arcanemachiner

But then someone would write an article complaining about how the newly-injected date confused their agent!

I think GPT 6 will be OpenAI's response to Fable/Mythos. There are (baseless) rumours that it will be coming fairly soon.

They're probably not going to remove Fable. They just extended it for another month.

Did you enable the flicker-free TUI mode?

I have my LLM agents fact check each other as a matter of course. They each regularly find things that the other missed. They are typically the same model (Opus).

Eh, it doesn't hit you until it hits you.

I finally bumped into a task that Codex would refuse to work on.

Was I attempting to reverse-engineer a GPU driver? Yes. Was I trying to hack into the DoD? No.

I wasn't doing anything wrong, but that's not what OpenAI's safety mechanisms thought.

No, that was totally different. They were just doing that for your safety.

I'll probably never use this, but at least they're not delusional enough to attempt to justify keeping their coding agent closed-source, especially after their recent data-harvesting cockup:

https://cereblab.com/

Probably at least two.

Isn't Fable just Mythos + guardrails? Sounds like you did throw Mythos at it.

Yes, there is an LLM feature that we have anthropomorphized as "reasoning" or "thinking", where an LLM has a scratch space where it can dump tokens that help to improve the final output.

OpenAI, to their credit, seems to be focusing pretty heavily on token efficiency in GPT 5.5 and beyond.

I have a functional Pi config, mostly self-made (it has everything I want, incl. subagents, web search, a /btw command, and other misc. addons), and my system prompt is ~3k.

You can't afford the best model. What are your specs and what models + quants have you tried?

Qwen 3.6 35B A3B and Qwen 3.6 27B can both do reliable tool calls on Pi at Q4_K_M using llama.cpp

Wow. That article totally sucked me in!

nginx is also Russian, so don't use... a third of the web.

People work on different things, fail to mention their field of usage in the comments, and then misunderstand the experiences of others who do the same. Repeat ad nauseam.

I find that I have to tell GPT and Claude to keep asking me questions, or they will just fill in the gaps themselves (wrongly).

They also stopped making them again.

The $5 is so they can see if open weights models are worth using, not so they can use it for a month. (Which you can't; The quota runs out way sooner than a month for any serious usage. Still worth the price of entry.)

4.7 Flash is a small model that's almost a year old, which is ancient. And yes, your dinky GPU will not run anything worthwhile.

Just spend $5 on OpenCode Go and give GLM 5.2 a shot if you have the time. It's not quite as good as Opus, but it's more than good enough for many tasks.

A second look is always useful when using these damn things.

The slop is breaching temporal containment!

Provides access to AI models for a per-token fee. See OpenRouter, they are one of many.

Billed at unsubsidized (and very expensive) API rates.

That rule can be followed, but it gets a little tricky when mixed up with the other ten thousand rules that it's following at any given time.

Yes, and you will still not understand as well as if you had built it.

Don't give it the necessary permissions to push to remote.

I run mine in a container, so it doesn't have access to the SSH key I use to push.

Opus is so damn slow that it's forced me to work on multiple items at a time, whenever possible. Waiting for one session? Just switch to another!

They didn't fork it, they post-trained on top of it.