Sabari Haridoss

Software Engineer @Multicoreware | Building personalized intelligence for people & business

[Sabari Haridoss @SabariHDev]

@Cosmosfinite @NousResearch How do you use it tho? like as a daily driver for coding and everything.

I almost never had any task which I'd just hand over and run on a vps

[Sabari Haridoss @SabariHDev]

@davis7 finally someone is mentioning about the Hallucination in opus 4.8.

[Sabari Haridoss @SabariHDev]

@MiniMax_AI now we wait for real benchmark from deepswe

[Sabari Haridoss @SabariHDev]

Claude spawning subagents

[Gusholder Haber Bülteni @gusholderhaber]

Kırkayak doğurdu, ancak yavruları ilk besini olarak annelerini yediler.

[Tyler @rezoundous]

Opus 4.8 is insane guys. It one shotted my session usage limit.

[Sabari Haridoss @SabariHDev]

@zeddotdev @OpenAIDevs after the v1.3.7 update, the zed agent gets stuck on loading. i’m using a chatgpt subscription with the gpt-5.5 low model. could you please look into this, @zeddotdev? any help would be appreciated. thanks.

[Sabari Haridoss @SabariHDev]

nah 😭

[Sabari Haridoss @SabariHDev]

@prnshtwt i kinda feel something id wrong with your account or could be the type of post you're making.

you should be getting more views, try posting the same viral templates people do

[Elon Musk @elonmusk]

@beffjezos Our recently completed Grok V9 1.5T run is looking great and that is before Cursor data is added in supplemental training

[Sabari Haridoss @SabariHDev]

Huge

[Zed @zeddotdev]

You can now use your ChatGPT subscription in the Zed agent, with the same usage and rate limits you benefit from in Codex directly. We're grateful that @openaidevs continues to support subscription-based access for third-party tools, even as others move toward usage-based billing.

[Sabari Haridoss @SabariHDev]

@Anaya_sharma876 Battery life sucks

[Sabari Haridoss @SabariHDev]

@prnshtwt Is it good?

[Sabari Haridoss @SabariHDev]

@prnshtwt @damnGruz 😭

[Sabari Haridoss @SabariHDev]

@prnshtwt at this point we might as well use whatsapp bro 🚶

[Sabari Haridoss @SabariHDev]

@prnshtwt Oh nice

[CJ Zafir @cjzafir]

How Codex 5.5 medium is beating Codex 5.5 extra high?

Add this rule in Agents. md:

"Don’t fight errors! Whenever you encounter the same error twice, research the web and find 3-5 possible ways to fix it. Then choose the most efficient solution and implement it."

This prompt release stress to think hard and run into a loop of bad decisions but find new perspectives that actually worked.

I ran this experiment on complex tasks (model training, running evals, converting best checkpoints to GGUF etc) and I encountered NO ERROR.

Best part: minimal 5 hr and weekly limit usage.

I am using Codex 5.5 medium (fast) and it feels instant.

But here's the catch: Your session plan has to be designed by Codex 5.5 extra high! Use the medium variant, only to execute the plan.

This way you're not using Codex 5.5 medium's loose thinking but using its fast speed to execute the task list properly.

Try it yourself.

[Sabari Haridoss @SabariHDev]

@prnshtwt start a memepage man, keep this account for grocery list.

[Sabari Haridoss @SabariHDev]

@droidbuilds you haven't used discord app in linux yet. it worse than anything