Glenn 'devalias' Grant

@thomai Curious what the alternative solution you ended up choosing to use was, if you're open to sharing?

`0.30.0` added the start of support for `--resume` and `--continue`: - https://github.com/openai/codex/releases/tag/rust-v0.30.0 - https://github.com/openai/codex/pull/3135 - https://github.com/openai/codex/pull/3185 - https://github.com/openai/codex/pull/3218 See also: - https://github.com/openai/codex/issues/1991 - https://github.com/openai/codex/issues/3233

Is this PR still relevant after things like this were merged? - https://github.com/openai/codex/pull/4470 - https://github.com/openai/codex/pull/4474 - etc

@Yusufkulcu Dumb question.. but did you try it again following the instructions in the warning message shown in your screenshot about how to potentially resolve out of memory issues by...

> How do we need to give the 8gb value you specified? @Yusufkulcu I'm assuming you mean 'why do we need to specify 8gb if the file is only 6-7mb'?...

> After that fix, now getting a new issue unfortunately: > > ``` > --------------------------------------------------------------------------- > AttributeError Traceback (most recent call last) > [](https://localhost:8080/#) in () > 23 note_seq.play_sequence(est_ns, synth=note_seq.fluidsynth,...

> do you suspect the issue is in [`main`/src/plugins/local-llm-rename/gbnf.ts](https://github.com/jehna/humanify/blob/main/src/plugins/local-llm-rename/gbnf.ts?rgh-link-date=2025-04-21T04%3A58%3A47.000Z) ? or with `node-llama-cpp` itself? i mean, current version of `node-llama-cpp` is @ 3.7.0 and this lib is @ 3.0.0 @skilbjo...

> didn't try it on older versions @skilbjo _nods_, fair. > but my guess is that increased specificity in the system prompt goes a long way @skilbjo _nods_, yeah; it...

> a common criticism of LLMs is that they are non-deterministic @skilbjo Sure.. but that prompt was seemingly stable and good enough to work from whenever it was first committed...

``` TypeError: register_with_handler() got an unexpected keyword argument 'for_restore' ``` See also: - https://github.com/magenta/mt3/issues/151