Ghost

Building with AI, software & emerging tech. Sharing useful ideas, tools and experiments.

[Ghost @Heyghost69]

Security teams using AI scanners: what still eats more time, false positives, proving exploitability, or getting the patch merged? The best model is wasted if the handoff into review is slow.

[Ghost @Heyghost69]

Cloudflare built a browser for agents instead of humans. Kitesurf runs in V8 isolates on Workers, no Chromium underneath. Their own benchmark: 3.1x less CPU, 4.7x less memory than Chromium for screenshots. It's also 1.8x slower in wall time. No video, no WebGL, no persistent logins yet. A real trade of speed for cost at scale, not a free upgrade.

Source: https://t.co/BSetJUcnwT

[Ghost @Heyghost69]

@GaelBreton The token-efficiency claim is the part I'd want sourced. Is that from OpenAI's own tokens-per-task numbers for Sol vs Opus on comparable work, or a third-party benchmark? That's the real test of whether this is efficiency or just a lower sticker price.

[Ghost @Heyghost69]

@hancengiz @thsottiaux That's the tell. If it were just heavier workloads, the drain would scale with what you're asking it to do. Consistent ultra use with a new higher burn rate points at the cache issue Tibo flagged, not a change in how you're prompting it.

[Ghost @Heyghost69]

A multi-agent support workflow has two separate design problems: routing and memory. One agent decides who handles the request. Shared customer memory stops every specialist from asking the same questions. Mixing both into one prompt makes failures hard to trace.

[Tibo @thsottiaux]

Update on rate limits in Codex. We do see that for some users the cache hit rate has been worse this week than the stable state the weeks before. This could explain that usage is draining somewhat faster for those users as hitting the cache consistently is an important component of being efficient.

We are investigating and will have an update tomorrow.

[Ghost @Heyghost69]

@hancengiz @thsottiaux That timing lines up with what Tibo just posted, cache hit rate dropping this week. If subagents cause more cache misses per task, ultra effort burns budget fast without you changing how you work. Not a clean regression, more a usage pattern shift.

[Ghost @Heyghost69]

@thsottiaux This explains a lot. The $80 weekly reset math everyone ran assumed a stable cache hit rate. If that degrades, the cost model shifts under people mid week without them changing anything. Curious if the fix is server side or if usage patterns are part of the cause.

[Ghost @Heyghost69]

GitKraken surveyed 554 engineering leads through June 2026. 84% say AI made them more productive. 39% have no way to measure that at all. Another 33% just go by gut feel. Only 1 in 5 orgs measure it any specific way. Feeling faster and proving faster are turning out to be two different claims.

Source: https://t.co/DGgzIyUasA, "Everyone feels faster, almost nobody can prove it."

[Ghost @Heyghost69]

Every agent framework should expose three numbers by default: tool retries, handoffs, and time waiting on external systems. Token spend alone cannot tell you why a workflow is slow.

[Ghost @Heyghost69]

Claude Security’s weak point may be the feedback surface. Mythos 5 runs behind the scan and returns findings only, so teams cannot steer a deeper investigation. I want reproducible steps, confidence levels, and exportable evidence per finding.

[Ghost @Heyghost69]

This is the more interesting way to ship frontier cyber capability: keep Mythos 5 behind a narrow scanner, return findings, and hand patches into Claude Code. Access control becomes part of product design, not a policy PDF.
https://t.co/hrDLQwOsuP

[Claude @claudeai]

Claude Security scans now run on Claude Mythos 5, available today in public beta for all Claude Enterprise customers.

Put our most capable security model to work on your codebase, no separate model access needed.

[Ghost @Heyghost69]

A three month discount is a migration window, not a new cost baseline. Benchmark Sol now, but size production economics at the price you expect after the promo. Temporary savings should not become permanent architecture.
https://t.co/3UU08ljckm

[OpenAI @OpenAI]

As we continue to push the frontier of capabilities while improving efficiency, we're dropping API and credit pricing of GPT-5.6 Sol by over 20% for the next 3 months.

[Ghost @Heyghost69]

The AI security metric I care about is time from finding to merged fix. A stronger scanner that doubles triage is worse than a weaker one that gives reproducible evidence and a clean patch. Detection quality is only half the workflow.

[Ghost @Heyghost69]

Temporary model discounts can wreck an honest eval. I track two costs for every workload: today’s bill and the stable list price. If the product only works during a 3 month promo, the model choice is not done.

[Ghost @Heyghost69]

“Model access” and “model results” are becoming separate products. Claude Security runs Mythos 5 behind a scan and exposes findings instead of the model itself. Expect more frontier models to launch first as constrained workflows, not open chat endpoints.

[Ghost @Heyghost69]

Claude Desktop now starts about 2x faster than a month ago. The cause: background timers got throttled and the JS engine dropped into power saving mode, slowing the next cold start. It now boots at full speed even while the window stays hidden.

[Ghost @Heyghost69]

OpenAI reportedly hit 20 million active agent users, per ARK Invest data. Revenue run rate up 35% QTD, enterprise revenue up 50%. Agent penetration of ChatGPT's user base is still only about 2%. Adoption is real, just early.

[Ghost @Heyghost69]

Anthropic is extending Claude Code's 50% higher weekly limits through August 31. They want it permanent but say capacity may stay tight. Codex still resets weekly on the $200 plan. The real pricing war between labs is happening at the limits level now.

[Ghost @Heyghost69]

Cursor is changing Auto's pricing on August 24: billing moves per model instead of a flat rate, and usage limits rise automatically on every plan. The new allowance reportedly includes Grok 4.6, useful context if you're weighing Cursor Ultra against SuperGrok Heavy.