Bad Boy

@max_spero_ That’s what she said

This is HUGE!

@Rasmic Me

if i host a cod/bf lobby who joining?

@thdxr Sweet

if the bot has its own computer it can make its own apps

@0x45o ART

do people not know GitHub history is a form of art

@AbubakerDev designs need vision, fable 5 in the hands of right designer would COOK

Fable 5 is impressive. But it still can’t create designs like this.

@kseniam0s startup

Give me a startup name SO COOL it sounds like the next unicorn 🦄

@Rasmic W

All you need to cook with AI

@AdamHoltererer Clean

GPT 5.6 Sol Frontend Test: Without Skills vs. With Skills

Gpt 5.6 Sol is lovely

@CelsooMoreno @thegenioo bot

@thegenioo Fable 5 nerfed version is still better than sol

THEY FIXED FRONTEND FOR GPT-5.6 FINALLY!!! THIS IS NOT EVEN SOL THIS IS LUNA

CTO shared this with me on day 1 something everyone should read if they are in an early-stage startup at least once

@Rasmic you the real model

Everyone’s dropping models

@AIatDoorDash Meituan better

Models out of the box have trouble reviewing DoorDash’s codebase, even when feeding them appropriate context. Single-pass AI reviewers only caught 30% of the real issues in our PRs. Instead, we built a multi-model (Sonnet 4.6 + Opus 4.8) code review agent that caught 53.6% issues at $3.91 a PR (most enterprise code review solutions perform significantly below 50% recall on DoorDash PRs). Today, we’re proud to share DashBench, our internal benchmark to compare multi-model/harness code review systems against each other. DashBench has given us confidence in maximizing the intelligence per dollar we’re spending on AI tokens to ship code safely.

@itsrameee Can your dad fight?

She’s in Pakistan mind you 😭

@netanyahu fuck you

@Imissbluey Creepy

Now kiss!

Somebody turned GitHub profiles into FIFA cards and I'm obsessed 😭

delete this.

Use Fable 5 as orchestrator and Opus + Codex to execute (to save fable usage): Fable 5 (max reasoning) = orchestrator Opus = deep reasoning subagent Sonnet = mechanical work subagent Codex = peer Sr. engineer, different perspective Setup: 1. Set Fable 5 as your main model In Claude Code: /model → Fable 5 → reasoning /effort to max 2. Create 2 subagents with /agents In Claude Code: deep-reasoner → pinned to opus "Use for reasoning-heavy phases, architecture, debugging complex issues, algorithm design. Think thoroughly, return a concise conclusion the orchestrator can act on." fast-worker → pinned to sonnet "Use for mechanical tasks, boilerplate, tests, formatting, simple edits. Execute efficiently." 3. Add OpenAI's official Codex plugin (install codex cli in your computer first), In Claude Code type: /plugin marketplace add openai/codex-plugin-cc /plugin install codex@openai-codex /codex:setup 4. Drop this in your CLAUDE.md in your folder: ## Orchestration workflow You (Fable) are the orchestrator. Plan, decompose, synthesize. Reasoning-heavy phases → deep-reasoner Mechanical work → fast-worker Codex (/codex:rescue --background) is a cracked engineer on par with deep-reasoner, from a different perspective. Treat as a peer, not a reviewer. High-stakes decisions: task Opus + Codex on the same problem in parallel, synthesize the best of both, without showing either the other's answer. Keep your own context lean. 5. Then prompt Fable like a tech lead: "Goal: [what you want] Context: [files, constraints] You're the lead. Delegate reasoning to deep-reasoner, grunt work to fast-worker, fresh-perspective problems to Codex. Show me your plan first, then execute." That's it.

@ai_for_success 🤣🤣🤣🤣

"Mom, how did we get so poor?" "Your father discovered Fable 5."