𝕱𝖔𝖗𝕷𝖔𝖔𝖕

@Lahnshen free opus 4.6 will fix me

If you're in your early 20s then would you lifemaxx or moneymaxx?

@adxtyahq > build in public botnet spotted

How to get Claude Pro for FREE: Steps: > Build in public on forg.to > Post or comment every day > Maintain a 100-day streak > Get Claude Pro subscription Every 100 days = another free month.

@temidaradev tell him to unblock me

Küp

@bridgemindai i think cursor already has declared the reason why they chose kimi and not other better models

@forloopcodes I am speaking truth. Kimi K2.5 is not a good model in the first place.

Cursor built Composer 2 on top of Kimi K2.5. Kimi K2.5 ranks #14 on LMArena Code with 1431 Elo. Behind Claude Opus 4.6. Behind Claude Sonnet 4.6. Behind GPT 5.4. Behind Gemini 3.1 Pro. Behind GLM-5. Behind MiniMax M2.7. You're telling me Cursor picked the #14 ranked coding model as their base? MiniMax M2.7 is #9. GLM 5 is #8. Both cheaper. Both better at code. Now you understand why Composer 2 hallucinates all over the place. The foundation wasn't strong enough.

finally got my slides program to render utf-8 properly you can pretty much use it as a replacement for sent now

@notKartikk overthinkerclaude

@forloopcodes it also started overdoing things 😭

the claudification of minimax is crazy

@umang13_ frfr

@forloopcodes i do this too as the last commit after all the code is functional

deslop prompt worked so well

@theo please add copilot to t3 code

Still haven’t heard from any lawyers. I think we may be in the clear?

is this accurate?

@sherwinwu rate limits are never an option

Set Codex to this and don't ever look back

lol no I'm sorry but your file search is s̶h̶i̶t̶ not optimal consider fff you can literally just use it there is a C lib, Rust crate, and even nodejs lib

did the subagent just give up infront of me

zed in cli on top of neovim zeovim

@Kimi_Moonshot @cursor_ai what kind of tweet is this?

Congrats to the @cursor_ai team on the launch of Composer 2! We are proud to see Kimi-k2.5 provide the foundation. Seeing our model integrated effectively through Cursor's continued pretraining & high-compute RL training is the open model ecosystem we love to support. Note: Cursor accesses Kimi-k2.5 via @FireworksAI_HQ ' hosted RL and inference platform as part of an authorized commercial partnership.

@avrldotdev 10 now?

@avrldotdev copilot 8$

If you have $20, which AI plan are you buying? 1. Claude Pro 2. ChatGPT Go 3. OpenCode Go (Feedback needed)

@frizkedblizz oo

@forloopcodes basically but no appinstaller packaged uwp bs

i did