parth.

2.8K posts

parth. banner
parth.

parth.

@TotallyNotParth

kings gambit | GMT +5:30

Entrou em Ağustos 2021
256 Seguindo132 Seguidores
Terp
Terp@OnlyTerp·
You couldn't pick a different model for your workers before I fixed that for you, Feel free to have a smart model orchestrate while a cheaper model/Local model does all the work Already live in the github 🫡
Terp tweet media
Terp@OnlyTerp

ULTRACODE-SHIM IS NOW LIVE 🔥 You can now run ANY model in UltraCode I built a github repo to make this really easy for you, Just send your agent there and let him COOK You deserve the flexibility to use LOCAL models & cost efficient models. So I made that happen for you 🫶

English
6
2
42
2.3K
lost in latency
lost in latency@lostinlatencyX·
MiniMax M3’s frontend capabilities are pretty nice very strong model for the price. not lazy, thinks through the task (thinks a lot), and doesn’t just take the shortest path M3 can reason between multiple design choices better than i expected with the right skills around it, m3 seems strong model will test backend tasks next.
MiniMax (official)@MiniMax_AI

Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities - Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas - MiniMax Sparse Attention scales context to 1M - Natively Multimodal from Step Zero API: platform.minimax.io Token Plan: platform.minimax.io/subscribe/toke… 🚀New! MiniMax Code: code.minimax.io Weights & Tech Report in ~10 Days

English
6
4
33
4.7K
nia
nia@only_shans_·
subhanallah is a fantastic word
English
1
0
3
26
Victor Su-Ortiz
Victor Su-Ortiz@VictorSuOrtiz·
DM me if you want early access to try M3 🚀
MiniMax (official)@MiniMax_AI

Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities - Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas - MiniMax Sparse Attention scales context to 1M - Natively Multimodal from Step Zero API: platform.minimax.io Token Plan: platform.minimax.io/subscribe/toke… 🚀New! MiniMax Code: code.minimax.io Weights & Tech Report in ~10 Days

English
11
0
40
3.5K
GMI Cloud
GMI Cloud@gmi_cloud·
Celebrating @NVIDIAGTC with 20% off every model on GMI 48 hrs, unlimited
GMI Cloud tweet media
English
1
2
2
145
Command Code
Command Code@CommandCodeAI·
Yes $1 Go plan is cool. But more is coming. Noon 12pm Monday, 1st June. Command Code deal drop. This one is gonna be crazy good!!
Command Code tweet media
English
31
9
173
5.1K
Santh
Santh@SanthProject·
I've spent the last 5 months trying out various AI subscriptions, and here is my ranking on how worth it they were for me. 1. kimi vivace plan 2. chatgpt pro 3. Claude Max 4. Google Ultra 20x(note at one point back in december this was the most worth it by far this is my last month) 5. supergrok(im honestly sure this will change soon but grok is just not a good model yet)
English
5
1
16
2K
parth.
parth.@TotallyNotParth·
@MrAhmadAwais giveaway winners announced? gotta see if i won or not!
English
1
0
0
132
Ahmad Awais
Ahmad Awais@MrAhmadAwais·
noon 12pm monday 1st june, command code deal drop.
Ahmad Awais tweet media
English
15
2
64
2.9K
Terp
Terp@OnlyTerp·
ULTRACODE-SHIM IS NOW LIVE 🔥 You can now run ANY model in UltraCode I built a github repo to make this really easy for you, Just send your agent there and let him COOK You deserve the flexibility to use LOCAL models & cost efficient models. So I made that happen for you 🫶
Terp tweet media
Terp@OnlyTerp

Composer 2.5 in ultracode is INSANE 🤯

English
22
25
323
87.5K
Li Yin
Li Yin@panda_liyin·
a coding agent will not be truly autonomous w/o browser use. last night, @adalagent in browser use mode autonomously fixed a long-backlogged issue, all while i was watching a movie with my friend @AnnieLiao_2000 . its like the great engineer i always wished i had.
Li Yin tweet media
English
1
1
5
301
Helvetica.
Helvetica.@kainsart_·
This is genuinely so fucking good bro
Helvetica. tweet media
English
4
0
35
748
parth. retweetou
𝖕𝖗𝖆𝖙𝖍
𝖕𝖗𝖆𝖙𝖍@prathamdby·
People of pi.dev and cursor.com PR Agent update since May 25 🧵 A lot landed: local git workspaces, auto PR descriptions, a new quality review lens, tougher reviews, and a big reliability pass. github.com/prathamdby/pr-…
𝖕𝖗𝖆𝖙𝖍@prathamdby

People of pi.dev and cursor.com PR Agent update since May 19 🧵 Big week, /ask, durable workers, Cursor SDK support, and a bunch of review UX changes. Link to the repo: github.com/prathamdby/pr-… Quick rundown:

English
1
1
6
268

Descobrir

@OnlyTerp @lostinlatencyX @MrAhmadAwais @only_shans_ @dee_hw @VictorSuOrtiz @NVIDIAGTC @gmi_cloud