Thibedi Rapoo (@thibedi_r) 's Twitter Profile
Thibedi Rapoo

@thibedi_r

Augmenting Call Centres with AI

ID: 826373907087253508

linkhttp://www.vanine.co.za calendar_today31-01-2017 10:17:47

43 Tweet

76 Takipçi

236 Takip Edilen

David Shapiro ⏩ (@daveshapi) 's Twitter Profile Photo

One of the best points that someone made to me once was this: "Humans generalize on far less data than AI currently does. That means there's something our brains are doing algorithmically to do far more with far less data. Until we figure out that paradigm, we are no where near

Thibedi Rapoo (@thibedi_r) 's Twitter Profile Photo

I’m currently building a pseudonymization workflow for Vanine. Creating a workflow that consistently identifies and replaces named entities or any personal identifiable information in call transcripts with pseudonyms has such an overlooked & underrated level of difficulty

ₕₐₘₚₜₒₙ (@hamptonism) 's Twitter Profile Photo

Networking is overrated- No matter how isolated you are and how lonely you feel, if you do your work truly and conscientiously, unknown friends will come and seek you. - Carl Jung

Hensen Juang (@basedjensen) 's Twitter Profile Photo

Lol they basically made H800 work same as H100 by dropping down to ptx and allocating sm units to get around nerfed link speed. Fucking brilliant

Amjad Masad (@amasad) 's Twitter Profile Photo

It’s amazing that no model has caught up with Claude on coding. Even if they look good on benchmark they’re still not as good at generating working good looking modern web apps. Whatever magic Anthropic did seems very durable.

Andrej Karpathy (@karpathy) 's Twitter Profile Photo

There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper

Thibedi Rapoo (@thibedi_r) 's Twitter Profile Photo

Doing for call centres what: • GPS did for driving - augmenting drivers • Autopilot did for flying - augmenting pilots • Algorithms did for trading - augmenting traders • Spellcheck did for writing - augmenting writers Building AI that augments humans in complex task.

Andrej Karpathy (@karpathy) 's Twitter Profile Photo

Products with extensive/rich UIs lots of sliders, switches, menus, with no scripting support, and built on opaque, custom, binary formats are ngmi in the era of heavy human+AI collaboration. If an LLM can't read the underlying representations and manipulate them and all of the

Koshiek Karan (@iamkoshiek) 's Twitter Profile Photo

the financial collapse of the SABC destroys sports in so many ways one of the greatest social equalisers is now exclusive, inaccessible & expensive the loss is bigger than money

ᴅᴀɴɪᴇʟ ᴍɪᴇssʟᴇʀ (@danielmiessler) 's Twitter Profile Photo

The problem with Apple‘s computers don’t reason paper The problem with the argument that AI cannot reason because they are just token manipulators is that the same exact thing applies to the human brain. You could easily say that it is nothing but a collection of neurons that

kwindla (@kwindla) 's Twitter Profile Photo

The team at Speechmatics just shipped a really clean integration of realtime speaker diarization for voice agents. I've tinkered quite a bit with multi-speaker voice agent pipelines, and this is the best implementation I've seen so far. Voice AI in 2025 is at a really