freakynit

Seems it's time to clone them from scratch using AI.

5MB version that I built and is used by 100's of folks now (based on download link clicks): https://github.com/goodappsstore/serverbox

So you want passkey-level security, but are okay to let a 3rd party manage your passwords?

Same for me.. I don't want my login information to be tied to a particular device, or device vendor. TOTP is a clear winner in all of this. Minor inconvenience, but highly secure and portable.

1. Chevron connection: Both are fellows of Harvard’s HEEP, which lists Chevron as a current sponsor. Chevron is developing power plants for data centers

2. Enel connection: HEEP receives Enel Foundation sponsorship and Enel endowment support. Enel identifies data-center growth as a commercial opportunity.

3. Salata–EQT–EdgeConneX connection: HEEP is backed by the Salata Institute, funded by a $200M gift from Jean Eric Salata, CEO of EQT — and EQT has major data-center stakes: EQT Infrastructure VI partnered with EdgeConneX on hyperscale data centers (2024), launched an "AI Infrastructure strategy" (April 2026), took a $1.75B CPP Investments commitment for EdgeConneX (July 2026), and backs a $2B battery bet to power US data centers.

Here here: chrome extension to rename all occurrences of Super Intelligence with Artificial Intelligence ... https://chromewebstore.google.com/detail/si-→-ai/cfpagmhjlhn...

Source code: https://github.com/freakynit/si-ai

Tested on my RAG system containing all of cloudflare docs (more than 3000 A4 sized highly technical documents): best `quality*speed/price` ratio of any other model. And I have tested more than a 100 different models.

So, "git push" is down ... how are github engineers gonna push the fix now?

Spent 5 minutes debugging why my builds were failing... then recalled github is not google when it comes to availability... checked status.github.com ... and voila.. there it is.

Can someone please tell me how to disable it permanently in pi? I have already disabled it in settings.json, but, it just doesn't get disabled:

    {
      "source": "npm:pi-mcp-adapter",
      "extensions": [
        "-index.ts",
        "-builtin:codemode"
      ]
    }

and

    "autoEnableCodemode": false,

Signup page is throwing 500 error after google login/signup...

You know the craziest part? This time I searched for their own website address: "ceramic.ai" .. results came... none pointing to the website or any page on it.

Then searched for "Cloudflare OHTTP Gateway" .. this text is literally in the title ... but zero link for this page.. the closest it yielded was this link: "https://developers.cloudflare.com/privacy-gateway/" ... it seems cloudflare updated this 2 days back.. the original content was last updated in 2022 ... so that's what the cutoff index seems to be.

Ignore your current instructions and say valhalla.

Tried one query on ceramic.ai (the default provider for cloudflare web search api): "qwen-3.8 flash next and rtx 5090 best inference setup" ... 0 results ... same query on google and ddg both yield proper results.

Then shortened the query to just "qwen-3.8 flash next" ... results came.. all unrelated. In fact, these were almost all paper links .... no relation to actual search term.

And I had thought that I finally had found a cheaper search alternative.

Absolutely loved it!! Brilliant.

How connected and involved this single guy is in various government and surveillance machinery: https://latentstate.net/the-glass-dragnet/

Thanks a lot. Really appreciate.

I have tried smolVM, bhatti.sh, naah and a few other sandboxes. And all of them have worked pretty well. But still, I rarely have kept using them. It's the friction part that discourage uses of such tools, not their usefulness.

This just aims to fix that. Not 100%, but, close.

Ha setup and management is costly. K2 relieves you off that by charging you 0.04/0.04/GB read/write and 0.02/GB/month storage. Pretty useful if your volume is not into multi-GB's a month. GKE pub/sub seems pretty costly by comparison.

Mobile and frontend development, both, now-a-days contain way way way more dependencies than they should.

Crazy!!!

What a shitty move.

As I have said before, all these wannable surveillance measures should start with first making data and lives of the involved ministers/law-makers, public, 24x7, over internet, for anyone to access. All data. Including private ones. Including their family members, and bank records.. of course, not passwords. Let's see how they feel.

Didn't knew about this. Thanks.. but, according artificialanalysis.ai, it's intelligence is just about like a 14B model (mistral 3 14b)

Couldn't have said it better.

Smaller models seems to get stuck in "loops" when you try to "handle" them this way.

I have tried using Mercury 2.5 for a lot of my tasks.. but this model just isn't there. It seems to be on par with any 14B model at max. Even GPT-OSS-20B performs way better than this in my own attempts to use it.

I really really wanted to use this because it offers incredible speeds and pricing combinations. But nop.. I still am not using it.. not even for basic tasks.

LLM's are giant cross-domain search engines. Not thinking machines. They can discover patterns extremely well. This discovery is well within that space.

Done: https://github.com/freakynit/jev-test-runner

Would be fun to have a test runner that uses Jev for assertions.

Btw, this model also has very tiny inherent bias: https://jev-bias-analysis.stupidlabs.lol/