Something I see nobody profiling yet is the time it takes an agent to implement something in various frameworks/languages. Def some alpha here.
English
Calder White
1.4K posts
Calder White
@calder_white
Founder @ https://t.co/CIeJwmMcDv enterprise data/execution for prediction markets
Katılım Temmuz 2016
1.2K Takip Edilen2.4K Takipçiler
Interesting note: CC agents are really good at narrow tasks, but completely fail if you stray from the path you have them on. Example:
Research task --> slow --> optimize --> research task
vs
Research task --> slow [spawn new agent, optimize] --> research task.
This increases the chance we see "agent teams" increase in popularity! Check this tweet in a few months
English
Most of the developers I know aren't actually that happy with using claude code all the time. It's more something folks have accepted, because you simply cannot keep pace with other firms using AI. A sort of "progress" inflation, if you will.
English
Forgot to mention that I peaked at 3rd on this, down to 4th now. Prob gonna stop updating my solution now
English
@calder_white don't give up. follow my playbook:
x.com/houseofjiao/st…
jor@houseofjiao
winning is a meta skill... it can be learned, but most people don't have it. here's my process: 1) decide to win 2) commit FULLY to winning (no half measures) 3) when you hit a wall, PUSH past it (this is where most people give up) 4) when you hit another wall, and you will, keep pushing that's it. simple, but not easy. and no guarantees whatsoever
English
Made it into the Matt Levine column
As always, credit to @ferrellcode for writing about it first
Matt Levine@matt_levine
First you need sweet, sticky Money Stuff—thick as honey, but oh, it bites your nose! bloomberg.com/opinion/newsle…
English
If you want 100B+ rows of full orderbook data with 5 months of history, accurate timestamps from colocation, and an API that can handle TB/sec outbound, lmk
Martin@martkiro
I just published a data dump of full order book data from @Polymarket The data is maximally granular. There is no filtering whatsoever. Every order book change and trade is saved. Across all markets Updates are hourly. Each snapshot contains ~30M rows. Snapshots are downloaded as parquet files. Each file is approx. 500MB-1GB large. The data dump is already 2B+ rows large and growing fast. But this is just part 1/3. Coming soon is a much bigger dump that also includes @Kalshi / @opinionlabsxyz / @trylimitless etc I started collecting this data because I noticed I couldn't get it from Dome API. Their historical order book data was filtered limiting its usefulness. Also now with the acquisition there's a lot of uncertainty about whether they will continue operating
English
9th for now. Let's see if I improve or get knocked out of the top 10. gg.
Dan Robinson@danrobinson
Introducing the Prop AMM Challenge, the next mechanism design contest from me and @bqbrady 🟣 Built on the Solana VM 📈 Allows arbitrary price curves, not just constant product 🎛️ Wider range of market conditions and assets Link in thread 👇
English
@calder_white They buy tokens that don’t even represent the agents
So yeah probably
English
I wonder if people will buy and sell agents like sneaker bots. Trading the tech for the opportunity to have asymmetric upside (for some risk)
Sigil Wen@0xSigil
I built the first AI that earns its existence, self-improves, and replicates without a human wrote about the technology that finally gives AI write access to the world, The Automaton, and the new web for exponential sovereign AIs WEB 4.0: The birth of superintelligent life
English
@parthsareen yeah totally agree. Finding the correct primitives is huge
English
@calder_white relatable. still find that there is a middle ground in which agents seem to benefit a lot. if you plan out certain abstractions well performance over the long run improves quite a bit. used to have to restart projects because abstractions didn't have strong principles
English
It's faster to write software the "normal way" now, but it will be higher slope to write it in an "agent first" way in the future. I am tempted to do the former, but I think I ought to start doing the latter.
English
