we are almost at the climax, be ready.
Sam Altman: "The world needs to accept that bad things will happen for AI to move forward."
6
413
manipaal
would you rather: > 6 months as an unpaid research intern at MIT or > 6 months as an SDE intern at Google, earning ₹1L/month assuming you're still in college. which one?
1
3
210
The landing is so good, lmao
hex was fully vibe coded. the app. the landing page. the animations. sound effects were ai generated. issues people open are fixed by opencode. the onboarding. even some of the creative ideas but i think it's pretty good software. it's fun to use. works on all platforms. performant (not electron!) our effort didn't go into the code. but there was a lot of effort it's a small app but i hope it improves your outlook on where we can go
6
363
so you can now download RAM, wtf.
1/4 Meet Qwenputer: Qwen3.5-4B with a full RISC-V CPU inside its weights, using the model's own Gated DeltaNet layers as RAM. It runs C and MicroPython in its forward passes, no external runtime. On DeepMind math: base 55–90%, base + Python tool 95–100%, Qwenputer 97.5–100%.
3
229
Number of questions asked on Stack Overflow: September 2021: 119,730 September 2024: 24,732 September 2026: 986
2
1
14
447
Replying to @lydiahallie
wait is it just me or is Opus 5.5 dumber
2
184
Introducing Kimi K3.1 Pro: our most capable 3T-class open-weight model. 🔹 1M-token context, 2.8T total / 104B active params (MoE), Multimodal. 🔹 Full-project coding: games in Unreal, Unity & Godot. 🔹 Excels at parametric 3D modeling in Blender & CAD. 🔹 More reliable at finance work: Accurate modeling with hallucination down by 65%. 🔹 Matching the strongest proprietary models across coding, agentic and knowledge benchmarks. Kimi K3.1 Pro and K3.1 Pro Highspeed (2–3× faster) are now live on Kimi.ai, Kimi Work, Kimi Code, and the Kimi API. Open weights by Nov 4, 2026. 🔗 API: platform.kimi.ai 🔗 Tech blog: kimi.ai/blog/kimi-k3-1-pro
5
203
I heard they found CVE 10 in html
1
12
440
POV: You never learnt PHP
1
21
720
freak quick - haikyuu!!
Small plays - Basketball
2
1
17
433
never deleting this app
2
4
55
1,343
Holy grail of coding agents
13
486
I get inspired by literally everything: old ads, packets, signboards. But Indian vintage design is so hard to find. It’s scattered across old newspapers and random blogs. So I made Virasat, an online museum of India’s everyday design 🧵 virahst[.]vercel[.]app
3
4
6
168
recursive self slopification is the new moat
1
13
527
Now add stremio on it and delete every subscription you have
Vibe coded my parents' TV this afternoon! It was showing a sponsored ad before you could even get to Netflix. Gave Claude Code the model number, it found the TV on wifi, removed 25 Xiaomi packages and wrote a new launcher. Looks like an Apple TV now lol
15
4
2
574
32,356
harsh retweeted
I get inspired by everything: old ads, packets, signboards. But Indian vintage design is hard to find. It’s scattered across old newspapers, blogs and random corners of the internet. So I built Virasat, an online museum of India’s everyday design 🧵 virahst.netlify.app
1
3
2
38
leetcode is dead.
hackerrank disavowing and apologizing for causing leetcode interviews
1
19
457
I can smell a oss model release soon
3
224