Scribe

240 posts

Scribe banner
Scribe

Scribe

@LearnWithScribe

AI-powered side hustles to land your first $1K client in 30 days. From manual outreach to automated systems. No code needed

Sumali Ocak 2021
420 Sinusundan20 Mga Tagasunod
Naka-pin na Tweet
Scribe
Scribe@LearnWithScribe·
Deal 🤝 Follow for follow. If we move as a team, we can all earn on Twitter. PS: I also create strong content on AI and automation.
Scribe tweet media
English
0
0
0
66
Scribe
Scribe@LearnWithScribe·
@7a7zz It was barely usable yesterday
English
1
0
1
12
7A7z
7A7z@7a7zz·
wow GLM 5.1 is slow on opencode go to be fair , other models arnt this slow so I think this is just cuz of heavy traffic
English
1
0
1
177
Scribe
Scribe@LearnWithScribe·
@opencode When the support for wsl ? I didn't find it in the documentation
English
0
0
0
13
Marko Denic
Marko Denic@denicmarko·
This is my website. Guess the stack!
Marko Denic tweet media
English
708
17
1.6K
365.9K
Scribe
Scribe@LearnWithScribe·
@0xSero So good that medium reasoning is enough for almost of tasks
English
0
0
1
476
0xSero
0xSero@0xSero·
GPT-5.3-Codex is still the best coding agent, no doubt about it. GPT-5.4 is better at computer use, but doesn't match the sheer autistic power Codex holds.
0xSero tweet media
English
63
15
898
80.3K
Scribe
Scribe@LearnWithScribe·
@0xSero @0xSero Can I use M2.7 for coding task , glm is actually just garbage and opencode rate limit is too low. How was your feelings ?
English
0
0
0
72
Scribe
Scribe@LearnWithScribe·
Miss x 2 boost codex so hard
English
0
0
0
5
Scribe
Scribe@LearnWithScribe·
@Prince_Canuma @Kurtulmehtap Sad because industry is moving toward more moe than just dense models, but I think , it can useful for increasing the expert size
English
0
0
0
16
Prince Canuma
Prince Canuma@Prince_Canuma·
Guess they called it "Turbo" for a reason 👀 Model: Gemma-4-26B-A4B-it Precision: BF16 Device: M3 Max 96GB
Prince Canuma tweet media
English
12
12
214
13.6K
Scribe
Scribe@LearnWithScribe·
@DailyDoseOfDS_ We need more metrics about accuracy lost in retrieval step
English
0
0
0
93
Scribe
Scribe@LearnWithScribe·
@Prince_Canuma Why peak Mel is slightly the same as baseline , the ram usage should be lower no ?
English
1
0
0
200
Supersocks
Supersocks@iamsupersocks·
@Amir_Intel tu vas tous les fusiller là mais t'as raison. La plupart regardent même pas les sources, la date, c'est affolant, ça m'agace
Français
3
0
9
149
Amir_Intel
Amir_Intel@Amir_Intel·
"OpenAI vient de publier la première étude exhaustive" Date en gros dans le rapport : 15/09/2025
Silicon Carne@siliconcarnesf

Suis resté sur le cul... OpenAI vient de publier la première étude exhaustive sur la manière dont 700 millions de personnes utilisent réellement ChatGPT. Les résultats remettent en cause toutes les hypothèses concernant l'adoption de l'IA. On va décortiquer tout çà semaine prochaine dans Silicon Carne... c'est super intéressant 🌶️ Voici tout ce que vous devez savoir en 3 minutes :

Français
1
0
2
464
Scribe
Scribe@LearnWithScribe·
Unpopular opinion : one shot capability of gpt 5.3 codex high > gpt 5.4 high
English
1
0
1
29
Scribe
Scribe@LearnWithScribe·
@bolaabanjo It can but you have to be way too specific so it’s frustrating
English
0
0
0
11
Bola Banjo
Bola Banjo@bolaabanjo·
Codex sucks at frontend lmao.
English
89
6
170
14K
Scribe
Scribe@LearnWithScribe·
@theo 😂 I noticed that earlier
English
0
0
1
26
Theo - t3.gg
Theo - t3.gg@theo·
Does Google actually hide all the cheaper plan options when setting up a new Google workspace? There are 3 cheaper options and I'm not allowed to see or select any of them.
Theo - t3.gg tweet media
English
167
10
1.3K
138.1K
Scribe
Scribe@LearnWithScribe·
Qwen 3.6 is a really good model with a strong design taste. Not quite at Gemini’s level but close and different
English
0
0
1
33
Scribe
Scribe@LearnWithScribe·
@thekitze It really likes to put everything in a box
English
0
0
0
456

Tuklasin

@7a7zz @opencode @Zai_org @denicmarko @0xSero @Prince_Canuma @Kurtulmehtap @DailyDoseOfDS_