GS

[hacker.house @hackerfantastic]

How to find 0day using local LLM's and "recursive prompting". I used this approach on a NVIDIA DGX Spark using Qwen 3.6 heretic and LLAMA.cpp with LiteLLM and Openclaw. It successfully analyzed a complex FOSS code base and found a single high-risk RCE 0day.

[GS @Svz477]

@kingofknowwhere which app

[Brad Mills 🔑⚡️ @bradmillscan]

I want to know how many fucking people were involved in making this promo

[AI at Meta @AIatMeta]

We’re sharing the next major milestone in our non-invasive brain-to-text decoder research: Brain2Qwerty v2.

Building on v1, which was published today in @Nature, Brain2Qwerty v2 is the highest-performing end-to-end pipeline capable of real-time sentence decoding from raw brain signals. It advances beyond character-level performance to decoding words and semantics, enabling accuracy for overall communication.

We believe this research has the potential to make a real difference for the millions of people who suffer from brain lesions or disorders that prevent them from communicating.

🧵👇

[Axel Bitblaze 🪓 @Axel_bitblaze69]

Claude code, completely free, forever.

a github repo called free claude code reroutes your claude code traffic to 10 different free / cheap providers like,

DeepSeek, Kimi, GLM, MiniMax, Qwen, and 5 more.

20,000+ devs running it.. setup takes 5 mins.

HOW TO SETUP (5 mins)

1. install claude code if you haven't
npm install -g @anthropic-ai/claude-code

2. install uv + python 3.14
curl -LsSf https://t.co/q8CRwASdgK | sh
uv self update
uv python install 3.14

3. install the proxy (single command)
uv tool install --force git+https://t.co/DLvG1IbHO8

4. start the proxy
fcc-server → opens Admin UI at http://127.0.0.1:8082/admin

5. configure in Admin UI:

paste your NVIDIA NIM key → Validate → Apply (free key at https://t.co/LDclhBfaV5)

6. launch claude code
fcc-claude

done. /model picker now auto-discovers every model your proxy can reach.

repo: repo: https://t.co/5OVDqUFW3x

[Isra @israfill]

you can use unlimited FREE deepseek v4 pro & flash, minimax m3, gemini 3.5 flash with zero credit card 😳

b. ai giving 500k free credits on signup, no verification needed

what you get:
- deepseek v4 pro & flash
- gemini 3.5 flash
- minimax m3
- more frontier models

it's openai compatible so you can plug it into any agent or bot. you just swap the base url and your existing tools work

full setup guide (bai 500k free credits):

step 1: go to https://t.co/pK3GidYD3R
> click "try b. ai" in the top right

step 2: sign up with google
> any gmail works, burner is fine.

step 3: credits appear instantly
> 500,000 in your account. no card, no verification need

step 4: swap your base url
> replace your openai endpoint with https://t.co/pK3GidYD3R's api endpoint
> all your existing tools and agents just work

step 5: repeat with a fresh email when you run out
> use [email protected], [email protected] etc
> each account gets 500k fresh credits
> incognito browser for each one

there's also a 1:1 top-up bonus up to $100 if you run through it all

meaning you deposit $10, they give $10 free extends your credits without creating new accounts

3 things to test with 500k credits:
1. stress test your agent pipeline across 4 models at once
2. compare model outputs side by side to find your cheapest option
3. run batch inference on a dataset without worrying about cost

this is the most generous free credit offer live right now

bookmark this and get this before the subsidy pool runs out

[Damir Akaza @Damir_Akaza]

A Carnegie Mellon student launched a Markov Chain model that reads the structure beneath the price and made $67,000 in three weeks on Polymarket.

In his applied mathematics classes he studied Markov Chains - the same model physicists used to simulate neutrons in nuclear reactors.

The same model describes how prices move on prediction markets.

He wrote a Python script.

> Takes 60 days of contract price history.

> Builds a transition matrix - a map of how the price actually moves between states.

> Runs 10,000 simulations in a tenth of a second.

> Calibrates the result against data from 72.1 million real trades.

The output is an exact probability and position size. No gut feeling.

His first test day brought $3,400.

A week later he improved the result and hit $17,000.

His balance has now reached $67,000.

full guide on how to build the same model - in the article below.

[HankAI @hank_aibtc]

卧槽 OpenAI 终于干了件人事！！！🔥

2026 年第一个开源模型来了——Privacy Filter，
Apache 2.0 直接放出！

1.5B 参数的 PII（个人信息） 检测神器，
专门把文本里的姓名、地址、电话、邮箱、身份证这些敏感信息秒红action掉。

关键是它能在你浏览器本地跑，WebGPU 直接干，
完全不用传服务器！

核心亮点：
1. 多语言支持
2. 完全本地运行（Transformers.js + WebGPU），无需上传服务器，浏览器即可使用
3. 实时处理文档，隐私保护优先

适合合规审核、
用户数据处理、本地隐私工作流等场景。
演示效果非常流畅，尤其适合需要强隐私保障的团队和开发者。

地址评论区👇

[Alex Zajac (🍔,🧠) @itsalexzajac]

An engineer built an interactive book on data structures and algorithms of 680 pages:

[HackerRank @hackerrank]

The role of a developer has changed. You're not just writing code, you're orchestrating agents.

Introducing HackerRank Orchestrate, a 24-hour hackathon to design, build, and ship an AI agent that solves real-world problems.

May 1 - 2 | Virtual
Registrations close April 30, 8 PM IST

Think you've got what it takes?

Register now: https://t.co/CnnGh8bERh

[Claude @claudeai]

Introducing Claude Managed Agents: everything you need to build and deploy agents at scale.

It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days.

Now in public beta on the Claude Platform.

[ℏεsam @Hesamation]

bro created an AI job search system for Claude Code that scored 700+ job applications and actually got him a job.

AND IT'S NOW OPEN-SOURCE.

It scans multiple company career pages, rewrites your CV per job, and even fills application forms. The repo has:
> 14 skill modes (evaluate, scan, PDF, ...)
> Go terminal dashboard
> ATS-optimized PDF generation via Playwright
> 45+ companies pre-configured (Anthropic, OpenAI, ElevenLabs, Stripe...)

GitHub: https://t.co/PwrYBOAphi

[Gabriel Chua @gabrielchua]

Every builder gets API credits + ChatGPT Pro + good vibes only.

$100k+ prize pool of credits and subscriptions.

@OpenAIDevs @reach_vb @yashrajnayak
@GrowthX_Club @abhishek @udayan_w

https://t.co/LapBEh2kmP

[meg.ai 🇨🇦 @MeganRisdal]

This looks like a very good hackathon! 💎💎💎💎 https://t.co/e2oNOPukhw

[Jonathan @joniverbeet]

If you're a vibe coder who loves building cool stuff, listen up.

Right now, we're running a vibe coding competition at https://t.co/C1CShogyZP.

The challenge is to build an AI News website (full details on the site).

There's a $1,000 prize pool for the top 5 builds.

Join now.

[Gabriel Chua @gabrielchua]

On 29 April, we’re bringing together the most ambitious builders for Australia’s first Codex Hackathon 🇦🇺

Build something in a single afternoon that wouldn’t be possible without Codex.

~$200K USD in credits & subscriptions up for grabs.

We’ll bring the tokens and vibes ✨ - see you there.

Link below 👇

[Dan McAteer @daniel_mac8]

This is amazing. Do this.

[Boris Cherny @bcherny]

I wanted to share a bunch of my favorite hidden and under-utilized features in Claude Code. I'll focus on the ones I use the most.

Here goes.

[BuBBliK @k1rallik]

> been paying $200/month for cloud AI APIs
> laptop: M2 MacBook, 16GB RAM
> tried running models locally, garbage quality after 4K tokens
> read this TurboQuant breakdown on Tuesday
> applied 3-bit KV cache compression
> same MacBook now runs 100K token conversations
> quality: identical to cloud
> cancelled all API subscriptions Wednesday
> it's been 3 days
> saved $200/month forever
> with a free algorithm from a free paper
> my MacBook didn't change. the math did