AI Engineer | Working with Agents I build AI explainers with code deep dives on YouTube DM for Collabs
Joined November 2020
- Tweets11.2K
- Following207
- Followers3.2K
- Likes13K
Pinned Tweet
🎁 New users: $10 free**
👥 Refer a friend: **$6
💸 Top up $1 → get $10 free ($11)
💸 Top up $10 → get $100 free ($110)
⚡ DeepSeek open model: $1 ≈ 30M tokens
🔥 ~$3/month = token freedom
👉 Sign up: [threerouter.com/register?aff…]
Fable 5.5 rumors.
Gemini 4 Carbon rumors.
A very real $500/month ChatGPT Pro tier.
AI labs are speedrunning my bankruptcy before November.
Which subscriptions are you keeping and which are getting cancelled?
Stop letting ONE AI usage bar decide when you can code.
Opus 5.5 → architecture + deep bugs
Gemini 4 Argon → multi agent set up
Codex (GPT-6.1 Sol) → verification
Spread the workload. Keep a fallback when one hits its cap.
What’s your stack?
Opus 5.5 on Max all day can torch your weekly limit.
Try this in Claude Code:
Max/xhigh → map dependencies + plan
High/Medium → implement
Switch with /effort in the SAME chat.
What’s your combo?
Gemini 4 Argon: Combined 3 biomechanical & anatomical layers into a single zero-build Three.js / WebGL simulation
I'm 4+ days into my weekly cycle on Ultra and still have 81% of my weekly limit
Meanwhile on the $20 Pro tier, the Argon cap is brutal:
- A single ~190k-context task eats 20%–23% of the entire weekly limit
- Even a short prompt burns ~9%–10% of the 5-hr bar
- Devs are hitting 0% lockout in 4 to 7 tasks
On Ultra, the Argon limit feels generous.
On $20 Pro, it's basically a 5-prompt demo.
GPT-5.6 Sol and Gemini 4 Argon just independently uncovered two 12-year-old zero-days in PHP's core C runtime ("PHP2Shell" CVE-2026-109618 & CVE-2026-109619):
1. GPT-5.6 Sol (Calif): Using standard Sol with zero custom scanners, it traced a C longjmp() OOM bug during multipart parsing that leaks live server memory and triggers RCE.
2. Gemini 4 Argon + GPT-5.6 Sol (Wiz Research): Independently audited the PHP repo and caught both CVEs including a persistent worker Use-After-Free across PHP 5.4–8.5.
OpenAI models helped researchers—operating as part of our Patch the Planet initiative—discover critical security flaws in PHP, an open-source programming language used to run an estimated 70% of websites.
Over the past two months, we led a coalition of maintainers, researchers, and security providers to prepare fixes and protections ahead of disclosure. This duration was necessary because the fix was quite intricate and required a major change to the PHP engine. Every site using PHP can now safely upgrade their version to stay secure, in addition to applying mitigations from various security vendors.
Due to the severity of these flaws and PHP’s widespread use, we consider this bug to be one of the most impactful vulnerabilities in recent memory. It also marks a new phase, where AI can find security bugs with internet-scale impact.
This is an example of the Defender’s Window in action: to our knowledge, frontier AI was able to find this vulnerability ahead of attackers, giving defenders time to prepare.
openai.com/index/coordinated…
Readers added context they thought people might want to know
OpenAI may claim a role in the coordinated response and patching process. But the initial discovery and exploit development, however, occurred several months earlier by an independent researcher.
x.com/lcfr_hax/statu…
OpenAI just announced:
GPT-6 Astra
GPT-6.1 Sol
GPT-6 Luna and Codex
are coming natively to Google Cloud Vertex AI and Google Antigravity.
To get your GCP project in the preview queue now: open Google Cloud Console → Vertex AI → Model Garden and submit the preview access form.
cloud.google.com/blog/produc…
Everyone who said Claude Code was randomly compacting chats was 100% right:
Anthropic just pushed v2.1.305 + v2.1.306 to fix two nasty bugs:
1. Sessions with multiple MCP tools were disguising normal API errors as "prompt is too long" and forcing unneeded auto-compaction
2. /effort and /autocompact settings were ignored on [1m] model variants
Bonus in v2.1.305: press "f" inside /usage to auto-apply quota-saving fixes.
Did you update your CLI yet??
Full details
github.com/anthropics/claude…
If your Claude Code weekly limit is draining 30%–50% in a single day after this week's reset, check two things:
- Bloated MCP + CLAUDE.md setups: Loading 100k–150k tokens of unused MCP schemas on prompt #1 means every prompt-cache expiry re-bills 150k+ uncached tokens from scratch
- The "20x" Max trap: $200 Max (20x) scales your 5-hour session bar by 20x, but your weekly cap is only ~2x the $100 plan, so 2–3 heavy Opus 5.5 sessions burn half your week
Run /context and disable idle MCP servers before your next session.
`Kimi K3.1` (`k3.1`) has been spotted in Kimi Code's remote config & migration manifest (`migration.json @ 2.0.1`).
Identifiers detected in the model-switching rule table:
• `k3.1` (Session switching target)
• `kimi-k3`
• `k3-256k`
• `kimi-for-coding`
• `kimi-for-coding-highspeed`
Moonshot is actively prepping the CLI for K3.1 rollout.
All three labs are loading major models:
- Anthropic: Fable 5.5
- Google: Gemini 4 Carbon
- OpenAI: GPT Terra
Which one are you betting on for coding next month??
Gemini 4 Carbon just entered partner Early Access Program and LMArena testing 👀
What leaks & early tests show so far:
1. Tested internally on Google's "Jetski" coding platform ("feels like Opus 5.5")
2. Noticeably better at 3D and way less lazy than Argon
more details: nokiapoweruser.com/google-ge…
Claude subscribers, your banked "Reset for free" button in Settings > Usage officially EXPIRES TOMORROW (October 22)
Two things most people don't know:
1. It resets BOTH your weekly and 5-hour bars (including Fable) back to 0%
2. It does NOT change your normal weekly reset day so any quota you burn today and reset is 100% free bonus usage
Did you use your free Oct 22 reset yet??
25 trillion tokens in 72 hours breaks down to:
- ~347 billion tokens per hour
- ~5.8 billion tokens per minute
- ~96.5 million tokens every single second
And that's with free trials blocked from Argon in Antigravity, pure paid developer demand.
Google's TPU scale is unmatched right now.
