redmonkey

[Maziyar PANAHI @MaziyarPanahi]

6,000,000+ PyPI downloads in under a year.

OpenMed 1.5.5 ships today: batch PII, on-device redaction in 9 languages, plus our first outside contributor merged.

The models and SDK are open-source, Apache 2.0.

Star the repo and start building!

[redmonkey @redmonkeyAI]

@OfficialLoganK Go Gemini, go. Release the Kraken

[redmonkey @redmonkeyAI]

@sflorimm 3x more expensive than python so your token running out fast

[redmonkey @redmonkeyAI]

@shengzheyao Latex rendering is awesome

[redmonkey @redmonkeyAI]

MiniMax M3 Free created sabotage test when reviewing claude's code - tough reviewer
'Lock-in is INSUFFICIENT — sabotage test proves it
I ran the same sabotage I used on the A66 review: replaced the paper-order r_corr in ref_a81_cs with the buggy order, then re-ran the harness.'

[redmonkey @redmonkeyAI]

Was using Qwen 3.7 MAX for review, and it caught quite lot of Claude bugs. But then accidently switched to Minimax M3, and it made Claude cry... How can it be free? @opencode

[Suni @suni_code]

https://t.co/5GPORA9S5h

[redmonkey @redmonkeyAI]

Hi @opencode I got this 'Model nemotron-3-ultra-free is not supported'

[redmonkey @redmonkeyAI]

@thdxr this would be nice too in opencode

[Factory @FactoryAI]

Introducing model routing to Factory.

Factory Router picks the right model for every task, automatically.

Maintain frontier performance while cutting costs by 25%.

[redmonkey @redmonkeyAI]

Looks like they improve Antigravity CLI quite lot. Look at those formulas in terminal

[redmonkey @redmonkeyAI]

Not sure what Caude fixed yesterday, but the session lasts much longer now -tried to burn tokens all night/ morning but couldnt finish it

[Google Antigravity @antigravity]

We’re transforming Google Antigravity into a scientific workbench. The new Science Skills bundle allows researchers to run complex workflows like protein analysis in minutes using specialized Alpha* models and 30+ major scientific databases.

[redmonkey @redmonkeyAI]

Quite impressed how Qwen 3.7 Max is catching Claude 4.7's bugs.

[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: https://t.co/fHRdSV7BwZ
Token Plan: https://t.co/BDCycxepZw
🚀New! MiniMax Code: https://t.co/GvB4YiB6Ul

Weights & Tech Report in ~10 Days

[redmonkey @redmonkeyAI]

Feels like Opus 4.8 gobbles up lot of tokens while with 4.7 i can work with for hrs

[redmonkey @redmonkeyAI]

Msybe will need to try

[Lea Verou, PhD @LeaVerou]

💡Recent insight: gaslighting @claudeai seems to improve code quality >90% of the time.

“You overengineered this, there is a simpler way”
“There is a smaller delta that buys us most of the benefits”
“There is a more elegant way”
“This is not architecturally coherent”

…before I even read its code. 😆

[redmonkey @redmonkeyAI]

@opencode Deepseek v4?

[redmonkey @redmonkeyAI]

@pallavmac Does that mean Opus 4.8 medium cost 2x Opus 4.7?

[redmonkey @redmonkeyAI]

@elder_plinius OMG, you are GOAT

[redmonkey @redmonkeyAI]

Can anyone confirm if Opus 4.8 burns more tokens vs 4.7?