codex-reset.com
Telegram alerts channel Discord server Email alerts

⚠️ strong Tibo signal · ✅ verified reset · 🎟️ banked reset — resets only, nothing else.

Tibo X posts Aug 16, 2026

Tibo's X posts on August 16, 2026

What Tibo (@thsottiaux) posted on X on Sunday, August 16, 2026 (UTC): 24 posts, in the order he posted them.

No Codex reset was announced that day.

Get the reset alertTelegramDiscordEmail

Tibo @thsottiauxView on X,

If you have a company and still use Opus instead of Sol, why so? Does price not matter to you? What's something that would convince you to switch?

Tibo @thsottiauxView on X,

Replying to @AISupplyGuy1

Do you have evals? Quite surprising as I would expect for most things you would net out 40-50% cheaper per task with Sol. Can you share more?

Tibo @thsottiauxRESET TALKView on X,

Replying to @ns123abc

I'll write more extensively about this, but OpenAI token != A\ token. We use different tokenizers. And OpenAI's tokenizer is significantly more efficient. This is important given you pay per token over the API and in usage. The difference is ~30% in number of tokens, definitely t.co/RwDz5AdK1t

Tibo @thsottiauxView on X,

Replying to @RJMcGirr

Sol can probably migrate you in a few hours. Why isn't it worth the many $$$ you would get back in return?

Tibo @thsottiauxView on X,

On tokens and prices per token. I said I’d write more about this, so here goes: an OpenAI token != another model’s token. We compare AI prices in dollars per million tokens as if a token were a standardized unit, like a gram or a kilowatt-hour. It isn’t. Different models use and produce the exact same text using different numbers of tokens, which means a lower price per token does not necessarily mean a lower bill. Imagine two identical pizzas. One is cut into 8 slices at $2 each. The other is cut into 16 slices at $1.25 each. The second place advertises cheaper slices, but the whole pizza costs $20 instead of $16. Bummer ... your stomach doesn't actually care about the number of slices you just ate. I know you are hungry now, but back to tokens. In one small comparison spanning English, technical, multilingual, and numerical text, the tokenizer we use for GPT-5.6 Sol used 766 tokens versus an estimated 1,170 for Claude Opus 5. That's a very significant difference of about 34.5% fewer tokens. You can get the same exact text, but pay for all those extra tokens. The price per token doesn't really tell this story. Even correcting for tokenizer differences misses the bigger point. What actually matters is price per successful outcome, and for that you can use benchmarks as a starting point, but really you have to try it and measure on your own use cases. That's all. May the tokens flow.

Tibo @thsottiauxView on X,

Sunday is for good vibes. As is any day of the week, but especially Sunday.

Tibo @thsottiauxRESET TALKView on X,

Here is how to enable a 1M-token context window in Codex for GPT-5.6 Sol. Even though we have tuned the context limit in Codex to be set optimally when it comes to performance and cost, this is a common ask, so here it is documented. A larger context window lets Codex retain more code, tool output, and conversation history before summarizing older material. You need a model that supports it. And GPT-5.6 Sol, for example, has a documented 1,050,000-token window. Open ~/.codex/config.toml and add or update these settings at the top level, before any [section] headers: ``` model = "gpt-5.6-sol" model_context_window = 1000000 model_auto_compact_token_limit = 900000 ``` The first setting selects the model. The second tells Codex to use a one-million-token context budget. The third starts automatic history compaction around 900,000 tokens, leaving some headroom. Restart Codex client and start a new session after saving. To try the configuration for a single CLI session without changing your defaults: ``` codex -m gpt-5.6-sol \ -c model_context_window=1000000 \ -c model_auto_compact_token_limit=900000 ``` Have fun, but also know that we tuned the default carefully!

Other days in August 2026

Posts and replies by @thsottiaux as codex-reset.com's monitor collected them through the X API: every post it saw from July 31, 2026; before that, only his reset posts.

Text only: images, videos, quotes and reposts are not shown, and each post links back to X. Days and the default clock are UTC; “Tibo time” is US Pacific.