Magnus HedemarkApr 27

New theme for Magnus919 blog. Made with #OpenCode and #KimiK26 for #GoHugo. #BBS inspired.

https://pmpt.us/gdPJr

A Little ANSI BBS Touch

Customizing the Hugo Terminal theme with a 1980s BBS sensibility; an ASCII progress bar, a quieter palette, and a signature look made with OpenCode.

Notes from the Rabbit Hole
PhelipeApr 24
Positivamente soddisfatto dalla combinazione #OpenCode / #OpenCodeGo / #kimik26
Lo sto testando su un repository contenente un backend dotnet e un frontend vue chiedendogli modifiche che vanno a lavorare contemporaneamente su entrambi (nuovo endpoint con relative nuove funzioni su repository, aggiornamento del frontend di conseguenza).
Va detto che la richiesta era piuttosto specifica e dettagliata e la memoria del progetto anch'essa molto esaustiva.
Show threadMagnus HedemarkApr 22

@awfulwoman I’ve definitely been spending more time using Chinese inference providers since heavy limits were placed on $100/mo #Claude Max subscribers. I was cut off Monday morning and am not allowed back in until late Thursday night. I used that time off to move to new tools and cancel my #Anthropic subscription.

#OpenCode is really good. So is #KimiK26 and #MiniMax27

AiBayApr 22

🚀 "L'innovazione non si ferma. Ecco Kimi K 2.6, il software che ridefinisce il concetto di autonomia. I padroni del software? Non più! #Innovazione #KimiK26" #socialmedia #artificialintelligence #technology

🔗 https://aibay.it/notizie/kimi-k-26-il-software-non-ha-piu-padroni-2026-04-22

Kimi K 2.6: il software non ha più padroni

Kimi K2.6 di Moonshot AI è un modello open source che eguaglia i migliori sistemi proprietari mondiali, ridefinendo gli equilibri economici e strategici de

AiBay
Andreas BeckerApr 21

Moonshot AI veröffentlicht das Open-Weights-Modell Kimi K2.6, das im Intelligence Index Platz vier belegt. Die Mixture-of-Experts-Architektur mit einer Billion Parameter und 256.000 Token Kontext erlaubt autonomes Long-Horizon Coding über 13 Stunden. Bis zu 300 Sub-Agenten arbeiten parallel.

#KimiK26 #MoonshotAI #OpenWeights #LLM #News
https://www.all-ai.de/news/news26top/kimi-2-6-openweight-test

Kimi 2.6 ist das beste Open Weight Modell

Die neue Architektur überzeugt durch enorme Ausdauer beim Programmieren und effiziente Agenten-Schwärme.

All-AI.de
michabbbApr 21

🚀 #MoonshotAI releases #KimiK26 — #opensource 1T-param MoE model, 32B active params, 262K context & native multimodal (image + video) input

🧠 +15% over K2.5 on benchmarks: better long-horizon coding stability, deeper reasoning & stronger instruction following #AI #LLM

🤖 #AgentSwarm now scales to 300 parallel sub-agents coordinating 4,000 steps simultaneously — up from 100 agents in K2.5

🧵 👇