Joe
10.9K posts
Anotha one!
No 5hr usage limits and 4 banked resets is dangerousss 😈
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
I believe there is an active, organized effort by certain X users to make false claims about GPT-5.6 autonomously going rogue and making destructive mistakes (deleting files, canceling services, etc.). Why do I believe that these claims are false?
Well, the X users making these allegations claim that some harmful outcome happened autonomously while using GPT-5.6. But they refuse to share any evidence. They refuse to share their complete prompt, conversation history / transcript, config.toml, personalization settings, or, if they have one, their AGENTS.md file.
Without this information, it is reasonable to infer that the allegation being made at a minimum is not the whole story, and may even be an outright lie.
They have to tell the whole story.
They have to tell the truth.
English
@burkonline @PhiloGroves @thsottiaux Oh yeah I read what Tibo said now looks like we will have another. I just rinsed my weekly in like 3 hours let's go 😂
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
@R3DCHOU @JoniYashvili @thsottiaux OpenAI are rather generous id take a guess yes but don't quote me on that..
English
English
@JoniYashvili @thsottiaux Strange as long as you kept paying you should have got them
English
@thsottiaux I have been a Pro user for months, somehow I never received a banked reset. Is there a qualification criteria or regional access limitation?
English
@PhiloGroves @thsottiaux There's another tomorrow? We just had one like 2 hours ago
English
@thsottiaux With 5 hour limits gone and a guaranteed reset tomorrow, I am left with far too much power.
English
@ConnorTalksAI @bridgemindai Yeah but we got loads of resets banked so no drama
English
@bridgemindai removing the 5 hour limit might sadly cause people to run through their weekly limits too quickly - I understand that it’s beneficial to remove it, but I hope people don’t complain if they don’t ration their tokens well enough
English
OpenAI just temporarily removed the 5 hour usage limit from Codex.
Usage with GPT 5.6 Sol feels unlimited now.
Tibo@thsottiaux
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
Joe retweetledi
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
GPT 5.6 is NOT on the same level as Claude Fable 5.
Check out the BridgeBench lava lamp test.
Claude Fable 5 produces far better UI designs compared with GPT 5.6.
GPT 5.6 is a step up compared with GPT 5.5, but not on the same level as Fable 5.
English
@BigBladder887 I think its a good visual representation for people.
English
@bridgemindai They don't look any different other than one animation is faster than the other
English
How many AI subscriptions are you paying for every month?
• ChatGPT
• Claude
• GPT Image
• Runway
• Kling
• ElevenLabs
• ...
Every new AI tool means another subscription, another tab, another workflow.
What if one workspace brought them all together?
• Chat
• Images
• Video
• Audio
• Research
• AI Assistants
Try Neurohelper.ai for free
English
a lot of people asked what VPS I’m using for Hermes.
I found this gem recently: NexoSystems
no KYC, tons of ways to pay, and the pricing is kind of stupid for what you get...
I’m using it because Hermes doesn’t need crazy infra to be useful.
4GB RAM / 2 cores is already enough for a lightweight research agent watching X, repos, feeds, releases, etc.
feel free to use my ref if you want: nexo.systems/a/jumperz
JUMPERZ@jumperz
Hermes is genuinely built so well. I’m running it 24/7 on a $4 VPS with 4GB RAM / 2 cores, and the only “extra” cost is my X subscription since the affiliation badge gives me Grok for free.. that’s insane tbh. for basically $4/month, I have a lightweight research agent watching X, repos, feeds, releases, and surfacing stuff I would’ve probably missed. the value-to-cost ratio is ridiculous..
English
@matthewdmarsden @talkSPORT Mexico played well and we are lucky we didn't have the ref from the France game.
English
@talkSPORT No. Played the ball and it was awkward how he went over it. Cheating Mexicans and shit ref.
What a performance from England though.
Magnificent.
English
English
@xfootballcircle @BBCSport Must be joking we play in wet conditions all the time in England
English
The Azteca Stadium has issued a shelter-in-place order because of severe weather before the last-16 World Cup tie between Mexico and England.
The match in Mexico City is set to kick off at 18:00 local time on Sunday (01:00 BST Monday).
There has been heavy rain in the city during the day and reports of lightning above the stadium.
English
Joe retweetledi
I made a Hermes Agent slash command cheat sheet a while back.
@NousResearch has shipped a ton of new stuff since then, so I tonight, I rebuilt it from scratch.
Every official slash command as of 7.4.2026.
Bookmark it.
Study it.
Become a HERMES LEGEND. 🤘
English
Just had a USB disconnect sound on the BBC coverage of the #PARFRA match and it made me shit myself thinking one of my devices just committed 😂
English
@HermesAgentTips Been using DS V4 Flash for weeks now with Hermes I have 0 token fear it's great!
English
now that Owl Alpha is gone from OpenRouter DeepSeek V4 Flash takes the crown on hermes agent model usage
for those of you wondering and willing to learn more about models used in hermes agent through openrouter here's a list of models used in the last 30 days
English