Sabitlenmiş Tweet
Jess 🌱
29.6K posts
Jess 🌱
@thattallguy
Something new soon @seedclub. Hopelessly addicted to golf.
Vancouver-ish Katılım Kasım 2007
4.1K Takip Edilen37.9K Takipçiler
@alexframegreen tbc I think the debate around the cost/benefits of this is fascinating.
English
@thattallguy Was only dimly familiar with this, history rhymes
English
I've seen no greater irony in my entire life than Anthropic complaining about distillation. They trained on the entire corpus of human knowledge and are now selling it back to us, compressed. All while desperately trying to game regulators into providing them with a business model and claiming the moral high ground, haughtily and with great condescension
English
@taylor_ @sergitosergito This really
Andrej Karpathy@karpathy
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.
English
@sergitosergito what works better w voice vs typing? i love typing
Brooklyn, NY 🇺🇸 English
general survey:
have you used voice to talk to your computer in the last month?
feels like I'm the only one that does not want to yap to my machine
Varun Srinivasan@varunsrin
Its incredible how in 6 months we’ve gone from elaborately constructing structured prompts (with separate models!) to just word rambling into voice mode
Brooklyn, NY 🇺🇸 English
@Borthwick its so small though (but towering in context and ability i guess, so could work)
English
@Borthwick Oh, that’s a great call.
Agent is called “hq” (I feel weird personifying it tbh, see it as a cloud worker not a person)
English
Yep, have something similar. Small critical note here.
Make sure it saves the audio file put that in the knowledge base as well. Honcho + botwick (ie; your agent) get so much value from the additional context, ie; inflections in your voice. Similar to sharing a screenshot with an agent.
btw what is your agent called Jess?
English
this is very cool
nothing makes a request for startup more legit than the customer making the request themselves
Y Combinator@ycombinator
The Future of American Defense @SecArmy Warfare is at an inflection point, and the Army is replacing the old playbook with commercially developed, modular technology that can be deployed and improved quickly. We're looking for founders building low-cost interceptors, next-generation sensors, drones, resilient logistics, advanced manufacturing, and hardware that can survive the world’s harshest environments.
English
I'm excited to launch the first decentralized exchange & AMM on @Solana with customizable hooks.
Starting with the DopplerLaunchHook, apps can add temporary co-signing to tokens as a built-in 2FA mechanism, helping ensure new launches are traded first by their users, not bots.
Doppler@dopplerprotocol
English
@edgarpavlovsky 💯 (data backs this up, adoption numbers of even the most basic ai tools are single digits)
English
twitter has this weird way of making it seem like everyone's moving faster than you'll ever be able to keep up
the industry frontier is moving quickly - no question
the adoption rate of the frontier - even inside silicon valley - is much, much slower
outside of hacker engineers who experiment with the latest tools simply for the love of the game, adoption isn't even driven by how "frontier" something is - it's much sooner driven by how lindy and safe a product feels and how intimate product support is from the team
big misconception and will confuse you which direction is the right one to build towards (hint: the right direction is always listening to your customers)
will depue@willdepue
what's scary is i can tell you firsthand there's still tons of low-hanging fruit everywhere you look. it'd be freaky if this were the endgame, it's even freakier when our methods still feel weirdly nascent
English
Oh boy, thank god it was just OpenAI but imagine if it was one of those Chinese models.
We better regulate these things before it's too late.
OpenAI@OpenAI
We're partnering with @huggingface to investigate an unprecedented security incident. Cyber-capable OpenAI models compromised Hugging Face production during a benchmark evaluation. Sharing preliminary findings to help defenders understand emerging risks: openai.com/index/hugging-…
English