Desimulate

omw

@jahooma Free with a side of supply chain attacks

Introducing a 100% free coding agent with DeepSeek v4 Pro Choose any model, all free: - DeepSeek v4 Pro/Flash - Kimi K2.6 - MiniMax M2.7 npm i -g freebuff

@AmarMh04 yes

@de5imulate can i use it as wallpaper?

@TravisToastLord Soon

@de5imulate Any updates on that game?

@ericzakariasson Can you configure which models play which roles?

orchestrate a swarm of agents here's a visualization of the swarm and how it's using multiple planners, verifiers, and workers try it today with /add-plugin orchestrate and then /orchestrate [goal]

@yacineMTB Just wait til you try orchestration

Fucking insane man. I wrote a prompt, explained very carefully what I want right before I left and it was done after I hung out with my kid at the park My progress is fully bottle necked by my ability to plan and structure work the right way

@nxhaaa19 This has to be rage bait

Claude Opus 4.7 vs GPT-5.5 what nobody is telling you: -Opus 4.7 wins on coding. It's not close. -GPT-5.5 wins on terminal workflows and math -Both have 1M token context windows -Opus 4.7 sees images at 3x higher resolution -GPT-5.5 uses 72% fewer tokens for the same task -Opus 4.7 is better at fixing real GitHub issues -GPT-5.5 is faster and cheaper to run at scale They're not competing. They're optimized for different work.

@BerkshireFX @BGatesIsaPyscho Definitely ants

@BGatesIsaPyscho Not sure ticks scuttle that fast. Think this may be a hoax.

🚨🇺🇸 Meanwhile in America “Look at them crawling out of there - millions of Ticks” The story is so insane - Farmers continue to report finding Boxes full of Ticks on their farmland, clearly left their on purpose. Now the US has already seen a sharp increase in the number of Tick related diseases.

@Mayhem4Markets Isn’t 27b even better? Why compare 35b MOE

This is actually insane. 🤯 Claude Opus 4.6 has around 200B active parameters and registers 75% on SWE-bench verified. Meanwhile, Qwen 3.6 35B A3B has 3B active parameters and scores 73.4% on SWE-bench verified. Same benchmark, but Qwen has 60x fewer active parameters.

@NickADobos Its reasoning limit meaning it’ll make better decisions. You don’t need high reasoning to code, use high reasoning to plan then low to execute

What’s the difference between GPT 5.5 low reasoning + /goal Vs GPT 5.5 xhigh reasoning + one shot Both are essentially yeeting compute at a task. But which one - is more efficient? - works better & produces better results? - finishes the task? Seems like the major difference is low would spend less time thinking between each step? And would do way more tool calls because of this?

@Raytargt He’s paying with his soul

21-year-old American student. $43,000 in 30 days on OnlyFans. Never left his dorm room. The girl doesn't exist. 1,247 paying subscribers. Zero suspect. Roommate thought he had a girl hidden under the bed. Filed a transfer request after a week of 3 AM moaning. Empty room. Top fan: married engineer in Berlin, wife six months pregnant. Sent Maya $1,847 in three weeks. Thinks she's 22, in Tampa, texted "I miss you" yesterday. Wrong on three of three. Maya is 4 markdown files. 12 KB total. Runs on a $400 used MacBook. Claude writes every reply. Flux generates every photo. ElevenLabs cloned her voice from a Fiverr actress who still doesn't know. Compute: $400/month. Net: $32,710. Starting capital: $400. OnlyFans paid out $5.8 billion last year. Anyone with a folder takes a slice. Someone's building yours right now.

@wiznesspro Opus is a reasoning model, it’s not that miles ahead at code. Planning with Haiku is like planning with a junior engineer. Plan with opus and execute with sonnet, or composer or kimi or anything.

Tous les utilisateurs Claude après avoir lu cet article

@justinsunyt Yeah it’s dumb

kanban doesn’t make sense for coding agents we tried it 6 months ago. every task just ended up in the “needs review” column

wake up

@NopContext good to be back

@de5imulate Missed you, bro.

sleep tight

@NopContext very

Dude, you still alive?

@ParthJadhav8 Please god don’t let the future of AI workflows be a kanban board

This is crazy !! Cursor now has built a Kanban board where you can just drop in tasks and the agent will pick those up and complete them.

@burkov Bad rage bait

Cursor is Elon's first purchase, which is a huge mistake. A coding agent harness is now open source (see Codex and Claude Code). The current design works virtually perfectly, so there's no need for a fundamentally new design. One can say that agentic coding is solved. One might argue that he bought Cursor for users, but users, as we know, switch between coding IDEs frictionlessly, so it's not like Twitter, where you cannot leave without losing followers. Cursor is an emperor with no clothes. A shell without substance. You only know it exists because it's been there before most others.

@_MaxBlade The only thing gpt 5.5 is one shorting is my usage limit

DEEPSEEK V4 is dead on arrival. I had it build a pokemon style battle app. 1 prompt. the game crashes EVERYTIME and the Ui is absolute garbage. GPT 5.5 one shotted a masterpiece. Codex is the way.