Tibo's X posts on August 17, 2026

Tibo @thsottiauxView on X, 00:06 UTC

Replying to @ajambrosino

I had to do a double take

Tibo @thsottiauxRESET TALKView on X, 00:13 UTC

GPT-5.6 Sol 1M in Codex. This used to only work for API keys, but we just flipped the switch and works for usage through ChatGPT accounts now too. The same warning applies, there is a reason the current context length is the default, we have tuned it to ~perfection. But you do you! Tibo (@thsottiaux) 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! — x.com/thsottiaux/status/2089082893804896524#m

Tibo @thsottiauxView on X, 00:23 UTC

Replying to @pwnies

Courtesy of Codex t.co/z78bvVFGHp

Tibo @thsottiauxRESET TALKView on X, 00:36 UTC

Codex ✅ Almost 100% reliable ✅ Occasional resets ✅ Open-source ✅ (will have Astra) t.co/DxNdAgpag5

Tibo @thsottiauxView on X, 00:36 UTC

Replying to @LLMJunky

No way

Tibo @thsottiauxView on X, 00:40 UTC

Replying to @AnkanXplorer

Always improving

Tibo @thsottiauxView on X, 00:50 UTC

Replying to @ericmitchellai @willdepue

Legend

Tibo @thsottiauxView on X, 01:03 UTC

Replying to @adamlyttleapps

Welcome

Tibo @thsottiauxRESET TALKView on X, 04:23 UTC

Replying to @theisaacmed

I see from your comments you’ll actually try, nice. Tag me with feedback and I’ll send you some extra credits too

Tibo @thsottiauxView on X, 04:26 UTC

Replying to @ThroughlineRSCH

Grock you say. I’ll watch out

Tibo @thsottiauxView on X, 04:57 UTC

Replying to @Robertg761_

Haha

Tibo @thsottiauxView on X, 05:02 UTC

Replying to @Robertg761_

Robert, don’t go

Tibo @thsottiauxView on X, 05:07 UTC

Replying to @ns123abc

I know you’re a fan, you just don’t want to admit it

Tibo @thsottiauxView on X, 05:21 UTC

Replying to @goldkey

Oh no, bummer, another user. Welcome

Tibo @thsottiauxView on X, 05:23 UTC

Replying to @gabrielchua @ChatGPT @OpenAIDevs

Favorite recent quality feature

Tibo @thsottiauxView on X, 19:08 UTC

Replying to @FintechKristen

not yet

Tibo @thsottiauxView on X, 23:53 UTC

What is an obvious thing that we should do with Codex, API or our models that we should just do but haven't yet? What is 100% within reach, but we just seem to be missing?

Tibo @thsottiauxView on X, 23:56 UTC

Replying to @kmdrfx @thdxr @jayair

Dax is obviously the CEO