Pooya Raki

@PsychopathDz @Feliks_L @CodeWithAmann You just need to get an API key from their website and plug it into OpenCode or even Claude code. You can also run it locally if you have the hardware.

@PooyaRaki @Feliks_L @CodeWithAmann Where to try it?

Be honest, which is the best open source AI model?

@CodeWithAmann Well if Composer is built on Kimi then I‘m out :)

@PooyaRaki v4 is really good u should also try kimi

@Feliks_L @CodeWithAmann Pro - max effort

@PooyaRaki @CodeWithAmann Flash or pro ?

People are scared of @deepseek_ai stealing their codebase… But isn’t it kinda the opposite? 😄 We’re the ones cloning its code into our repos! Who’s storing who at this point? 🤔

AI-native software engineering teams operate very differently than traditional teams. The obvious difference is that AI-native teams use coding agents to build products much faster, but this leads to many other changes in how we operate. For example, some great engineers now play broader roles than just writing code. They are partly product managers, designers, sometimes marketers. Further, small teams who work in the same office, where they can communicate face-to-face, can move incredibly quickly. Because we can now build fast, a greater fraction of time must be spent deciding what to build. To deal with this project-management bottleneck, some teams are pushing engineer:product manager (PM) some teams are pushing engineer:product manager (PM) ratios downward from, say, 8:1 to as low as 1:1. But we can do even better: If we have one PM who decides what to build and one engineer who builds it, the communication between them becomes a bottleneck. This is why the fastest-moving teams I see tend to have engineers who know how to do some product work (and, optionally, some PMs who know how to do some engineering work). When an engineer understands users and can make decisions on what to build and build it directly, they can execute incredibly quickly. I’ve seen engineers successfully expand their roles to including making product decisions, and PMs expand their roles to building software. The tech industry has more engineers than PMs, but both are promising paths. If you are an engineer, you’ll find it useful to learn some product management skills, and if you’re a PM, please learn to build! Looking beyond the product-management bottleneck, I also see bottlenecks in design, marketing, legal compliance, and much more. When we speed up coding 10x or 100x, everything else becomes slow in comparison. For example, some of my teams have built great features so quickly that the marketing organization was left scrambling to figure out how to communicate them to users — a marketing bottleneck. Or when a team can build software in a day that the legal department needs a week to review, that’s a legal compliance bottleneck. In this way, agentic coding isn’t just changing the workflow of software engineering, it’s also changing all the teams around it. When smaller, AI-enabled teams can get more done, generalists excel. Traditional companies need to pull together people from many specialties — engineering, product management, design, marketing, legal, etc. — to execute projects and create value. This has resulted in large teams of specialists who work together. But if a team of 2 persons is to get work done that require 5 different specialities, then some of those individuals must play roles outside a single speciality. In some small teams, individuals do have deep specializations. For example, one might be a great engineer and another a great PM. But they also understand the other key functions needed to move a project forward, and can jump into thinking through other kinds of problems as needed. Of course, proficiency with AI tools is a big help, since it helps us to think through problems that involve different roles. Even in a two-person team, to move fast, communication bottlenecks also must be minimized. This is why I value teams that work in the same location. Remote teams can perform well too, but the highest speed is achieved by having everyone in the room, able to communicate instantaneously to solve problems. This post focuses on AI-native teams with around 2-10 persons, but not everything can be done by a small team. I'll address the coordination of larger teams in the future. I realize these shifts to job roles are tough to navigate for many people. At the same time, I am encouraged that individuals and small teams who are willing to learn the relevant skills are now able to get far more done than was possible before. This is the golden age of learning and building! [Original text: deeplearning.ai/the-batch/issu… ]

Safe is a cornerstone of the Ethereum ecosystem.

There’s a bug in X: Tap Edit Profile -> Edit Professional Profile. App freezes for a few seconds… then crashes. Hey @elonmusk mind taking a look?

@sama You mean really good at burning tokens no? :)

5.5 xhigh in fast mode is really good i think i got psyoped by twitter on medium for a bit

Running AI agents like Codex/Claude locally without isolation is stressful. Even “strong” sandbox settings can be bypassed by mistake. Just run them in Docker instead! Super easy: one Dockerfile that installs the CLI inside the container. Now you can let them cook without worrying about your system. More freedom, Less stress! I’ll share a quick guide soon…

everyone’s trying to do more faster, louder, nonstop and I’m just here wondering is this life or just a race?

@Anoyroyc Tried Composer 2, in my experience it hallucinates a lot compared to models like Opus. It even generated way more code than needed for something that should’ve been just a couple of lines.

🚨Cursor just pulled off the most insane power move in tech.. yesterday they needed OpenAI and Anthropic to survive.. every feature ran through their APIs.. Cursor was basically a fancy wrapper around other people's AI.. while everyone was building features.. Cursor was building infrastructure.. they weren't just using AI models.. they were learning how to replace them.. then Composer 2 dropped.. suddenly Cursor has their own model competing with GPT.. their harness makes any AI 10x better at coding.. customer to competitor overnight.. the companies that powered Cursor are now irrelevant in its ecosystem.. one update reversed the entire dependency chain.. they turned their biggest weakness into their strongest weapon.. nobody noticed until it was over.. this is ho in tech.. you don't fight giants.. you become one..

@Italianclownz How many tokens did you burn for $0.05? That’s important. I burned around 9M for only $0.17, which is insane. I guess the same amount of tokens on Opus would cost about 10 bucks.

I tried Deepseek V4. And in less than 5 minutes I already burned .05 using opencode and vibe coding.

@lividprowess Never heard of that! Keeping up with AI tools is basically a full-time job now :)

@PooyaRaki why dont u use Mistral

Tried DeepSeek Burned ~9M tokens for $0.17 🤯 v4 (pro max effort) is actually insane Models getting this good this cheap feels illegal Anyway… back to Claude/Codex 😂

@BacLeodiv Where are MySql/MariaDB?

if you had to start a new SaaS today, what database are you picking? - PostgreSQL - MongoDB - Firebase - Supabase

@ritu_twts Read .env

i am a Vibe Coder, scare me with one word

@mr_r0b0t Would be nice to measure model quality with proper agent onboarding. Looks insanely cheap

Be me: Sign up for DeepSeek API because everyone is saying how reasonably priced it is. Load up $50, let’s see. 30 minutes in, here’s where we’re at using V4-Pro

How come everyone just grabs an AI agent and throws it into their repo like it’s plug-and-play? You wouldn’t hire a dev and give them zero context. Why are we doing it with AI?

It‘s no longer: hand coding vs vibe coding It’s: how fast can you vibe code by hand and still trust what you ship?