What people are actually building, every day, summarized.
Today's chat centered on the arrival of Kimi K3 and its native CLI harness, which @geilt broke down in depth: AgentSwarm with 128 subagents (8 concurrent), 1M context window, HighS…
The community spent the day rearchitecting coding stacks around a new multi-model reality. OMP.sh emerged as the harness of choice, with @jcartu, @samb69, and Kieran championing it…
Model wars dominated the day, with Fable 5's aggressive safeguards pushing builders toward Sol and GPT-5.6. @jcartu vented about Fable burning tokens then refusing basic sysadmin t…
Coding agent workflows dominated the day. Grok 4.5 keeps winning converts on raw speed and token efficiency — @william_hodges burned only 25% of his weekly allotment across two sol…
The AI model wars dominated the day. What was billed as Fable's last day turned into a full extension from Anthropic, with the 5-hour usage limit temporarily removed for Plus, Busi…
Model orchestration dominated the day, with Grok 4.5 emerging as the cheap-fast executor of choice paired under Fable or Codex 5.6 as planner. @geilt swapped Gemini for Grok CLI 4.…
The day was dominated by post-launch reality checks on GPT-5.6 Sol. Members reported burning 50% of weekly quota in hours on Sol xHigh doing planning alone, with Extra-High and Ult…
The day belonged to OpenAI's GPT-5.6 rollout, which quietly landed via `codex update` / npm reinstall with no in-app prompt. Three tiers shipped — Sol (smartest, deeper planning, m…
Two big model moves shaped the day: Grok 4.5 dropped with a meaningful jump in tool-chain planning, 500k context (1M coming), and cleaner agent behavior — Elon claims Opus 4.7-leve…
The day whipsawed between panic and celebration as builders raced to burn Fable 5 credits ahead of a hard sunset, only to have Anthropic extend access on Claude plans through July…
The day was dominated by the Fable 5 anonymous-plan sunset (11:59 PM PST July 8), triggering a credit-burn frenzy with builders rotating multiple $200 accounts, running overnight l…
The July 7 Fable 5 anonymous-plan cutoff dominated the day, with an early surprise quota reset catching some accounts before the expected ~11:59 PM PST deadline. Builders like @jas…
Independence Day found builders at the keyboard, not the grill, racing to squeeze every drop out of Fable 5 before its July 7 anonymous-plan cutoff. The dominant workflow crystalli…
Fable 5 dominated the day as builders raced to squeeze value from limited-access windows before token caps hit. The emerging pattern: use Fable for planning, architecture, ADRs, an…
Day two of Fable 5's redeployment brought a sharply mixed reception. Enthusiasts like @filiuser, anonymous, and @samb69 reported one-shot Shopify checkout clones, a 2.7M-fact produ…
The day was dominated by Anthropic's redeployment of Claude Fable 5, which returned worldwide with US export restrictions lifted and inclusion in anonymous plans for up to 50% of w…
Anthropic dominated the day with a one-two punch: Sonnet 5 launched mid-morning at ~Opus 4.7 quality for $3/mtok with promo pricing through Sept 1, then hours later Anthropic annou…
Today's 414 messages from 73 active builders centered on stack consolidation and the rapid ascent of Chinese open-weight models. The Opus + Codex + GLM-5.2 combo hardened as the co…
Today's 651 messages across 79 builders centered on three big threads: harness/model stack choices, agentic coding methodology, and AI voice tutors as a flagship 'actually useful'…
Today's dominant thread was OpenAI's reported plan to gate GPT-5.6 (Fable 5) access to ~20 approved US companies, possibly with KYC and residency-based blocks. anonymous and @jason…
The biggest drop of the day was Cognee v1 from @Max_Bernstein, a memory layer claiming 145% better long-context recall than Opus 4.8 and GPT 5.5, an effective 100B-token context wi…
The day was dominated by builders rethinking their dependence on Anthropic as pricing, instability, and looming US regulation collide. Multiple users confirmed Claude 4.6 still bea…
The day's biggest debate centered on Codex vs Claude Code economics: builders broadly agreed Codex gives more bang per buck (rarely hitting limits, faster execution, gpt-image-2 in…
Anthropic dominated the day on both sides of the coin: Claude went down mid-morning with 500 errors that broke active CLI sessions, sending builders to Codex, OpenCode, and OhMyPi…
Today's discussions spanned testing strategy, model releases, and the widening guardrail gap between providers. @tounano kicked off a deep thread arguing real-browser E2E tests are…
Today's chat was dominated by Anthropic's announcement that Claude will require ID verification, sparking concerns about account farming, foreign access, and a domino effect across…
Today's chat was dominated by a Hermes reality check — @samarh90 called it a token guzzler and shiny object, prompting @rmktg and @Coybh to share concrete revenue use cases includi…
Today's chat was dominated by a reality check on running GLM-5.2 locally — @jcartu walked the group through why maxed-out Mac Studios won'anonymous cut it for the 1.1TB model, reco…
Today's builder chat zeroed in on a noticeable shift in Claude 4.8 — multiple users reported it taking initiative beyond requested scope, with @jcartu sharing that it autonomously…
Today's chat split between agent architecture, a wave of Meta account bans, and Midjourney's surprise pivot into MRI hardware. @jarvisballer, @rmktg, and anonymous went deep on mul…