Krishna Sangeeth @whiletruelearn

The pravasi song from Thakara is a mood lift song. Not sure what happened to their band. Need more OC like this.

standard VLMs generate box coordinates token-by-token. this creates a sequential bottleneck LocateAnything introduces parallel box decoding (PBD) it predicts each full bounding box (or point) as an atomic unit in one forward pass. this unlocks massive parallelism

LocateAnything is a new vision-language grounding model from @NVIDIAAI performs diverse localization tasks like dense object detection, GUI element finding, OCR, document layout, and referring expression comprehension NVIDIA is demoing it at CVPR today

Total BS asking people to download a closed source binary.

my bucket list from a long time back.

@aswinmohanme Oh that’s rough man.

Caught a very bad flu. Not sure what’s running in ernakulam but i have never been this fast to ask antibiotics from a doc.

Meet Vedant Shrivastava, Nisarga Adhikary, and Sarthak Sidhant ,they exposed CBSE in every possible way : 17 years old Vedant Shrivastava : > Applied for the CBSE re-evaluation process > Got a different Physics answer sheet > Posted it on X > Got labelled "Pakistani" by the BJP IT cell > Brought CBSE to its knees and proved them wrong 19 years old Nisarga Adhikary : > Bro hacked the CBSE website > Reported the vulnerability to them > But they didn't take any action > Then bro posted it on X > Showed everyone that it could be hacked 18 years old Sarthak Sidhant : > Bro exposed a CBSE tender > Took it to X > Wrote a detailed thread > Explained how the CBSE OSM tender conditions allegedly favoured COEMPT > And today came on the media > Exposed them with facts These three boys are doing what whole media failed to do, all of them took x to expose CBSE .

Amazing that the genz is questioning the system , these kids are the future of our country . Absolute power corrupts absolutely and the effects of that corruption is now for everyone to see.

ANI @ANI

a week ago

#WATCH | Ranchi, Jharkhand | A class 12th student, Sarthak Sidhant, says, “…I have written a blog that compares the tender documents of CBSE. I have uploaded and published it… There were at least 15 discrepancies, as per my blog. I would like to highlight three or four of them.

571 6K 19K 1.6M 2K

CBSE people didn't configure their AWS bucket properly and now we can paginate & enumerate all their media which has 2026 answersheets & question papers. ListObjectsV2 works without any auth and the bucket root is listable too — anyone on the internet can download any scanned booklet — across institutions. Multiple institutions are using the same bucket, insanely insecure.

@ni5arga @cbseindia29 good morning CBSE, you said you used scanners to scan these copies, now since the copies are out to the public view, do you mind explaining which copies when scanned through a scanner, have a drop shadow? and these 3 folds? did you really use scanners?

Hey @ICICIBank why don’t you allow credit card payments via UPI for your accounts without savings account linked. I am forced to use other apps like Cred just because i don’t want to do netbanking.

hermes update fixes all the current issues with it.

We've created the world's fastest PDF parser ⚡️ And it's more accurate than any other open-source, model-free PDF parser out there (pymupdf, pypdf, markitdown, pdftotext, opendataloader, pymupdf4llm) Introducing LiteParse v2 - we rewrote the entire library into Rust and adapted it as native packages for Python and Node. It supports 50+ different document types, can be triggered directly or installable directly within your favorite AI agent. Blog: llamaindex.ai/blog/liteparse… Repo: github.com/run-llama/lite…

LlamaIndex 🦙 @llama_index

2 weeks ago

LiteParse v2.0 is out now, and it is blazing fast + runs everywhere! We rewrote everything from scratch in Rust, and now: - up to 100x faster parsing - install natively in Rust, JS/TS, and Python - a custom WASM package enables browser and edge runtime usage pip install

32 72 608 497K 681

Just some reflections on being a solo founder shipping software. serendipitylabs.in/blog/six-thing…

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

AI might end social media as we know it. When everyone can write like the best writers in the world, and generate perfect photos where nobody knows what’s real or fake anymore, the marginal dopamine hit of showing superiority over you fellow humans die.

UPDATE: Came up with an even better version of this prompt after the feedback Ask Codex to look across your sessions, Memories, and Chronicle, identify patterns, reuse what already exists, and only create the smallest useful skill, subagent, or automation. "Look back over my recent work from the last 30 days, or all available history if shorter, and identify repeated manual workflows worth packaging. Use available evidence in this order: - Recent Codex sessions and task summaries. - Codex Memories and rollout summaries to find patterns repeated across sessions. - Chronicle, if enabled, to spot repeated work outside Codex. Use Chronicle for discovery only; confirm important details in the relevant source system when possible. - Existing skills, custom agents, and automations, so you reuse or extend what already exists instead of duplicating it. Look broadly for work that is repeated, time-consuming, error-prone, context-heavy, or benefits from a consistent process. Include workflows across coding, research, writing, planning, communication, operations, analysis, and personal administration. Only act on a candidate when it: - occurred at least twice, or is clearly likely to recur and costly to repeat; - has stable inputs, a repeatable procedure, and a clear output or stopping condition; - would materially improve speed, quality, consistency, or reliability; - is not already adequately covered. Choose the smallest appropriate form: - Skill: a reusable workflow or playbook. - Custom subagent: a bounded specialist role or investigation task suitable for delegation. - Automation: a scheduled or recurring check, report, reminder, or monitor. - Skip: work that is too one-off, ambiguous, sensitive, or poorly evidenced to package. First produce a compact shortlist with: - repeated workflow - supporting evidence and dates - frequency/confidence - recommended form: skill, subagent, automation, extend existing, or skip - why it is or is not worth creating Then create only the high-confidence missing items. Keep them narrow, practical, source-aware, and easy to validate. Do not create speculative, overlapping, or overly broad assets. Finish with: - what you created or extended - what you deliberately skipped - what needs more evidence before packaging"

Vaibhav (VB) Srivastav @reach_vb

2 weeks ago

Copy and paste this into your codex: “Look through my recent Codex sessions and identify repeated workflows or repeated asks. For anything I keep doing manually, suggest: 1. a skill if it is a reusable workflow 2. a custom subagent if it is a bounded role or investigation task

40 110 1K 286K 2K

Kiro web looks cool and has 50% usage free till May 29th.

youtu.be/lQxrHmjHf28?si…