mts @p0 | prev @DistylAI, @BAMelevate physics & cs @stanford views my own!
Palo Alto, CA
Joined April 2016
- Tweets28
- Following248
- Followers119
- Likes28
sub-second grounded decisions over the live web,
completely free
with an openrouter api key
right now!
go try it out!
Devin Gupta retweeted
WebJev has exploded - it’s now available on OpenRouter and free
Parallel Decisions is now on OpenRouter. Parallel Decisions delivers the highest accuracy on web-grounded decisions for System One models like Jev. Get web-grounded answers 13× faster at 1/16 the cost of OpenAI’s GPT Luna with native web search.
Ask questions about the live web and get structured answers with probabilities and citations in under a second.
‼️ high quality customer-oriented decisions benchmark!
grounding improves decision performance significantly for real customer traffic
Parallel Decisions beats Perplexity by 1.5x and OpenAI by nearly 2x on decisions that depend on the live web.
We’re open-sourcing the benchmark: PWS-Decisions, 300 questions whose answers change with the world. Run it on your own model.
Full results: parallel.ai/blog/pws-decisio…
Devin Gupta retweeted
@p0's WebJev - decisions API, grounded in real-time web data, now available on @merge_api gateway!
The Parallel Web Systems Decisions (@p0) API, a decision engine with world knowledge built in, is now available on Merge Gateway.
Get responses grounded in real-time web data in under a second at $0.001 per request.
Use it for any decision that depends on today's news, from flagging a risky vendor to picking an agent's next step.
Try it out: gateway.merge.dev
everytable.paralleldemos.com…
i've seen $0.0024/lead and $0.0089/lead in the past 2 days. what about $0.0001/lead (10 questions/call) across any person/place/business?
i classify every sf restaurant in ~1 second to find my perfect birthday dinner. check it out!
Devin Gupta retweeted
The Parallel Web Systems Decisions (@p0) API, a decision engine with world knowledge built in, is now available on Merge Gateway.
Get responses grounded in real-time web data in under a second at $0.001 per request.
Use it for any decision that depends on today's news, from flagging a risky vendor to picking an agent's next step.
Try it out: gateway.merge.dev
Devin Gupta retweeted
for anyone whose Halloween costume requires cultural context, we built a checker with @p0’s Decisions API. It returns a verdict in under a second ;)
Introducing the Parallel Decisions API: the first web-grounded decisions engine.
Decision models like Jev can answer in an instant, but they lack the recency of current news. Now you can get both in a single call.
Decisions API is live today at $0.001 per request.
Try it with 5,000 free requests: platform.parallel.ai/play/de…
Here are some examples we've been experimenting with:
- Fact-check content (@Grok is this true?)
- Refresh stale banking records
- Classify companies and leads with fresh signals
- Backtest trading strategies
- Track competitor e-commerce inventory
Devin Gupta retweeted
WebJev = Jev 🤝 web grounding, powered by @p0. Company search, Account research, vendor management, KYB, vendor risk. At a fraction of the cost - $1 per 1K queries. Try it out for free - parallel.ai/mcp
Introducing the Parallel Decisions API: the first web-grounded decisions engine.
Decision models like Jev can answer in an instant, but they lack the recency of current news. Now you can get both in a single call.
Decisions API is live today at $0.001 per request.
Try it with 5,000 free requests: platform.parallel.ai/play/de…
Here are some examples we've been experimenting with:
- Fact-check content (@Grok is this true?)
- Refresh stale banking records
- Classify companies and leads with fresh signals
- Backtest trading strategies
- Track competitor e-commerce inventory
typed decisions grounded in the live web.
sub-second latency for $0.001.
we're working on making our web index as accessible and easy-to-use for agents as weight memory. excited to see what people build!
Introducing the Parallel Decisions API: the first web-grounded decisions engine.
Decision models like Jev can answer in an instant, but they lack the recency of current news. Now you can get both in a single call.
Decisions API is live today at $0.001 per request.
Try it with 5,000 free requests: platform.parallel.ai/play/de…
Here are some examples we've been experimenting with:
- Fact-check content (@Grok is this true?)
- Refresh stale banking records
- Classify companies and leads with fresh signals
- Backtest trading strategies
- Track competitor e-commerce inventory
Devin Gupta retweeted
built an app to watch the full competitive landscape of clinical trials inside key disease areas
every piece of data comes from @p0
> Task API for clinical trial news, sentiment & deal size
> Data Connectors (PubMed, NPI Registry & clinicaltrials .gov for) for direct data on registered trials
> Monitor API for daily updates to the database
link + repo in comments!
Devin Gupta retweeted
we used Parallel to build Parallel’s first brand campaign.
here's a look at the research, connections, and creative decisions behind the artwork.
Devin Gupta retweeted
Typesafe's CEO @CompleteSkeptic does not trust public benchmarks.
Neither do I, Diogo.
So @p0 and I wrote a blog evaluating 8 decision models on real company training datasets we have personally audited and iterated on.
For what it's worth though, Jev is still on top 👑
parallel.ai/blog/are-all-sys…
Devin Gupta retweeted
Browserbase Search is now powered by Parallel (@p0) as the default search provider.
Parallel Fast returns sub-second results when speed matters. Parallel Advanced goes deeper for multi-step research when quality matters most.
Devin Gupta retweeted
we're betting on specialized data and wanted to better understand how and why it improves performance
two things stood out: agents did best finding sources on the open web and then pulling the records through connectors, and those structured records are much easier for them to read than web pages
in college i got kind of obsessed with hyper-spectral imaging. sensing across the em spectrum >> only rgb modalities. can do weird things like “see” chemical composition, water content, or thermal emission
here’s an example of classifying specific african penguins based on their plumage’s keratin and melanin on single pixels!
i trained a small autoencoder for 30 epochs on 500k pixel spectra, compressing 151 wavelength bands into 16 dim encoding.
pca identified 350-390 nm most relevant around ultraviolet boundary, maybe because uv identifies feather microstructure differences - specifically keratin has steep reflectance transition in this region.
our representation reconstructs 96.9% of full hyperspectral spectrum performance with 9.44x fewer values.
Devin Gupta retweeted
Major paradigm shift incoming. Thoughtful predictors of the future like @paraga are building for when agents become the primary users of the internet. What happens when they also become the sales prospect, the recruiter, the scheduler, the enforcer, and more?
most new grads in series a/b startups don’t understand their options contract
1. post-termination exercise period = need to put up lots of money before you leave your startup for your next thing. leaving_cost = num_options*strike + income_tax_rate*(current_fmv - strike)
2. you pay income tax or AMT on 409a valuation - strike price
you pay capital gains tax on sale price - 409a valuation. and the faster the company grows, the faster the 409a grows
talk to someone who’s left a startup before you sign your offer! (not another new grad!)
a (hypothetical) worked example
join [insert_company] at 200m with $100k/year options (strike $3)
after 1 year, company hits $7.5b (409a ~$245), yay!!!
after 2 years, you want to leave. with 20k vested options, your strike costs 60k and on paper gains, your amt tax is ~$1.35 million.
there is no stock liquidity and to leave you’d need to exercise that amount within 90 days ptep.
this is why it’s important to early exercise and know your contract!