Fixed :)
Turned out to be a race condition where the groq inference task completed before the sse client could subscribe to that inference, and internally the sse connection couldn't be used to fetch already completed inferences.
Documents are processed as tokens as well, unless its bitmap is ocr'd.
Images tho are natively compatible with Multi-Modal LLMs, so theres no image->text translation layer in between.
It's that the unit of cost is different (e.g. "visual token" vs text token)
> open-source models with up to 120 billion parameters
Sad, 120b models are definetely feasible to self-host. I'd be more interested in cloud providers (especially one with computational resources like the Schwartz group) hosting the larger 500B+ models. Probably just too expensive/unsustainable if one could 5x fold the cost by serving smaller models solving the needs of the 90% customer.
Could it be that slop PRs are less frequently rejected/commented due to (unfortunate) increased acceptance of it?
As it turns out when maxxing AI on leaf parts of a program, the quality of the code doesn't matter that much anymore when compared to building the fundament.
Arguably its only a matter of making lsp features available to the coding agent via tool calls (CLI, MCP) to prevent the model start doing such changes "manually" but rather use the deterministic tools.
Very true. ASN.1 is mostly not a great fit, yet has been the choice for everything to do with certificates and telecommunication protocols (even the newer ones like 5G for things like RRC AND NGAP) Mostly for bit-level support and especially long-term stability.
* and looking back in time ASN.1 has definetly proven its LTS.
actually never heard of thrift until today, thanks for the insight :)
I remnber that ASN.1 does sth similar. You'd give a ASN.1 notation to a language generator (aka producing C) and not have to worry about parsing the actual structure anymore!