What people are actually building, every day, summarized.
Astra's honeymoon ended on day three as builders reported loops, scope creep, and drift — the fix being a properly tuned harness and the emerging 'OMPHA' stack (OMP + Hindsight + A…
Sunday's dominant story was Astra's dramatic arc — early raves called it a 'generational leap' for frontend, UI/UX, and game design, with members canceling Claude subs to consolida…
Saturday was Astra's day. The model started appearing inside Codex for $200-tier ChatGPT users (logout/login required) and builders immediately called it a step-function upgrade ov…
Thursday belonged to Astra. OpenAI's new model (rumored GPT-6) began rolling out in the Codex model picker, and early testers led by @jcartu called it a bigger leap than Opus-to-Fa…
Tuesday's chat centered on model shakeups, ad platform pain, and infrastructure economics. Grok 4.6 got extended praise from @thewildzeno as a fast, pragmatic code-writing subagent…
Monday was dominated by Anthropic's surprise Fable 5.1 drop — builders reported dramatically faster inference, improved cache efficiency, and a less 'Claudish' tone, with most gett…
Saturday's conversation revolved around a shifting tooling stack. OMP emerged as the group's default coding harness, with @justingacina, @jcartu, @jarvisballer and others reporting…
Saturday's chat was dominated by video generation economics, with anonymous and @nowwatchthisdrive breaking down real per-second costs across Seedance 2.5 ($9 for 30s), Higgsfield…
Friday's conversation opened with a sharp debate on whether internal tools should be UI-first or agent-first. @tidemid argued that an agentic surface over your datastores makes tea…
Wednesday's chatter centered on model selection and harness maturity. A vocal thread pushed Grok as the main coder — fast, clean, and less preachy than Claude — with Jason Katiff,…
Wednesday's builder chatter split between a landmark performance milestone and a wave of practical stack blueprints. @jcartu cracked GLM 5.3 Flash on four 6k's, hitting 320 tokens/…
Wednesday's conversation centered on the Grok ecosystem and model choice. @jasonakatiff recommended running Grok alongside Codex for code reviews — Grok consistently surfaces more…
Apple's new Mac Studio with M5 anonymous/Ultra dominated Sunday's conversation, with 512GB configs landing at ~$17–20K and 4-unit clusters hitting ~4.8TB/s aggregate memory bandwid…
Sunday's discussion was anchored by @tounano's detailed walkthrough of a near-autonomous creative pipeline for native ads: a 100-ad decomposed library feeds headline generation, im…
Sunday's dominant theme was disciplined multi-model orchestration for coding. @jasonakatiff and GuruTime showed that Claude/Fable can directly invoke other CLIs headlessly (grok -p…
Saturday's chat was dominated by hands-on model orchestration experiments. anonymous led an in-depth Grok bot migration off Hermes — using Fable to write a handoff spec, then havin…
Today's chat opened with deep testing of the mystery 'ox-alpha' stealth model on OrcaRouter. anonymous ran it head-to-head against Opus 5 on a 47-shot video analysis pipeline and f…
Today's discussion centered on maturing AI-assisted coding workflows, with @jasonakatiff leading a push toward multi-model adversarial reviews — running Grok, Codex, and Claude Cod…
Today's discussion revolved around scaling AI-assisted coding workflows and getting smarter about model routing. Orca IDE cemented itself as the community's default harness, with @…
Claude infrastructure buckled under load all day, with widespread 'service busy' and model overloaded errors breaking long coding sessions — one member lost a 13-hour run. Sentimen…
Voice dictation dominated the day, with Wispr Flow hailed as a genuine AI aha moment — @jcartu reported 10-12x productivity gains running it on Android and Arch Linux, sparking a b…
Today's conversation centered on coding model preferences, with a lively debate over GLM 5.2 versus Kimi K3. The consensus leaned toward Kimi K3 as the stronger primary model, whil…
Model drops dominated the day. DeepSeek V4 Pro (0813) launched with ~65 tok/sec throughput, near-free cached tokens, and aggressive pricing — but hands-on testing quickly soured, w…
Anthropic's decision to embed invisible token-level watermarks in Claude output under new EU rules dominated the day, with builders concluding that scrubbing would require rewritin…
Today's chat was dominated by AI video economics and orchestration cleanup. Seedance 2.5 landed with strong reactions — @bartekadamczyk demoed 1:1 reference-video copies with consi…
Today's chat centered on model economics and local video gen. @jcartu evangelized Qwen3.8 anonymous as a legitimate Kimi K3 alternative at ~$250/quarter with 1M context and vision,…
Today's chat was dominated by growing frustration with Claude Opus 5's slowness and quality regressions, pushing many builders back to Codex or hybrid setups where Claude plans and…
Today's discussion centered on orchestration architecture, with @jarvisballer and anonymous sharing detailed playbooks for keeping orchestrators 'dumb' — offloading real work to fr…
MiniMax H3 dominated the day as builders collaborated on local inference optimization across every tier of consumer GPU. anonymous clocked 90 seconds per 5s clip on a 5090, anonymo…
MiniMax H3 dominated the day as builders got a strong open-weight video model running locally on a single 5090 — generating 5s cinematic clips in ~3 minutes and 15s 768p scenes wit…