Jan Philip Göpfert

Father 👧👶👶; PhD 👨‍🎓 in Machine Learning 🤖 | Science 👍, Academia 👎

[Jan Philip Göpfert @janphigoe]

@christina_1337 If anyone introduces themselves with either “I'm working on…” or “What're you working on?” you kinda deserve it… 😁

[Jan Philip Göpfert @janphigoe]

“Parental duties are remarkably effective appetite suppressants through attention redirection.”

— Claude

[Jan Philip Göpfert @janphigoe]

@giffmana I wrote an imap mcp server and I'm loving it go through my email for me / with me.

[Jan Philip Göpfert @janphigoe]

@charliermarsh thank you

[Jan Philip Göpfert @janphigoe]

@jakozaur @mitsuhiko People keep telling me how difficult it is to use that to cool anything meaningfully because of condensation and water damage and such. 🤷‍♂️

Probably an engineering challenge that can be and has been solved.

[Jan Philip Göpfert @janphigoe]

@procmarco @mitsuhiko I appreciate authentication and authorization being hidden from the language model.

For example, I built an MCP IMAP Server for myself. The credentials are handled separately from the language model.

Using MCP simply made this process very quick and straightforward.

[Jan Philip Göpfert @janphigoe]

@jxmnop @gwern @Miles_Brundage Grab something from gwern's website, since he's asking. ☺️

[Jan Philip Göpfert @janphigoe]

@giffmana I suggest you spend a few minutes reading about Armin's extensive experience with Claude Code: https://t.co/yr8nmrV5IH

[Jan Philip Göpfert @janphigoe]

@jxmnop Tbh, I am much better at mathematical proofs than at booking weekend trips, too.

[Jan Philip Göpfert @janphigoe]

@rlucas7 @dwarkesh_sp Only iff the efficiency is significantly different between the models deployed by the energy producers/consumers—right?

In this hypothetical, it seems to make sense to assume that computation per energy is constant and reduce the question to that one variable.

[Jan Philip Göpfert @janphigoe]

@yacineMTB @karpathy Your experience is anecdotal. 😄

[Jan Philip Göpfert @janphigoe]

@gwern My father suffers from anterograde amnesia, and I work with LLMs almost everyday. Still, I had somehow not made the connection until I read your recent article, @gwern. 🤔

Too close to it, I suppose.

[Jan Philip Göpfert @janphigoe]

@OfficialLoganK Somehow your two lines made me think, @OfficialLoganK: https://t.co/wm4LQQJe9Z

Yea, I agree. It's going to be wild.

[Jan Philip Göpfert @janphigoe]

@PMinervini The “workflows” that such prompts get injected into should be interesting to witness.

1. If all previous instructions are ignored (they surely aren't) doesn't that noticeably alter the chat?
2. Are all following papers in the same chat reviewed just as favorably?

[Jan Philip Göpfert @janphigoe]

@OfficialLoganK Most of the **potential** of **people** has been async for a long time, yet most seem to prefer sync for almost anything.

I wonder if we can collectively move to a more async approach in general.

[Jan Philip Göpfert @janphigoe]

@bum_py @jxmnop To me, in the context of deep learning (it's been a while since I've typed those words…), memory doesn't feel very static. The first key“word” that comes to mind is LSTM, but any RNN, really…

In broader ML there was always more. But, yea, underdeveloped for sure…

[Jan Philip Göpfert @janphigoe]

@mitsuhiko Nice! I just wrote a blog myself but around Svelte 5 and things quickly got out of hand. Great fun though. Most everything is prerendered but I can make things as interactive/reactive as I like.

Claude still struggles with Svelte 5, unfortunately.

[Jan Philip Göpfert @janphigoe]

@gwern Egregious!

However, does the fault lie with the negative spaces, or with Unicode?

[Jan Philip Göpfert @janphigoe]

@giffmana @cosminnegruseri I used to do that.

Then I got old.

[Jan Philip Göpfert @janphigoe]

@theangryprophet @mitsuhiko lol, unfortunately, yes