Kyle Jeong
@kylejeong
644 Following 8.4K Followers
alexandr wang's poasts are his version of the "zuck glow-up". he's becoming "cool" again by just not caring what people think and being himself online.
a nightmare to comms teams across the globe, but honestly working very well for muse's distribution.
Show more
if you'd like to test this, shoot me a DM!
I built JevSearch, search the web & validate your results with Jev.
Give a query and selection criteria, use @browserbase search to get the t25 results, then Jev scores and returns the t5 results.
Jev often chooses urls outside of the initial top 5 as more relevant.
Show more
posted to our blog if you prefer to read there:
This is experimental, so we'd love feedback!
Checkout this branch to try it out:
Extract is especially interesting because Jev can’t generate text.
Instead, Jev picks the elements containing the values. Stagehand copies their text, parses numbers, and resolves URLs.
For repeated rows or cards, Jev identifies the fields in one item.
Show more
Observe uses the same selection process.
Looking for one element? Jev picks a candidate.
Looking for several? We ask whether each candidate matches, batching the questions together.
Stagehand returns the matching elements as executable actions.
Show more
For Act, we break the instruction into smaller decisions. “Type ‘San Francisco’ into the destination field” turns into:
Identify the action: fill
Identify the text: San Francisco
Choose the destination input
Then deterministic code fills the field and checks the value.
Show more
Most browser actions involve choosing among things already on the page.
Stagehand turns the page into candidates, with context like labels, headings, and table rows. Jev picks the action and Stagehand executes it.
If the choice is uncertain, we fall back to an LLM.
Show more
In early evals, we're seeing adding Jev cut median Act latency from 1.97s to 0.46s (about 4.3× faster)
Across 240 real-site task runs, success went from 85% to 95.4%.
Jev-pilled son or fly brain neural net daughter
you can build a price-monitoring tool on @browserbase in <5 minutes using fetch w proxies
running this for 3 products costs roughly $1.50 a day if i price-check every 15 minutes.
Show more
we built blazing fast computer/browser use with Jev + @Stagehanddev.
this task cost $0.001 and executed at near instant speed (in a remote browser btw)
the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand executes it.
Show more
you can turn Jev auto-regressive using a 254 token library
this uses a derivative of the original GPT-2 set (removed things like "ing" since Jev had trouble generating full words and just kept repeating itself)
it's quite limited in tokens albeit so don't mind the incoherence
Show more
i made an llm from first principles with Jev
29 yes/no questions per character: should the next key be a–z, space, comma, or period?
highest probability gets append to it, then fed the updated text back in & repeat
an autoregressive loop made out of a classifier
Show more
try fetch with proxies for hard to reach corners of the web:
you can build a price-monitoring tool on @browserbase in <5 minutes using fetch w proxies
running this for 3 products costs roughly $1.50 a day if i price-check every 15 minutes.
Show more
SF builders: I'm running a weekly pastry-powered tour of the city.
I bring a box of pastries. You talk me through the wild stuff you're building. No pitch deck. No formality. Just real engineering.
If your team is cracked enough for a drop-off, my DMs are open.
Show more
i built Scout, a small but mighty deep research agent that lives in slack.
it uses @browserbase search and fetch + proxies to reach corners of the internet agents couldn't access before.
Show more
this is the most important talk i've given in my time as a founder.
in the next twelve months, we believe that every task that humans do online will be assisted by agent.
watch this if you want to see the future that we're building for @browserbase
Show more
We’re recruiting the next generation of student founders, builders, designers, and creators at @vestucla.
Our members have raised millions, graduated from accelerators like @kp_fellows @fdotinc, and have been early employees @Etched @browserbase @interaction and more.
If you’re interested in meeting them, i’m happy to chat
Show more
