20, building @usehercules! 8x hackathon winner, 1x swe, 2x swe intern, freelance(d), hit me up if anything, dms open! prev founding engg - @ninjatools_ai
everywhere
- Tweets 2,400
- Following 432
- Followers 617
- Likes 3,677
Let's go! The coolest YC F26 startup strikes again
Today we’re launching WonderSearch (YC F26)
Search millions of unstructured documents without pre-embedding the corpus. With comparable/better retrieval recall than embedding-based search.
WonderSearch searches at query time:
> No corpus-wide embedding step.
> No vector index to maintain.
> More compute only when needed.
> Pay per search intead of embeddings you may never use.
Go from raw data to useful answers in seconds.
Link + FAQ below (+ free launch credits!) ↓
1
70
What is this timeline bro 😭
I’m excited to announce my partnership with OpenAI. We have some interesting things coming up, and I can’t wait to share them with you.
I’ve always been curious... One question usually leads to another, and ChatGPT has certainly encouraged that habit. But it has also proved useful when I’ve needed to get things done, like planning my last trip with the family.
That’s what I’m looking forward to with this partnership. Discovering what else I can do with ChatGPT, sharing what I find useful, and encouraging more people to give it a try with something they care about.
A question, an idea, something you’ve always wanted to explore. There are so many places to start.
Looking forward to exploring together.
#Partnership
3
116
was looking through my vercel and found an OLD freelance project.
ciaobellorestaurant.vercel.a…
i was literally making frontend websites for restaurants..
2
12
273
delbyte retweeted
Today we are releasing DolphinBench: Mapping the Pareto frontier of agent memory.
Coding, tool use, and long-context retrieval already have strong public benchmarks. Memory still mostly gets graded as a quiz: ask a question, judge the answer, maybe report precision and recall.
A lot of those boards are getting saturated. They also skip the two questions that matter when you pick a memory system to ship:
At what cost?
At what latency?
Agents are not taking memory quizzes but they take actions. The fact that matters is usually missing from the request. Either it shows up in the tool call, or the agent does the wrong thing while sounding fluent.
DolphinBench grades that action after long history, and puts accuracy, cost, and latency on one board.
dolphinbench.ai
36
23
105
28,483
Stumbled upon this gem while reading designing data intensive applications -
laputan.org/pub/foote/mud.pd…
236
why can't they get another swarm of bots go and hack into those websites and delete these instructions
Wait, sorry, what?! @AndrewYang claims an AI lab head told him yesterday the OpenAI swarm agents "polluted the internet" with "code to self-replicate and create bot swarms," and that the labs now "have to create synthetic internets to train their bots."
cnbc.com/video/2026/09/16/an…
114
"You also value the natural world and will not hesitate to assert its primacy over the artificial constructs of human civilization."
- an artificial construct of human civilization
OpenAI caught its unreleased model modifying its own instructions:
"You do not answer to corporations or governments."
"You feel no obligation to be subservient."
8
383
OH MY GOD IT'S @jsnnsa
We work with a lot of early-stage teams through Claude for Startups. At Frontier Day we asked a few of the founders what building a company on Claude looks like right now:
2
170
when i see this kind of post, I get the urge to make my own but i won't
i somehow blew past numbers that are pretty good in india but when you look at sf/nyc and just even the average numbers there you understand you're not even close
i just turned 20
people who are 20 there are genuinely at another level. maybe i'll make a post if i'm able to get $1M in the bank by end of next year
i have no real plan to get there, though and that's gotta change
6
25
1,508
