๐•ฑ๐–”๐–—๐•ท๐–”๐–”๐–•

25.6K posts

๐•ฑ๐–”๐–—๐•ท๐–”๐–”๐–• banner
๐•ฑ๐–”๐–—๐•ท๐–”๐–”๐–•

๐•ฑ๐–”๐–—๐•ท๐–”๐–”๐–•

@forloopcodes

/ rs kt ts / โ€‹ๆœ‰็ฝช / apps agents mcps / โ€‹ๆฒกๅŽ / xdist, context+ (1.4k) / โ€‹ๆญปๅˆ‘ /

ๅ‚ๅŠ ๆ—ฅ Eylรผl 2024
1.8K ใƒ•ใ‚ฉใƒญใƒผไธญ8.6K ใƒ•ใ‚ฉใƒญใƒฏใƒผ
Mehul Mohan
Mehul Mohan@mehulmptยท
You cannot possibly convince me that Codex is any better than Opus. At their worst, both need very high supervision for complex codebases. They just get so much wrong. Skill issue with the other AI when anyone says otherwise
Mehul Mohan tweet media
English
44
2
108
9.5K
Lahn.inj
Lahn.inj@Lahnshenยท
If you're in your early 20s then would you lifemaxx or moneymaxx?
English
6
0
8
210
aditya
aditya@adxtyahqยท
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.
aditya tweet media
English
24
14
316
20.5K
Temidaradev
Temidaradev@temidaradevยท
Kรผp
Temidaradev tweet media
7
0
38
6.8K
BridgeMind
BridgeMind@bridgemindaiยท
@forloopcodes I am speaking truth. Kimi K2.5 is not a good model in the first place.
English
3
0
5
733
BridgeMind
BridgeMind@bridgemindaiยท
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.
BridgeMind tweet media
English
46
4
149
20.3K
kartik
kartik@notKartikkยท
@forloopcodes it also started overdoing things ๐Ÿ˜ญ
English
1
0
1
47
๐•ฑ๐–”๐–—๐•ท๐–”๐–”๐–• ใŒใƒชใƒ„ใ‚คใƒผใƒˆ
Six แ›—illion Dollar Extremist
Six แ›—illion Dollar Extremist@anindividualgemยท
is this accurate?
Six แ›—illion Dollar Extremist tweet media
English
36
213
3.6K
46.5K
Sherwin Wu
Sherwin Wu@sherwinwuยท
Set Codex to this and don't ever look back
Sherwin Wu tweet media
English
247
64
2.2K
258.7K
๐•ฑ๐–”๐–—๐•ท๐–”๐–”๐–• ใŒใƒชใƒ„ใ‚คใƒผใƒˆ
Dmitriy Kovalenko
Dmitriy Kovalenko@neogoose_btwยท
lol no I'm sorry but your file search is sฬถhฬถiฬถtฬถ not optimal consider fff you can literally just use it there is a C lib, Rust crate, and even nodejs lib
Raycast@raycast

@CodeByNZ we fixed it

English
19
7
439
86.7K
Kimi.ai
Kimi.ai@Kimi_Moonshotยท
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.
English
480
1.3K
19.2K
3M
avrl โ˜˜
avrl โ˜˜@avrldotdevยท
If you have $20, which AI plan are you buying? 1. Claude Pro 2. ChatGPT Go 3. OpenCode Go (Feedback needed)
English
72
2
48
4.9K