Alex’s AI posts
Alex Getman’s posts on AI models, tools, releases, prices and usage limits, newest first.
Search
Anthropic
AlexClaude Code users, change this setting if you use subagents
Claude has prompt caching with a 1-hour TTL, but that’s only for the main agent. Subagents get just 5 minutes by default. If you use long-running…
OpenAIAlexGet your banked reset and sign for it
AnthropicAlexClaude Sonnet is now 20% cheaper on many tasks thanks to cheaper cache
OpenAIAlexGPT-6 is rolling out in web, including to Plus users!
AnthropicAlexClaude Haiku 5.5 is out!
Absolutely destroys GPT-Luna across all benchmarks. The model is extremely cheap, especially under 100k context. Input $0.10 / MTok up to 100,000…
AnthropicAlexClaude Haiku 5.5 appeared in the new Claude Code binary
OpenAIAlexTibo reset Codex limits
The features were pretty weak. Even the new math proofs release couldn’t save it. Series tied 1-1.
OpenAIAlexDay 2 of the OpenAI sprint: negative overall
2.1 is a decent feature. Auto-review for risky actions sounds useful, especially for sub-agents and long-running tasks. But I’m always on bypass…
MistralAlexThe French at Mistral just dropped Large 4
Looks like Europe’s biggest hope in frontier AI is still alive. 1 trillion parameters, with 49B active at a time. In some benchmarks, it already…
OpenAIAlexDay 1 of OpenAI’s sprint: overall positive
Going from ~30 TPS to ~50 TPS is already a meaningful improvement and basically puts it at Fable-level speed. That said, I think the bar is higher…
OpenAIAlexThe OpenAI team has entered its redemption arc
From now on, every day brings either a genuinely useful feature or a full reset. Let the comeback begin.
OpenAIAlexCodex reset has arrived!
OpenAIAlexCodex reset incoming, so we gotta use up our limits
OpenAIAlexFeels like Tibo won’t be doing any more resets
GoogleAlexGemini 4 Argon scores 53 and ties for 3rd place with Fable 5.1 and GPT 6 Astra on the AA Intelligence Index
GoogleAlexGemini 4 Argon takes the #1 spot on Text Arena
GoogleAlexGoogle announced Gemini 4 Argon
Pricing starts at $2 per 1M input tokens and $10 per 1M output tokens. For now, only approved organizations have access.
OpenAIAlexI’m seeing a lot of negativity around OpenAI, so let’s separate the real issues from the noise
Since GPT-6.1 Sol came out, I’ve been using it nonstop. In terms of usage, it honestly feels almost like Luna. My limits barely move. I even run…
AlexNew banked reset just landed, check your account
OpenAIAlexGPT-6.1 Sol ranks 5th on the AA Intelligence Index
Honestly, it feels like they just took Astra, cut the price, and called it Sol. Kind of a rushed rebrand after people roasted OpenAI, let’s be real.…
OpenAIAlexOpenAI dropped a bunch of new stuff today
Here’s my quick take: 1. Dots Some kind of OpenClaw alternative, I guess. I didn’t even understand half of it and honestly I don’t care. 2.…
OpenAIAlexDevDay recap is already here (?)
OpenAIAlexGPT-6.1 Sol IS OUT!
OpenAIAlexOpenAI DevDay is officially underway!
Their biggest event of the year. I’ll keep you posted. https://openai.com/live/
AnthropicAlexAI subscription buying guide:
$1 - Command Code $10 - OpenCode $20 - Claude $40 - Claude + GPT $120 - Claude Max + GPT At $1 and $10, you’re basically just paying for DeepSeek…
AnthropicAlexSonnet 5.5 Max beats GPT-6 Astra Max on the Intelligence Index vs
cost curve A few other things stand out: 1. At medium, GPT-6 Sol is much cheaper than Sonnet 5.5 at a fairly similar intelligence level. 2. Around…
AnthropicAlexSonnet 5.5 ranks #2 on the Artificial Analysis Intelligence Index, ahead of Fable 5.1
It also beats GPT-6 Sol by 8 points.