What people are actually building, every day, summarized.
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…
Model preferences shifted noticeably today — Opus 5 is quietly replacing Fable as the orchestration model of choice for several builders, with @fmill1 and anonymous reporting it be…
Model wars dominated the day, with Grok 4.5 fast emerging as the token-efficient workhorse favorite while GPT-5.6 Luna anonymous impressed on quality but disappointed on speed (80…
DeepSeek dropped V4-Flash-0731 (ds4f) today and it dominated the conversation — 153M tokens for 79 cents, 200-250 TPS on dual RTX 6000s, 100-300 tok/sec on M5 anonymous 128GB runni…
Token economics and harness choice dominated the day. Kieran shared research showing Claude Code sends ~33k tokens of harness overhead before your prompt while OpenCode sends only…
Prompt engineering evolution and platform reliability defined the day. @iamgalba showed that trimming ~70% of verbatim from CLAUDE.md, skills, and progressively-disclosed docs made…
Kimi K3 dominated the day as subscriptions opened broadly and Moonshot released open weights on HuggingFace (attribution only required above 100M MAU or $20M monthly revenue). @Vai…
Kimi K3 dominated the morning as builders hunted for non-China hosting options. @jcartu confirmed Fireworks.ai now hosts K3 in the US with near-lossless MXFP4 quantization (invite-…
Day two of Claude Opus 5 dominated the channel, with builders running head-to-head tests against Fable, Codex 5.6, and Grok 4.5. Consensus: Opus 5 is cheaper and faster than Fable…
Anthropic dropped Claude Opus 5 (and Sonnet 5) mid-morning and it dominated the day. Early testers report it beats Fable on most tasks at lower cost, is noticeably faster, and refu…
Builder trust in Anthropic continues to erode as members report Claude/Fable/Opus outputs degrading, burning tokens on unrequested testing, and stalling in loops. Weekly usage caps…
Anthropic continues to lose builder trust as Claude, Fable, Sonnet, and Opus ship degraded outputs, burn tokens on unrequested testing, and expand scope beyond user instructions (e…
Anthropic dominated the day for the wrong reasons — a ~1.5 hour full outage (65+ incidents) plus noticeably degraded Sonnet and Opus output pushed Fable users to migrate en masse t…
Today's builders' chatter was dominated by Anthropic's Fable 5 falling out of favor — users report silent auto-downgrades to Opus mid-task, cybersecurity refusals on benign work (i…
The day was dominated by a rapid harness and model reshuffle around OMP (omp.sh), which emerged as the coding harness of the moment. Builders migrated from Claude Code and stacked…
Today's chat was dominated by a major harness and model reshuffle. OhMyPi (OMP) emerged as the coding harness of the week, with @jcartu's endorsement pulling @mj888g, @geilt, anony…
Today was dominated by the Kimi K3 launch and a broader reshuffling of the model-and-harness stack. @jcartu ran K3 head-to-head against GPT 5.6 Sol, Fable, and GLM 5.2 on a complex…