I've only had that happen with Chinese models until now. Interesting that Fable is doing it too.

Curious, which model do you use for Codex? I'm very happy with the solutions '5.5 high' finds. It's like it understands exactly what I mean and it also anticipates all sorts of situations. Before I used '5.5 medium' for some time and it was a bit underwhelming. It may sound funny but it's like it didn't care that much to do a good job.

I use GPT 5.5 High Fast, I often benchmark versus Fable (and previously did versus Opus) and it's night and day.

Claude still (and has always) writes far too much code to fulfill a given spec or plan. It misses edge cases and is generally far too verbose.

Claude also is (and even more so with Fable) super tokenmaxxing, i.e. it seems tuned to use the max amount of tokens per task, whereas Codex will simply get your job done as you specified with the minimum fuss and tokens.

Codex feels way more steerable and just more "professional" as though I'm working with a seasoned engineer, versus someone smart but over excitable, like a super smart associate engineer.

High Fast? I don't see that option in my Codex. I only have 3 models: 5.4-mini, 5.4 and 5.5, each with 4 levels: low, medium, high, extra high.

That's a good salary, better than Romania on average. And if you also have lower prices (at least that's what I heard), even better then.

I'm also unemployed. So far the models that I've used the most are Kimi and GLM. I haven't done that much agentic coding though, I've mostly used them for studying math and general conversations and I'm generally happy with their performance.

There's DeepInfra. There's also OpenRouter where you can find several providers.

I thought it was determined (slight pun) that free will is not a thing. I'm referring to Sapolsky's book "Determined: A Science of Life Without Free Will)" as an example.

In case you don't know, Gemini 2.5 flash is hosted on DeepInfra. They also have 1.5 flash but not 2.0 flash.

I have no affiliation with DeepInfra. I use them, because they host open-source models that are good.

Thanks. Yeah, for now we're moving to 3.1 flash lite as that's the new cheapest at $.25/1M and is also still "good enough". 2.5 flash is more expensive at $.30/1M (looks like Deep Infra charges the same as GCP/VertexAI for it). I might check them out for Gemma though. We benchmarked Gemma2 when that came out and it wasn't remotely usable for us largely because the context window was way too small. It looks like 3 or 4 might be worth evaluating though.

Xiaomi's mimo-v2-flash is great if you care about speed and performance - it's 1/10 the price of Gemini 3.1 Flash Lite and faster (on OpenRouter).

GCP does server other non-Google models, but I'm not sure what they have other than Anthropic models. I don't think Haiku is a great model though.

I use ChatGPT and Claude on OpenRouter, because it's just easier than buying credits on each platform separately.

by keeping the how part a secret

I wonder, how does a Julius perceive another Julius, as another competent worker? What about a non-Julius then?

I've seen it rationalized by saying you should be moving jobs every year or so, because if you're not doing that, then you're not growing. I've always thought of this as a sort of Julius coping mechanism. On some level, I think a Julius views a non-Julius as a stagnant old gray beard who rejects the "growth mindset".

To be clear: I've never seen people who follow this strategy contribute anything of value, and it's the biggest red flag on a resume. You learn and grow more by seeing things through.