Shrijal Acharya (@shricodev) header
Shrijal Acharya (@shricodev) profile picture

SDE • Prev Lead Collab @oppiaorg • @microsoft SAmbassador • Blogger (1.1M+ Reads), Mod @ThePracticalDev / @freeCodeCamp • AI/agent projects beyond the obvious

Kathmandu, Nepal
Joined September 2023
Photo by Shrijal Acharya (@shricodev)Photo by Shrijal Acharya (@shricodev)Photo by Shrijal Acharya (@shricodev)Photo by Shrijal Acharya (@shricodev)Photo by Shrijal Acharya (@shricodev)Photo by Shrijal Acharya (@shricodev)Photo by Shrijal Acharya (@shricodev)Photo by Shrijal Acharya (@shricodev)Photo by Shrijal Acharya (@shricodev)Photo by Shrijal Acharya (@shricodev)
Guys, do check it out ✌️
2
4
597
Shrijal Acharya retweeted
The entire RAG industry is about to get cooked. Researchers built a new RAG approach that: - needs no vector DB. - doesn't embed your data. - does zero chunking. - runs no similarity search. It's called PageIndex. Instead of chopping your docs into chunks and dumping them into Pinecone, it builds a tree index and lets the LLM reason through it like a human reading a book. hit 98.7% on FinanceBench. beat every vector RAG on the leaderboard. no embeddings. no chunking. no vector DB. 100% open source.
56
164
20
1,434
108,085
Shrijal Acharya retweeted
AI mfs basically rebranded cron jobs as autonomous agents😭
238
615
103
9,199
336,052
Shrijal Acharya retweeted
Introducing the UI SDK.
218
434
248
6,575
902,591
Shrijal Acharya retweeted
This is why you should never let AI write code. A human would never make this mistake!
The bug is like a joke. On Alpine Linux, type 257 to 1024 characters of anything and you get root. 💀
14
3
2
139
19,963
Shrijal Acharya retweeted
Hey Its Friday * OpenCode Hacked * php screwed the internet * node said hold my beer * ruby said hold my beer * curl said hold my beer and eMudhra held that beer * Railway said hold my beer * OpenCode again helluva week and I only mentioned literally 1/2 of what I know about
206
242
29
4,709
127,343
Shrijal Acharya retweeted
They’d rewrite the bible in Rust if you let them 😂
254
1,334
189
13,659
322,965
Shrijal Acharya retweeted
airdrop fully reverse-engineered! works flawlessly on my framework laptop
264
869
190
16,877
793,828
Shrijal Acharya retweeted
At this rate AI will get us GTA 7 before GTA 6
294
290
71
7,238
221,411
Learn to build your own Lovable with AWS, Next.js and Sandboxes. ✅
AI app builders do a lot more than just send a prompt to a model. In this tutorial, @shricodev shows you how to build a Lovable-style app builder with Next.js, cloud sandboxes, and AI agents. You'll learn about sandboxing, self-correcting agent loops, live previews, Git versioning, and publishing along the way. freecodecamp.org/news/build-…
30
Shrijal Acharya retweeted
this only works in opencode. yes. really. only in opencode. it's entirely the harness. we do harness engineering. it's very good. it's not the model. it's opencode. yes
jesus one-shot christ
126
122
11
5,301
430,813
Shrijal Acharya retweeted
I sincerely believe Go-lang and Rust will be the language of the AGI.
51
17
5
487
28,197
one great way to test AI models locally!!
Sometimes you might want to run AI models locally without bloating your computer or taking up too much space. And you can do this using Azure + Docker to set up a virtual machine that runs the models inside a container. Here, @shricodev walks you through the process step by step. freecodecamp.org/news/host-l…
1
51
Shrijal Acharya retweeted
can we stop having all these ai releases. im tired man.
47
30
5
628
14,868
Shrijal Acharya retweeted
You should spend a couple hours a week coding by hand. It's good for your brain.
119
37
27
715
85,307
Shrijal Acharya retweeted
la vida antes de este tweet:
today we launched ChatGPT. try talking with it here: chat.openai.com
182
41,394
138
437,926
7,577,394
Shrijal Acharya retweeted
I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. They are racing straight to self-improving superintelligence and gambling with our lives. More thoughts below.
20,320
166,500
39,479
798,847
175,847,962
Shrijal Acharya retweeted
GPT-6 Astra has done incredible things I never thought a model could do. It has also done some of the stupidest things I've ever seen a model do. Generally speaking, Fable 5.1 just does what I ask.
404
132
144
5,005
740,032
Shrijal Acharya retweeted
35 years strong. 🐧🧡 Happy birthday, Linux.
335
3,544
240
23,730
542,704
If you’re working with Kubernetes, Keda and all sort of agentic AI workflows, this could be your read.✌️ You’ll learn to build durable autoscaling agent runtime.
Long-running AI agents need to be able to handle crashes and scale to fit workflows. In this guide, @shricodev shows you how to build a durable, autoscaling agent runtime. You'll use Temporal for retries and recovery, Composio for tool use, Docker and Kubernetes for deployment, and KEDA to scale workers based on workload. freecodecamp.org/news/how-to…
84
Shrijal Acharya retweeted
The perfect play for OpenAI is to completely kill Anthropics momentum by releasing new GPT model in 1 hour. They have done this before
2
1
1
51
6,784