Joyboy

A brief summary of the new auto-browser update/refactor. Auto Browser v1.1.0 is live. This is the architecture release. The project moved from a working browser-control system into a cleaner, more extensible MCP-native browser platform. The controller is no longer centered around a few oversized files. It now has an app factory, focused routers, middleware modules, browser services, a shared action pipeline, and MCP tool packs. The product direction is sharper too: governed browser agents. Auto Browser gives AI agents a real Playwright browser with human takeover, reusable auth profiles, approval gates, audit trails, operator visibility, and MCP-first tool exposure. v1.1.0 adds the foundation for governed skill induction: browser traces can become staged skill candidates with provenance, verifier context, and review boundaries. Drift monitoring can re-check those skills and mark degraded ones when the web changes. Also shipped: MCP resources/subscriptions tool annotations per-tool metrics response metadata safer route error handling JSON-safe tool descriptor caching deterministic deep health checks fail-closed startup wiring Auto Browser is open-source, local-first browser infrastructure for agents that need real browser control without giving up ownership of sessions, auth, and workflow governance. github.com/LvcidPsyche/au…

@mattjay I just implemented a package and dependency ban unless I approve. That’s one of the only things I have my approvals on for

Everyone using Claude code and/or Codex - how are you enforcing them to not pull in new/potentially malicious packages from npm or PyPi?

@gadievron @github I was just looking at the docs on this from another post! Will check it out

@TheIdealGinger @github We opened up AgentMesh for free. It’s like a VirusTotal but got extensions, skills, etc. (agentmesh.knostic.ai). You can also check out how we secure coding agents and their supply chain, on the IDE, if you like. Free up to 5 licenses. knostic.ai

1/ We are sharing additional details regarding our investigation into unauthorized access to GitHub's internal repositories. Yesterday we detected and contained a compromise of an employee device involving a poisoned VS Code extension. We removed the malicious extension version, isolated the endpoint, and began incident response immediately.

solana:VNo7EjR3XVzvbjUgQrFAXNwSms34fHwHBt1Xoaopump really getting ready for the run to start meme szn and you’re not holding enough

@ChowdhuryNeil Same thought from yesterday. That’s anthropics best way back in my opinion but 5.6 goblin lord elite is right around the corner too

we need to keep saying GPT-5.5 is better than Opus 4.7 so we can collectively ragebait Anthropic into releasing Mythos

@jun_song Same. Those two are dream setups. Maybe DGX studio instead of M5. But both dreamy

- 2x RTX Pro 6000 - Mac Studio M5 Ultra 512GB 개인으로써 두개중 하나만 있다면, AGI에 도달할때까지 컴퓨팅 문제는 없을겁니다.

@K4y1s Keep your head up king, while in between jobs go and build something that you have been holding hostage in your creativity space and drive self-growth. It’s only a matter of time before someone comes knocking.

Unhappy to announce that I was laid off after just one month, due to a reorg that dissolved TON's DevRel team 🥲 I spend most of that time researching AI automation for docs processes 🤖 If your docs can't keep up with engineering, I can help 👀

@sama @gdb @thsottiaux new model release to celebrate the big court win??

@br0ckObama @baglord69 I stg

@baglord69 Maybe take the loss and go all in on chudhouse at 10k

FUCK man, this is actually breaking me. I went all in because I truly believed my read was right. Now I’m watching years of grinding, stress, sleepless nights and everything I built get wiped out in real time. If $BTC loses 75k, I’m probably finished. Yesterday I felt untouchable. Today I can barely look away from the chart. I keep refreshing like something is going to save me, but the truth is I let one trade get big enough to decide my life. Knowing I did this to myself because I got greedy and started thinking I couldn’t lose... that’s what hurts most.

@hetmehtaa This is the only way. Secured channels ftw

If you're looking for a cracked security engineer for your company like me, I am open for opportunities. PS: I will disable all inbound and outbound traffic in your firewall to make most secure infra

my company got breached the attacker had access for 11 days on day 3 he emailed our IT helpdesk complained that the VPN was slow our helpdesk reset his password upgraded his access tier to fix the "connectivity issue" and closed the ticket as resolved CSAT score: 5 stars we found this in the logs during forensics the attacker had rated our IT support excellent

@evilsocket @Manitcor On that note, I actually wrote a rule for Claude to do a sycophancy check every 5 user messages. Helps ground and recalibrate and you add in recursive loops and self healing. Costs a little bit but worth it.

@Manitcor When is ok to stop, exactly? This creates a recursive mechanism that depending how it is handled, can add even more noise to the context.

- Claude Code (opus@max effort) writes feature X. - /security-review (opus@max effort) finds no issues in X. - Claude Code (opus@max effort), no initial context but my simple prompt, finds an authentication bypass. How does this make any sense?

@Authoritym54 @requestprice @TriCast_ Auto-browser is completely free my friend! Stay tuned for my first paid product release coming soon. I will have a multi week beta testing phase where I will give free credits to selected individuals to test and give feedback.

@TheIdealGinger @requestprice @TriCast_ has anyone paid for the product yet? even if you don't have a website

If you’re a founder, let’s connect.

Riding a donkey to find a horse

@thsottiaux I chewed through my weekly in 36 hrs so this is perfect timing

Codex usage limits have now been reset across all paid plans. Enjoy the weekend!

@sflorimm Lmao ITS A JOKE!! 😂

@sflorimm Sup cunt

Talk to me like ChatGPT.

It’s almost time

If I wanted to dunk on yall I would have done it at the top. SMH idiots

@thsottiaux Noticed a bit of drift yesterday and had to restart my goals after fixing. Didn’t think it would be product-wide. Will wait for good news @thsottiaux

Codex team is aware of reports of GPT-5.5 performing worse for some users and investigating. We don't have anything conclusive yet and systems are healthy but we will share updates as we go.