wpasc

pimp my agent

I'm no quant/hft/wall st person, but iiuc a lot of those trades happen in dark pools or by other means to make the positions they take hard to track. meaning you can't go get the receipts of every trade made by medallion fund nor some competitor

as a lawyer, can you speculate as to why anthropic/openai aren't facing many or any consequences for their agents? I'm not asking in a "grab the pitchforks" way. more out of genuine curiosity as my uninformed recollection of the CFAA is as you describe it.

Funnily enough, all the models are down and github statuses are all green

Look at the base of the structure on the right side, and you'll see that in the same plane there are the bumps present and bumps hidden by the same flat plane in a way they shouldn't be. then the left side, the bump visibility doesn't make lego sense

(i agree that maybe OP pointing that out is nitpicking, but to steelman the case, such inaccuracies are what code review would find and are the subtle bugs that might pass a code review and break prod)

I genuinely enjoyed the game of "where's waldo" that

> easily identifiable problems

sent me down. as soon as I parsed that line I stopped reading, and I tabbed back over to spot them

agreed on the notion that

> people are sleeping on the ChatGPT Work/Codex

just in general. I find it to be far superior (imo) for all tasks atm. Claude just overdoes things in writing, coding, architecture, etc

idk who came up with it first, but ASD-STE100 has been floating around more since matt pocock put it in one of his skills

The author notes:

> One caveat: my experience comes mainly from working on infrastructure and developer tools at large companies, on teams where engineers have a lot of bottom-up autonomy to influence their roadmaps. In a more top-down environment, there may simply be less room to work this way.

I wonder if the overall trend in tech is that engineers are experiencing less bottom-up autonomy and more top-down controlled environments. I would be curious to see how many tech companies (or the average engineer's experience) have changed from being tech led where engineers have autonomy to being more product management led. My suspicion without evidence is that the overall engineering autonomy has decreased over the years as the culture of tech has (in my opinion) shifted away from tech focus to more business, management, product focus with engineers just as the widgets who are tasked with fulfilling the goals of business, management, product.

all hypothesis, only anecdata

This is the key seam that proves the investigation.

Two things to flag:

What's wild (imo) is pretty much everyone I talk to/read from (anecdata) HATES the way claude writes. I see it in the comments on Hacker News, hear about it in discussions with my colleagues, and talk about it with my non tech family. it's over the top bad. now it seems like these quirks will now be enforced in some weird way to meet the watermarking rules?

you beat me before I refreshed the page. what would you say... you do here?

THIS IS NOT A MUNDANE DETAIL MICHAEL

not OP, but i believe the commenter is referring to how GFC in '07 had wide ranging negative effects for a lot of people who had nothing to do with investments in mortgage backed securities

thank you for this comment, "wedge" has been one of the words that has been popping up in a lot of LLM writing i've seen lately. (source: it was me asking the LLM to summarize some features in a repo! the words "load-bearing" "wedge" "spike" "crux" and plenty others have been driving me crazy)

edit: as I keep reading the paper, I keep noticing some common sentence construction patterns, stylistic choices, and other little tics that I find frustrating because they are the very same things that I've been working on a few "writing-style skills" to get rid of