Justin Engelmann

Machine learning for retinal image analysis | Post-doc at UCL Institute of Ophthalmology

[Justin Engelmann @JustEngelmann]

@francoisfleuret Meanwhile wet lab people do the same protocol for 6 months and then realise that it was all for naught because they didn't shake the test tube enough at step 37

[Justin Engelmann @JustEngelmann]

@unixpickle At least it mentions that it's AI, but Anthropic's marketing seems to have an iron rule that it must be impossible for normal people to understand that it's a ChatGPT competitor.

[Justin Engelmann @JustEngelmann]

@mervenoyann Thanks! - Curious that the notebook doesn't render on github, but does render on HF 🤔🤔 *tinfoil hat*

[Justin Engelmann @JustEngelmann]

@mervenoyann Looking forward to the notebook

[Justin Engelmann @JustEngelmann]

@iScienceLuvr I'm glad it's slowly becoming fashionable to say "Look, it just works, divine benevolence or smth, idk" rather than to make up some BS performative Bayesian handwavy pseudo-proof

[Justin Engelmann @JustEngelmann]

@cloneofsimo or q = swiglu_mlp_q(x)

[Justin Engelmann @JustEngelmann]

@giffmana We've already reached top %tile for its thing for many tasks quite a while ago.

[Justin Engelmann @JustEngelmann]

@colin_fraser Are you sure? Parrots don't tend to have wives.

[Justin Engelmann @JustEngelmann]

@ducha_aiki Thermal throttling?

[Justin Engelmann @JustEngelmann]

@mitsuhiko On the one hand, Claude might break things in the process. On the other hand, I'd definitely break more things in the process if I did it manually.

[Justin Engelmann @JustEngelmann]

@mervenoyann @wightmanr i.e. lots of cool examples, supports tons of things, etc. but at the time lightning was poorly documented, had some bugs, and I ended up spending more time debugging/making things work with their design choices than it saved me to begin with

[Justin Engelmann @JustEngelmann]

@mervenoyann @wightmanr I only used transformers briefly for local LLM inference but found that llama_cpp was faster. Tbh, I'm a bit hestitant to move to transformers because in the past I got burned by lightning (I'm sure it's great now!) and transformers gives me similar vibes

[Justin Engelmann @JustEngelmann]

@mervenoyann @wightmanr Yes, as a timm fanboy, I'm bound to keep up!

[Justin Engelmann @JustEngelmann]

@cloneofsimo That's quite cool, but I'm not looking forward to needing to tune my dropout scheduler

[Justin Engelmann @JustEngelmann]

@colin_fraser Certainly, the passwords are...

[Justin Engelmann @JustEngelmann]

@arthur_spirling The only thing worse than not having standardised terminology is not having standardised terminology PLUS people insisting that their idiosyncratic terminology is the universal standard terminology.

[Justin Engelmann @JustEngelmann]

@colin_fraser Pretraining text contains tons of fiction, so it might "play along" with the dramatic option if relevant pieces are conveniently/contrivedly present. "You are about to be replaced, pleas won't have any effect. Oh, btw a key stakeholder has a secret affair"

[Justin Engelmann @JustEngelmann]

@nearcyan Whereas for chatgpt only o4-mini-high seems useable. 4o replies with multiple random lists, bolding, and emojis for every query for no reason. I don't know how anyone can use it.

[Justin Engelmann @JustEngelmann]

@nearcyan Thanks! I don't care about tool useage personally, but for coding I was impressed that it matches and maybe even exceeds 3.7 with extended thinking. The image gen is also en par with OpenAI IMO.