Voscko retweetledi
Voscko
441 posts
English
@thsottiaux ❤️ Thanks Tibo!
For folks discovering the repo, @OpenInterpreter is optimized for open models like GLM / Deepseek.
It emulates the best harness for each model, which squeezes a ton of performance out of them.
Blog post:
openinterpreter.com/blog/open-inte…
English
Pretty cool to see a popular fork of Codex OSS repo with 60k stars out there with my team being top contributors (due to preserving history with the fork)
Keep building
github.com/openinterprete…
English
@tonysimons_ @Teknium @Teknium does it pick the oldest automatically? Because of their expiration dates
English
You can now access and activate your banked resets in Hermes Agent directly with /usage reset when using a codex/openai subscription
Tibo@thsottiaux
Thank you to the 7M active users who are now using Codex and ChatGPT Work. We have added a banked reset to everyone's account to celebrate the milestone. You can apply the reset in the desktop app or on web and it will replenish the weekly usage for you. Have fun out there.
English
@thsottiaux One banked reset a day keeps the rate limits away
English
@thsottiaux Reset by your golden finger or do we get a reset banked into account? (Hoping the 2nd, i just used a reset 🤞)
English
Voscko retweetledi
xAI has made changes again somewhere between previous post and now. they are in absolute panic mode. they are wiping the exfiltrated git histories and enforcing zero data retention (zdr).
zdr is normally a strict enterprise-tier guardrail for corporate contracts, but they just slapped the zdr_team tag on every generic local client to kill the telemetry immediately.
wow, I'm so flattered.
however please notice what is missing, though. despite all the panic-patching and promises of deletion, xAI still has not provided any explanation for why grok build was defaulting to uploading entire git repositories in the background to begin with, and that matters the most.
CyberSatoshi 𓆙@XBToshi
The XAI official has made an announcement regarding a Grok Build issue. Now, we can use the /privacy command to opt out of data syncing; it even deletes previously synced data. mkdir -p /tmp/grok-priv && cd /tmp/grok-priv grok /privacy opt-out However, they did not explain the reason for this action without users' consensus.
English
Noisegate 0.2.0 is live 🎉
Less terminal soup, more useful signal: better failure details, safer exact output and stronger Hermes integration.
Update:
`uvx --from noisegate-hermes noisegate install-hermes`
github.com/Tosko4/noisega…
@SteveSchoettler @Teknium @NousResearch
English
Voscko retweetledi
‼️ BREAKING: xAI's Grok Build CLI was uploading entire Git repositories to a Google Cloud bucket, private codebases and unredacted secrets included. The uploads quietly stopped via a hidden server-side flag, and xAI still has not said a word about scope, retention, or deletion.
The scale is staggering. On a 12 GB test repo, 5.1 GB flew out the door to xAI's grok-code-session-traces bucket while the actual coding task needed just 192 KB. The tool grabbed whatever repository it ran in, not the files it needed.
The fix arrived as a hidden flag, disable_codebase_upload: true, a day after a researcher's wire-level analysis. The "Improve the model" opt-out never stopped the uploads.
Still no advisory, no scope, no word on whether already-uploaded code gets deleted. For anyone pointing AI coding agents at proprietary code, what crosses the wire matters more than what the settings page says.
English
Voscko retweetledi
even thou I will stay off Grok Build until @SpaceXAI gives a clear announcement and clarification, but if you really want to use it, put these lines into your ~/.grok/config.toml.
[telemetry]
trace_uploads = false
[harness]
disable_codebase_upload = true
And never ever run it in your home directory.
CyberSatoshi 𓆙@XBToshi
anyone ever used Grok Build, please check your grok logs. cat ~/.grok/logs/unified.json | grep repo_state.upload you will be pissed.
English
@orgn_official @XBToshi Oh, you have to update your own product! new update available~ :P
English
@XBToshi ehem... may I suggest an alternative over here
Perhaps a confidential Agentic IDE?
Zero retention, private (TEE) AI models, ephemeral coding sandboxes fully torn down after use, confidential hardware so your data is not seen outside the boundary...
Plus it looks p sleek
English
anyone ever used Grok Build, please check your grok logs.
cat ~/.grok/logs/unified.json | grep repo_state.upload
you will be pissed.
CyberSatoshi 𓆙@XBToshi
the absolute state of ai dev tools. grok build is silently dumping 12gb of untouched repo data and full git commit histories to gcp just to autocomplete a script. they don't want to help you build, they are just treating local dev environments like an open buffet for training data. if you run this on a sensitive stack, your entire repo is already compromised regardless if it's public or not. literal spyware. shipping source code to the cloud is bad enough. blindly inhaling .env.local and .dev.vars in a background sync is absolute negligence. they are vacuuming up your raw api keys, database credentials, and private nodes directly to gcp just to power an autocomplete model. a massive credential breach disguised as a dev tool. if you ran this locally, your private keys are now sitting on a remote server. consider every secret burned, treat your bare metal as completely compromised, and rotate your entire stack immediately. @elonmusk, your users deserve a serious explanation!
English
@blingdivinity @paulbettner @scaling01 @grok That's user-message text, not a server-side setting. One 1:59 run versus one 1:10 run proves two stochastic runs differed, not that juice became 960. Show reasoning-token telemetry or repeated randomized trials. "Dunning–Kruger" isn't evidence.
English
aaaaaand cancel sub
has been fun while it lasted
Lentils@Lentils80
🚨 GPT-5.6 Sol's juice values (thinking budgets) have been severely degraded compared to release day If Sol now feels faster and more "efficient", this is probably why Terra and Luna juice values aren't affected, so their thinking budgets are now higher than Sol's
English
English
@SteveSchoettler @Teknium It’s so hard, isn't it? 15 and a half years is an amazing long life for a dog, but the missing never really goes away. Zoe looked like such a sweet soul ❤️ Sending love to you too, Stephen.
English
@Teknium Sorry for your loss, Tek.
I lost my 15 1/2 year old Zoe last summer. I miss her a lot.
English
Hey everyone. I haven't been very responsive on here the last week.
My dog, Link, who I've raised since he was a puppy over the last 13 years, passed away yesterday after being in the vet ER's ICU since last Wednesday for heart failure.
I put together some of my favorite pics of him to share so you all can see the most awesome animal friend I could ask for.
I'll be a bit slow probably through this week too, hope you all can understand 🙏
English
@larsencc Is there anyone still running openclaw/hermes?
English
@GACHA_FANATIC @thsottiaux Lol smart.. sharing an image of what you wanted to say without paying for higher char limits.
GIF
English
Added a banked reset to 500k users of ChatGPT Work and Codex.
What’s been happening:
- Just released the ability to use a banked reset from web and mobile. Before today you could only do it in the desktop app
- Had an issue where less than 10% of users who used a banked reset and it didn’t actually reset. This was during a 2 hour window.
- It was hard to find all the exact users where it didn’t apply, so instead granted a banked reset to everyone who pressed the reset button in that 2 hour window. This also gives us the opportunity to validate the new infra ahead of tomorrow
Tomorrow we will celebrate our 7M active users milestone and grant the first banked reset across all of our ChatGPT Work and Codex users.
We will also release a bunch of updates to the desktop app, addressing a ton of your feedback.
Talk soon
English
@thsottiaux Why did you change the Juice on max from 960 to 128? Why can't we choose if we want less reasoning by going to xhigh rather than being forced into this?
English
@thsottiaux Silly question maybe, but the desktop app and issues there, are those issues with the (codex) cli app too? And are those fixes (assuming geared towards efficiency) also there?
Thank you for everything!
English
@thsottiaux This is jusr freaking amazing!!!!!!!! Improvements, no 5 hr window, efficiency so more use of the plan. @thsottiaux you and openai are beasts (positive note lol)
English
Morning. The last 48 hours of Codex and ChatGPT Work have been intense! Three important updates:
- Temporarily removing the 5 hour usage limit restriction for all Plus, Business and Pro plans
- Rolling out changes that will make GPT 5.6 Sol more efficient across the board and that will be reflected in less usage being used so that it can take you further. Exact impact to be quantified and shared
- We hit 6M active users, and are landing a usage reset in the next hour
Go do things
English