Sidakpreet Singh
44 posts
Sidakpreet Singh
@impreetentious
Product Strategy @HCLSoftware // MBA @IIM_I
New Delhi, India Katılım Ocak 2026
26 Takip Edilen2 Takipçiler
No spoilers here, but anyone doing WORDLE today…. I mean….
WTF???
Is that even a word???
😳🤨
English
@wholyv I use AI for it (duh). Use the lower end models like Haiku 4.5 or GPT 5.4 mini to just analyse the files and split your required work to be done in phases. Making mistakes and/or correcting the plan with multiple followups is much less token costing when you use a low end model.
English
@impreetentious how do you divide your one main goal to different phases that don’t require context from other phases?
English
@uday_devops Depends on how big an LLM you are planning to run. And why chrome, there are much less ram-hungry and better browsers out there..
English
@wholyv Yes, been doing this for the past 3-4 months now. Depends case to case. Some tasks can be split into non-dependent phases. Some have to be done sequentially.
English
@impreetentious so you divide the phases in such a way that each phase is completely separate from another phase? the work done in one phase won’t clash with the work done in the second phase?
English
@V1rendra_ GPT OSS 20B (crazy good compared to models in its class, punches above its weight)
English
@wholyv That is where the phased-plan comes in. I try to finish a phase or a set of tasks in one-go. I only get up once I've completed a phase, so that the new phase can be continued in another chat with minimal context required. Works for both Claude Code and Cowork (for me)
English
@impreetentious how do you handle with Cache hit if you are resuming work after some time?
English
Hey @X 👋
Connect me with people who are into:
• Tech 💻
• Coding
• Vibe coding
• Full-stack development
• Software Engineering
• AI/ML
• Building SaaS & Micro SaaS
• DSA
Always looking to learn, share ideas, and meet builders.
Let's #connect! 🤝
#BuildInPublic #SaaS #AI #Coding #TechTwitter
English
@thsottiaux Thanks a lott @thsottiaux @abraibrai
I finally got my first reset, less go. Time to sacrifice my sleep yet again😁😁
English
I love Codex because it was my first app that actually made me fall in love with everything about this world. I've been with ChatGPT since 4o times.
My Github profile is at ItsMonarch04. Each of my 9 repos was incepted amd wokred on by Codex. Can't give any more proof than that.
English
@thsottiaux Is this again only for the old users? or will the newer users finally get a chance too? @thsottiaux @abraibrai
English
Hello. We have reached 8M active users across Codex and ChatGPT Work.
We are once again resetting the usage limits for all. And we continue to not have the 5h rate limit as well, allowing everyone to explore the boundaries of GPT-5.6 Sol and discover how ambitious you can be.
See you tomorrow for more updates on our growth!
Sam Altman@sama
5.6 sol growth is insane. the inference team has done heroic work to be able to support demand. we are going to move mountains to continue to scale, but it is possible there are some hiccups soon.
English
@sama Yet no weekly resets for the relatively new subscribers after publicly announcing this. You are no different than Anthropic
English
GPT-5.6 sol is half the price and ~twice as token efficient as fable in many cases for accomplishing the same task.
happy to deliver at one-quarter of the price.
English
English
@impreetentious @OpenAI That's Nonsense, they shouldn't advertise reseting everyone's "Usage limits"
English
Every time @OpenAI's Codex has a so-called "usage reset," a lot of people, including me, don't actually get it.
Is this intentional, or is it meant as a marketing strategy to encourage more people to sign up?
I don't really understand.
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
@kiruweb @adonis_singh @thsottiaux @abraibrai Confirmed by them just half an hour ago. I was also surprised and now angry that we were blueballed like this
English
@kiruweb @adonis_singh then we won't get one. Apparently there was a cutoff time for accounts which were gonna get the reset. And open ai folks @thsottiaux @abraibrai cleverly chose not to tell us about this.
English
@kiruweb @adonis_singh Is your account new? like bought in the last 24 hours or so?
English