Tibo's posts on August 17, 2026

Replying to @kmdrfx

@kmdrfx @thdxr @jayair Dax is obviously the CEO

14 replies · 3 reposts · 185 likes

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?

6,365 replies · 115 reposts · 5,225 likes

Replying to @FintechKristen

@FintechKristen not yet

48 replies · 2 reposts · 237 likes

Replying to @gabrielchua

@gabrielchua @ChatGPT @OpenAIDevs Favorite recent quality feature

47 replies · 5 reposts · 288 likes

Replying to @goldkey

@goldkey Oh no, bummer, another user. Welcome

75 replies · 7 reposts · 1,796 likes

Replying to @ns123abc

@ns123abc I know you’re a fan, you just don’t want to admit it

22 replies · 1 repost · 495 likes

Replying to @Robertg761_

@Robertg761_ Robert, don’t go

61 replies · 1 repost · 388 likes

Replying to @Robertg761_

@Robertg761_ Haha

17 replies · 0 reposts · 104 likes

Replying to @ThroughlineRSCH

@ThroughlineRSCH Grock you say. I’ll watch out

31 replies · 2 reposts · 883 likes

Replying to @theisaacmed

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

112 replies · 2 reposts · 1,061 likes

Replying to @adamlyttleapps

@adamlyttleapps Welcome

24 replies · 0 reposts · 164 likes

Replying to @ericmitchellai

@ericmitchellai @willdepue Legend

1 reply · 0 reposts · 40 likes

Replying to @AnkanXplorer

@AnkanXplorer Always improving

43 replies · 2 reposts · 644 likes

Replying to @LLMJunky

@LLMJunky No way

24 replies · 0 reposts · 342 likes

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

1,683 replies · 420 reposts · 13,254 likes

Replying to @pwnies

@pwnies Courtesy of Codex https://t.co/z78bvVFGHp

31 replies · 5 reposts · 646 likes

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! — https://x.com/thsottiaux/status/2089082893804896524#m

618 replies · 253 reposts · 6,057 likes

Replying to @ajambrosino

@ajambrosino I had to do a double take

35 replies · 6 reposts · 1,043 likes