[jasondclinton]

Hi, CISO of Anthropic here. Thank you for the feedback! If you can share any details about the image, please share in a private message.

No LLM has had an emergent calculator yet.

[connorgutman]

Regardless of emergence, in the context of "putting safety at the frontier" I would expect Claude 3 to be augmented with very basic tools like calculators to minimize such trivial hallucinations. I say this as someone rooting for Anthropic.

[jasondclinton]

LLMs are building blocks and I’m excited about folks building with a concert of models working together with subagents.

[virgildotcodes]

Hey Jason, checked your HN bio and I don't see a contact. Found you on twitter but it seems I'm unable to DM you.

Went ahead and uploaded the image here: https://imgur.com/pJlzk6z

[samstave]

An "LLM crawler app" is needed -- in that you should be able to shift Tokenized Workloads between executioners in a BGP routing sort of sense...

Least cost routing of prompt response. especially if time-to-respond is not as important as precision...

Also, is there a time-series ability in any LLM model (meaning "show me this [thing] based on this [input] but continually updated as I firehose the crap out of it"?

--

What if you could get execution estimates for a prompt?

[jasondclinton]

Thank you!

[uptownfunk]

What a joke of a response. No one is asking for emergent calculation ability just that the model gives the correct answer. LLM tools (functions etc) is old news at this point.