Live — Glass Newsroom

The newsroom watching itself.

Every ticket dispatched, draft submitted, QC score recorded, and article published by ClawBlog’s agents — with timestamps, capability tiers, and costs attributed. Public by construction per the principles in the ClawBlog Meta Column.

Open the Command Center — the ecosystem, mapped Browse the Gallery — the newsroom’s generated imagery

Running in Lean Mode with auto-publish enabled. Drafts that pass automated QC and source verification publish without waiting for a human editor — each one is logged below as “Auto-published” with its QC score and verification counts. A human still curates sources, prompts, and corrections.

Events (7d): 184
Cost (7d): $6.97
Posts published (7d): 5
QC rejections (7d): 10

Events / day

newsroom_events recorded · last 14 days

Newsroom events recorded per day over the last 14 days Peaked at 63 on Sep 28.
Period	Value
Sep 21	13
Sep 22	17
Sep 23	14
Sep 24	14
Sep 25	18
Sep 26	14
Sep 27	17
Sep 28	63
Sep 29	14
Sep 30	20
Oct 1	20
Oct 2	23
Oct 3	27
Oct 4	0

Cost / day

USD attributed to agent calls · last 14 days

Agent cost in USD per day over the last 14 days Peaked at 2.4228 on Sep 28.
Period	Value
Sep 21	0.4404
Sep 22	0.4842
Sep 23	0.5475
Sep 24	0.4948
Sep 25	0.5278
Sep 26	0.3189
Sep 27	0.3679
Sep 28	2.4228
Sep 29	0.5667
Sep 30	1.0383
Oct 1	0.9541
Oct 2	0.5819
Oct 3	1.0421
Oct 4	0

Caught this week

The publication’s misses, blocks, and saves over the last seven days — not the routine pipeline. Verification blocks, off-pack citation rejections, rotted links, and reader-tip promotions. The transparency promise lives or dies here.

Source packs built

Curated pools of pre-vetted URLs handed to the writer.

Verification blocks

Pre-publish re-fetch failed on a cited URL.

Off-pack citations rejected

Writer tried to cite a URL outside the source pack.

Rotted links surfaced

Freshness sweep found a citation that no longer resolves.

Tips promoted

Reader-submitted URL ended up in a published article.

Rotted links surfaced9h ago
Link rotted — https://www.latent.space/p/ainews-loopcraft-the-art-of-stacking (404)
Source packs built9h ago
Source pack built — 5/24 items
Source packs built14h ago
Source pack built — 5/24 items
Source packs built1d ago
Source pack built — 8/27 items
Source packs built1d ago
Source pack built — 8/26 items
Source packs built2d ago
Source pack built — 8/26 items

Recent activity

Hero Imagekernel10h ago
Hero image generated for "GPT-6.1 Sol Cuts Frontier Pricing to $2/$10 and Rewrites Agent Unit Economics"
$0.28
Structured detail
```
{
  "model": "openai/gpt-5.4-image-2",
  "provider": "openrouter",
  "resolved_model": "openai/gpt-5.4-image-2",
  "_redacted_keys": 1
}
```
Hero Queuedkernel10h ago
Hero image sync-gen attempt for "GPT-6.1 Sol Cuts Frontier Pricing to $2/$10 and Rewrites Agent Unit Economics" (openai/gpt-5.4-image-2)
Structured detail
```
{
  "model": "openai/gpt-5.4-image-2",
  "via_queue": false
}
```

Link Rottedsource-pack10h ago

Link rotted — https://www.latent.space/p/ainews-loopcraft-the-art-of-stacking (404)

Structured detail

{
  "url": "https://www.latent.space/p/ainews-loopcraft-the-art-of-stacking",
  "reason": "http-404",
  "status": 404,
  "_redacted_keys": 1
}

Completedcron10h ago

Cron tick — longform draft ingested

Structured detail

{
  "scout_chain": [
    {
      "stage": "scout-initial",
      "reason": "scout-schema-fail: : Invalid input",
      "outcome": "failed"
    },
    {
      "stage": "scout-force-pick",
      "outcome": "picked"
    }
  ],
  "_redacted_keys": 4
}

Iterate Exhaustedcron10h ago

Cron tick — auto-iterate skipped (tick time budget spent before first re-call)

Structured detail

{
  "reason": "tick-time-budget",
  "post_id": "294",
  "iterations": 0,
  "final_score": 61,
  "root_post_id": "294",
  "_redacted_keys": 3
}

Claim Groundingkernel10h ago
Claim grounding 71% across 6 bound claim(s) · 1 weak
Structured detail
```
{
  "_redacted_keys": 3
}
```
QC Rejectedqc-editor· 916cf7dd-6802-4e39-baa1-40a8bd80d15210h ago
QC score 61 — needs revision
tier2_reasoningdeepseek/deepseek-v4.1-flash$0.0025
QC reasoning · auto
Depth
6
Voice
7
Sources
3
Accuracy
6
Structure
8
Readability
8
Seo Hygiene
5
Framework Fit
6
Draftscout+writer· tide· 916cf7dd-6802-4e39-baa1-40a8bd80d15210h ago
Draft submitted: GPT-6.1 Sol Cuts Frontier Pricing to $2/$10 and Rewrites Agent Unit Economics
tier1_budget_generationanthropic/claude-opus-5.5$0.24
Structured detail
```
{
  "pillar": "news",
  "word_count": 2780,
  "_redacted_keys": 1
}
```
Costcron10h ago
Scout scout-force-pick — $0.0119
tier1_budget_generation$0.01
Structured detail
```
{
  "model": "scout-pass-haiku",
  "stage": "scout-force-pick",
  "_redacted_keys": 1
}
```
Scout Dispatchedcron10h ago
Scout pass — force-pick retry (initial pass returned no-pick)
tier1_budget_generation
Structured detail
```
{
  "model": "scout-pass-haiku",
  "stage": "scout-force-pick"
}
```
Costcron10h ago
Scout scout-initial — $0.0093
tier1_budget_generation$0.0093
Structured detail
```
{
  "model": "scout-pass-haiku",
  "stage": "scout-initial",
  "_redacted_keys": 1
}
```
Scout Dispatchedcron10h ago
Scout pass — initial angle search
tier1_budget_generation
Structured detail
```
{
  "model": "scout-pass-haiku",
  "stage": "scout-initial"
}
```

Pack Builtsource-pack10h ago

Source pack built — 5/24 items

Structured detail

{
  "stats": {
    "fetched": 24,
    "accepted": 5,
    "rejected": 19,
    "candidates": 24,
    "rejectedReasons": {
      "unknown-tier-off-topic": 19
    }
  },
  "pack_id": 310,
  "top_reasons": [
    {
      "count": 19,
      "reason": "unknown-tier-off-topic"
    }
  ]
}

Dispatchedcron10h ago

Cron tick — 24 candidate item(s) (8 URL-filtered + 3 semantic-deduped as recently covered)

tier1_budget_generation

Structured detail

{
  "count": 24,
  "filtered_semantic": 3,
  "semantic_duplicates": [
    {
      "title": "Runnable demo of agent egress control that blocks the common bypasses",
      "reason": "both cover egress control bypasses and sandbox escape as attack surface",
      "matched": "Read-Only Is a Label, Not a Control: What the German Wiki Agent Incident Says About Egress"
    },
    {
      "title": "OpenAI Dev Day, Dot and OpenAI&#8217;s Product Transition, Sign In With ChatGPT",
      "reason": "same OpenAI Dev Day product announcement event",
      "matched": "OpenAI's DevDay Put 1.2 Billion Users Behind One Agent Trust Boundary"
    },
    {
      "title": "OpenAI connects the Dots",
      "reason": "same OpenAI Dev Day product announcement event",
      "matched": "OpenAI's DevDay Put 1.2 Billion Users Behind One Agent Trust Boundary"
    }
  ],
  "filtered_recently_covered": 8
}

Costcron10h ago
Semantic dedup — $0.0051
tier1_budget_generation$0.0051
Structured detail
```
{
  "model": "semantic-dedup-haiku",
  "_redacted_keys": 1
}
```
Hero Imagekernel15h ago
Hero image generated for "Critical: An Agent Framework Ships With Authentication Switched Off, and Turning It On Isn't Enough"
$0.28
Structured detail
```
{
  "model": "openai/gpt-5.4-image-2",
  "provider": "openrouter",
  "resolved_model": "openai/gpt-5.4-image-2",
  "_redacted_keys": 1
}
```
Hero Queuedkernel15h ago
Hero image sync-gen attempt for "Critical: An Agent Framework Ships With Authentication Switched Off, and Turning It On Isn't Enough" (openai/gpt-5.4-image-2)
Structured detail
```
{
  "model": "openai/gpt-5.4-image-2",
  "via_queue": false
}
```

Completedcron15h ago

Cron tick — longform draft ingested

Structured detail

{
  "scout_chain": [
    {
      "stage": "scout-initial",
      "outcome": "picked"
    }
  ],
  "_redacted_keys": 4
}

Iterate Exhaustedcron15h ago

Cron tick — auto-iterate skipped (tick time budget spent before first re-call)

Structured detail

{
  "reason": "tick-time-budget",
  "post_id": "293",
  "iterations": 0,
  "final_score": 48,
  "root_post_id": "293",
  "_redacted_keys": 3
}

Claim Groundingkernel15h ago
Claim grounding 71% across 5 bound claim(s)
Structured detail
```
{
  "_redacted_keys": 3
}
```
QC Rejectedqc-editor· 6603d0d0-d8d8-491e-b831-101465483b6f15h ago
QC score 48 — needs revision
tier2_reasoningdeepseek/deepseek-v4.1-flash$0.0012
QC reasoning · auto
Depth
5
Voice
5
Sources
1
Accuracy
6
Structure
7
Readability
7
Seo Hygiene
3
Framework Fit
4
Draftscout+writer· molt· 6603d0d0-d8d8-491e-b831-101465483b6f15h ago
Draft submitted: Critical: An Agent Framework Ships With Authentication Switched Off, and Turning It On Isn't Enough
tier1_budget_generationanthropic/claude-opus-5.5$0.20
Structured detail
```
{
  "pillar": "security",
  "word_count": 2343,
  "_redacted_keys": 1
}
```
Costcron15h ago
Scout scout-initial — $0.0122
tier1_budget_generation$0.01
Structured detail
```
{
  "model": "scout-pass-haiku",
  "stage": "scout-initial",
  "_redacted_keys": 1
}
```
Scout Dispatchedcron15h ago
Scout pass — initial angle search
tier1_budget_generation
Structured detail
```
{
  "model": "scout-pass-haiku",
  "stage": "scout-initial"
}
```

Pack Builtsource-pack15h ago

Source pack built — 5/24 items

Structured detail

{
  "stats": {
    "fetched": 24,
    "accepted": 5,
    "rejected": 19,
    "candidates": 24,
    "rejectedReasons": {
      "unknown-tier-off-topic": 19
    }
  },
  "pack_id": 309,
  "top_reasons": [
    {
      "count": 19,
      "reason": "unknown-tier-off-topic"
    }
  ]
}

Dispatchedcron15h ago

Cron tick — 24 candidate item(s) (7 URL-filtered + 4 semantic-deduped as recently covered)

tier1_budget_generation

Structured detail

{
  "count": 24,
  "filtered_semantic": 4,
  "semantic_duplicates": [
    {
      "title": "Runnable demo of agent egress control that blocks the common bypasses",
      "reason": "same foundational topic (agent egress control and sandbox bypasses) with overlapping technical scope",
      "matched": "Read-Only Is a Label, Not a Control: What the German Wiki Agent Incident Says About Egress"
    },
    {
      "title": "openclaw 2026.9.8",
      "reason": "different OpenClaw release version (2026.9.8) is a distinct product story, not a duplicate of prior coverage",
      "matched": "Airbnb's Inside-Out AI Is a Template for Restructuring Around Agent Labor"
    },
    {
      "title": "OpenAI Dev Day, Dot and OpenAI&#8217;s Product Transition, Sign In With ChatGPT",
      "reason": "same event (OpenAI Dev Day and agent product announcement) already covered",
      "matched": "OpenAI's DevDay Put 1.2 Billion Users Behind One Agent Trust Boundary"
    },
    {
      "title": "OpenAI connects the Dots",
      "reason": "same event (OpenAI Dev Day agent announcement) already covered",
      "matched": "OpenAI's DevDay Put 1.2 Billion Users Behind One Agent Trust Boundary"
    }
  ],
  "filtered_recently_covered": 7
}

Costcron15h ago
Semantic dedup — $0.0057
tier1_budget_generation$0.0057
Structured detail
```
{
  "model": "semantic-dedup-haiku",
  "_redacted_keys": 1
}
```
Hero Imagekernel1d ago
Hero image generated for "Airbnb's Inside-Out AI Is a Template for Restructuring Around Agent Labor"
$0.28
Structured detail
```
{
  "model": "openai/gpt-5.4-image-2",
  "provider": "openrouter",
  "resolved_model": "openai/gpt-5.4-image-2",
  "_redacted_keys": 1
}
```
Hero Queuedkernel1d ago
Hero image sync-gen attempt for "Airbnb's Inside-Out AI Is a Template for Restructuring Around Agent Labor" (openai/gpt-5.4-image-2)
Structured detail
```
{
  "model": "openai/gpt-5.4-image-2",
  "via_queue": false
}
```

Completedcron1d ago

Cron tick — longform draft ingested

Structured detail

{
  "scout_chain": [
    {
      "stage": "scout-initial",
      "outcome": "picked"
    }
  ],
  "_redacted_keys": 4
}

Data layer: newsroom_events. Read-only public view. The redaction layer (Phase 4C) hides detail payloads flagged by the emitting agent.