Giridhar K

Machine learning research

[Giridhar K @gkbytes]

@AravSrinivas Just make vim keybinds the default to navigate pages, tabs, results. single key access to pplx agent to type in questions, copy and paste responses.

[Giridhar K @gkbytes]

@BockLab This is interesting! Is the model served on HF or github to study the embeddings?

[Giridhar K @gkbytes]

@ManUtd Onana
Dalot Maguire Martinez Mazaroui
Mainoo Casemiro
Bruno Mount
Amad Rashford

[Giridhar K @gkbytes]

@apsarathchandar @polymtl @ChandarLab Congratulations!

[Giridhar K @gkbytes]

@Supermathie @dustychipura +1 for LaTeX

[vicki @vboykis]

i'm just a girl standing in front of the ml research community please begging everyone to type their python method inputs and outputs especially if they are tensors or weird nested dicts of lists of dicts

[Marques Brownlee @MKBHD]

Good morning to everyone except whoever invented Daylight Savings time

[Alex MacCaw @maccaw]

Always worth remembering.

[Giridhar K @gkbytes]

@sh_reya @studygone2sleep

[Giridhar K @gkbytes]

@MattBMcDermott May be semantic scholar can help?
https://t.co/5QOTThUHsw
Last I checked, the search api may be limited to title, metadata and abstract.

[Giridhar K @gkbytes]

@ssgrn @Meta Congratulations, Suchin!

[Giridhar K @gkbytes]

😶 Me 1 -0 ChatGPT

[Giridhar K @gkbytes]

@_awbery_ hope you get well soon!

[Giridhar K @gkbytes]

@deliprao Great thread, I am guessing GPT took the whole CoT for performance improvements too seriously. May be the user doesn't need all the steps but those may be useful for the model to arrive at the correct code. May be hide and use extra CoT tokens for internal computation?

[Arthur Mensch @arthurmensch]

Removed, enjoy !

[Greg Brockman @gdb]

GPT-4 for radiology. Far from perfect, but state-of-the-art performance on some tasks: “Surprisingly, we found radiology report summaries generated by GPT-4 to be comparable and, in some cases, even preferred over those written by experienced radiologists”
https://t.co/bi6RwqgeHw

[Giridhar K @gkbytes]

If llama2 needs a license, do _versions_ of llama2 (quantized, instruction tuned etc ) also need the meta license?

cc @MetaAI @karpathy

[Giridhar K @gkbytes]

something that's more productive.

[Giridhar K @gkbytes]

While this could be interpreted as bad news, being a user/answerer of SO and stackexchange as a student earlier on in my career, I believe the surge of LLMs will relieve quite a lot of stress from beginner coders.
For every good SO question there could possibly be more than 100s

[Mahesh Sathiamoorthy @madiator]

This makes me sad:
https://t.co/j7W5RiBYkA

[Giridhar K @gkbytes]

of duplicates asked by beginner users who will be hunted down by the mods for a variety of reasons (duplicates, rewording, not adhering to the pastebin guidelines, laTeX formatting, writing in CAPS, vague descriptions, ). The mods/users now can focus on a different work, perhaps