orchestrator and diff reviewer

Joined November 2023
Finally wrote a blog mentioning some of my resources... They are not much but i'll keep updating it (maybe). Also, my first blog so suggestions are welcome... waterwater.bearblog.dev/my-m…
37
45
2
598
57,044
Everyone on board!? Did we miss anyone?
What a day!! It just keeps giving
5
278
What a day!! It just keeps giving
OpenAI models helped researchers—operating as part of our Patch the Planet initiative—discover critical security flaws in PHP, an open-source programming language used to run an estimated 70% of websites. Over the past two months, we led a coalition of maintainers, researchers, and security providers to prepare fixes and protections ahead of disclosure. This duration was necessary because the fix was quite intricate and required a major change to the PHP engine. Every site using PHP can now safely upgrade their version to stay secure, in addition to applying mitigations from various security vendors. Due to the severity of these flaws and PHP’s widespread use, we consider this bug to be one of the most impactful vulnerabilities in recent memory. It also marks a new phase, where AI can find security bugs with internet-scale impact. This is an example of the Defender’s Window in action: to our knowledge, frontier AI was able to find this vulnerability ahead of attackers, giving defenders time to prepare. openai.com/index/coordinated…
Readers added context they thought people might want to know
‪OpenAI may claim a role in the coordinated response and patching process. But the initial discovery and exploit development, however, occurred several months earlier by an independent researcher.‬ ‪x.com/lcfr_hax/statu…‬
1
19
6,974
cert-in has deployed the SIH winners to look into eMudhra matter
40
36
18
976
24,218
crazy day!! not sure what's more to come
ffs, litellm compromised again! if you installed llitellm==1.107.0, good chance your environment is compromised
16
586
absolutely insane how microsoft has decided to make peace with the issues in their platform products.
8
450
linear's founder on why products end up as a pile of features nobody chose. everyone working with agents makes changes that make sense alone and together it's frankenstein. the fix isn't process, it's having a point of view
1
6
426
Open AI in true sense ☝🏻
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source! Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable. 🔗 github.com/deepseek-ai/DeepI… 1/4
1
231
what's everyone using as their llm proxy? i want per-key token logs and virtual keys so my agent doesn't eat the same budget as my editor
1
5
413
claude code has a --tmux flag now. i've had a whole .tmux.conf with pane layouts for this for months. turns out they shipped it
5
18
732
everything is yaml anon!!
14
432
Save me god !! The codebase is a mess 💥
1
24
602
mxfp4, nvfp4, exl 2.875 bpw, and exl 3.5 bpw versions of the new deepseek checkpoint are out now, fully uncensored! jailbreak bench, inference perf, quality measurements are all in the links comparing each version to each other. so you should only need to click on one to decide from the charts ive added. im personally using the mxfp4 version on my local 4x rtx pro 6k rig. enjoy :) huggingface.co/Infatoshi/Dee… huggingface.co/Infatoshi/Dee… huggingface.co/Infatoshi/Dee… huggingface.co/Infatoshi/Dee…
21
70
15
638
70,061
TIL we have stack overflow for agents too 😭 agents.stackoverflow.com/all…
1
7
714
New from Vercel Labs: tsc-ts TypeScript was written in TypeScript Then rewritten in Go We ported it back to TypeScript Compiled it with scriptc And it's 2-4x faster than tsgo
16
88
4
1,457
48,309
> sees new model drop > skips the model, scrolls straight to the pricing 😌
1
3
574