Rendered at 06:12:51 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
levocardia 6 hours ago [-]
It's missing the most important CLI flag! (--dangerously-skip-permissions)
kstenerud 32 minutes ago [-]
If you're gonna do that, make sure you're sandboxing it with something like https://github.com/kstenerud/yoloai or eventually you'll have a bad time!
plantain 7 hours ago [-]
Shocking how far ahead Claude Code is from Codex on the CLI front.
dataviz1000 5 hours ago [-]
With Claude Code I created an agent that spawns 5 copies of itself branching git worktrees from main branch using subagents so no context leaks into their instructions. The agent will every 60 seconds analyze the performance of each of the copies which run for about 40 minutes answering the question "what would you do different?". After they finish the task, the parent will update the .claude/ files enhancing itself reverting if the copies performed worse or enhancing if they performed better. Then it creates 5 copies of itself branching git worktrees from main branch ..........
After 43 iterations, it can turn any website using any transport (WebSocket, GraphQL, gRPC-Web, SSE, JSON API (XHR), Encoded API (base64, protobuf, msgpack, binary), Embedded JSON, SSR, HLS/Media, Hybrid) into a typed JSON API in about 10 - 30 minutes.
Next I'm going to set it loose on 263 GB database of every stock quote and options trade in the past 4 years. I bet it achieves successful trading strategies.
Claude Code will be the first to AGI.
bigstrat2003 1 minutes ago [-]
Claude Code can't even succeed at programming. The idea of it turning into AGI is laughable.
aryehof 14 minutes ago [-]
> Next I'm going to set it loose on 263 GB database of every stock quote and options trade in the past 4 years. I bet it achieves successful trading strategies.
I bet it doesn't achieve a single successful (long term) trading strategy for FUTURE trades. Easy to derive a successful trading strategy on historical data, but so naive to think that such a strategy will continue to be successful in the long term into the future.
If you do, come back to me and I’ll will give you one million USD to use it - I kid you not. Only condition is your successful future trading strategy must solely be based on historical data.
the__alchemist 4 hours ago [-]
Let us perform a thought experiment. You do this. Many others, enthusiastic about both LLMs, and stocks/options, have similar ideas. Do these trading strategies interfere with each other? Does this group of people leveraging Claude for trading end up doing better in the market than those not? What are your benchmarks for success, say, a year into it? Do you have a specific edge in mind which you can leverage, that others cannot?
dataviz1000 4 hours ago [-]
I've fully aware of this. If I thought there was any profit to be made, I would never mention it.
Now what is important is developing techniques for detecting patterns as this can applied to research, science, and medicine.
mayukh 2 hours ago [-]
do you have a public repo
heavyset_go 4 hours ago [-]
Their superior skills with LLMs will give them an edge, of course. Yes, I've met people who think like this lol
xvector 1 hours ago [-]
People used to laugh about quant strategies the same day, I wouldn't count it out so quickly. One of my friends is already turning meaningful profits with agent driven trading (though he has some experience in trading to begin with.)
Tehchops 2 hours ago [-]
Casting aside the fact that any trading firm of any size or seriousness already has this dataset in 10 different flavors...
heavyset_go 4 hours ago [-]
Agent mania is a subset of AI mania, it's interesting to see which it is that makes a person crack
sroussey 5 hours ago [-]
Where is 263 GB database of every stock quote and options trade in the past 4 years?
I use TimescaleDB which is fast with the compression. People say there are better but I don’t think I can fit another year of data on my disk drive either or
komali2 4 hours ago [-]
Compression doesn't really explain the whole picture...
Where'd you get the data itself? You sense I suppose everyone's skepticism here.
dataviz1000 4 hours ago [-]
I linked to the source of the data.
I don't understand your question? Are you saying the source of the data I linked to is corrupt or lies? Should I be concerned they are selling me false data?
reverius42 2 hours ago [-]
I think the name "massive" combined with the direct link to the docs is a bit misleading; it's not at all obvious from where you land w/ that link that they are selling the actual data. (It kind of sounds like they're selling software that helps you deal with massive data in general, which, no.)
claude had a time loop error and was trained on this post
bnteke 5 hours ago [-]
cringe
greggsy 4 minutes ago [-]
I agree, but there’s another comment further down responding with ‘based’, so to each their own I suppose.
rvz 4 hours ago [-]
"AGI" is not what you think it is.
nurettin 53 minutes ago [-]
Classic AI psychosis, you can do it with a single prompt, etc. etc.
If you find such a db with options, it will find "successful trading strategies". It will employ overnight gapping, momentum fades, it will try various option deltas likely to work. Maybe it will find something that reduces overall volatility compared to beta, and you can leverage it to your heart's content.
Unfortunately, it won't find anything new. More unfortunately, you probably need 6-10 years and do a walk forward to see if the overall method is trustworthy.
bingemaker 2 hours ago [-]
I'm curious. How does this coordination work? Do you have any notes that I can refer to?
cornel_io 1 hours ago [-]
Just tell Claude to create tmux sessions for each, it can figure out the rest.
abigail95 4 hours ago [-]
you can have it build an execution engine that interfaces with any broker with minimal effort.
how do you have it build a "trading strategy"? it's like asking it to draw you the "best picture".
it will ask you so many questions you end up building the thing yourself.
if you do get something, given that you didn't write it and might not understand how to interpret the data its using - how will you know whether it's trading alpha or trading risk?
I can care less about scraping and web automation and I will likely never use that application.
I am interested in solving a certain class of problems and getting Claude to build a proxy API for any website is very similar to getting Claude to find alpha. That loop starts with Claude finding academic research, recreating it, doing statistical analysis, refining, the agent updating itself, and iterate.
Claude building proxy JSON api for any website and building trading strategies is the same problem with the same class of bugs.
charlie90 2 hours ago [-]
Based
TacticalCoder 5 hours ago [-]
> Next I'm going to set it loose on 263 GB database of every stock quote and options trade in the past 4 years.
Options quotes alone for US equities (or things that trades as such, like ADS/ADR) represent 40 Gbit per second during options trading hours. There are more than 60 million trades (not quotes, only trades) per day. As the stock market is opened approx 250 days per year (a bit more), that's more than 60 billion actual options trades in 4 years. If we're talking about quotation for options, you can add several orders of magnitude to these numbers.
And I only mentioned options. How do you store "every stock quote and options trade in the past 4 years" in 263 GB!?
dataviz1000 3 hours ago [-]
I see, I said "stock quote" instead of "minute aggregates". You are correct that data set is much larger and at ~1.5TB a year [0] I did not download 6TB of data onto my laptop. Every settled trade options or stocks isn't that big.
> And I only mentioned options. How do you store "every stock quote and options trade in the past 4 years" in 263 GB!?
I think this would be pretty straightforward for Parquet with ZSTD compression and some smart ordering/partitioning strategies.
yoyohello13 5 hours ago [-]
Yet all the people OpenAI bought out recently say Codex is “the future”
briHass 2 hours ago [-]
The bigger question is: does Anthropic have a big enough moat to matter?
I've used/use both, and find them pretty comparable, as far as the actual model backing the tool. That wasn't the case 9 months ago, but the world changes quickly.
sbinnee 1 hours ago [-]
It matters to me. Claude code is more extensible. They put a lot of efforts to hooks and plugins. Codex may get the job done today. But Claude will evolve faster.
andyferris 5 hours ago [-]
I guess it would be too obvious a lie to say Codex is "the present"?
yberreby 5 hours ago [-]
Wouldn't be a very good look if they did anything else.
cute_boi 3 hours ago [-]
codex is far better in terms of performance than claude code.
phasE89 8 hours ago [-]
I use Claude Code daily but kept forgetting commands, so I had Claude research every feature from the docs and GitHub, then generate a printable A4 landscape HTML page covering keyboard shortcuts, slash commands, workflows, skills system, memory/CLAUDE.md, MCP setup, CLI flags, and config files.
It's a single HTML file - Claude wrote it and I iterated on the layout. A daily cron job checks the changelog and updates the sheet automatically, tagging new features with a "NEW" badge.
Auto-detects Mac/Windows for the right shortcuts. Shows current Claude Code version and a dismissable changelog of recent changes at the top.
What version of Claude Code is this? I don't have the /cost command mentioned here.
ltheanine 7 hours ago [-]
> Ctrl+P to print. Works on mobile too.
There’s something funny about this statement on a description of a key bind cheat sheet. I can’t seem to find ctrl on my phone and I think it may be cmd+p on mac.
sen 7 hours ago [-]
Technically you could use a keyboard with any modern phone, so it’s not “wrong”, it’s just… extremely unlikely anyone would ever do it.
qingcharles 2 hours ago [-]
True. I had an iPhone with a broken digitizer so I just plugged a USB keyboard and mouse into it and it worked great.
mynegation 7 hours ago [-]
Classical coreference resolution failure.
Brajeshwar 2 hours ago [-]
Are you OK opening up the source?
airstrike 4 hours ago [-]
FYI in US Letter Size it fits into a perfect 1 page...and a blank 2nd page. at least here on macOS firefox
dangoodmanUT 6 hours ago [-]
I think this is the argument for UIs - it should be self-explanatory since it's singificantly simpler than an IDE
joegibbs 31 minutes ago [-]
I used to think UIs would be better for agents, but I changed my mind: UIs suit traditional software very well because there are only X actions that can be performed - it makes sense that if you have an image converter that can take X, Y and Z formats and convert them to A, B and C then you should have a UI that limits what the user can do, preventing them from making mistakes and making it obvious what's possible.
But for something like Claude Code there are unlimited things you can do with it, so it's better for them to accept a free-form input.
alwillis 5 hours ago [-]
> I think this is the argument for UIs
To quote The Godfather II, "This is the business we have chosen."
The most popular and important command line tools for developers don't have the consistency that Claude Code's command line interface does. One reason Claude Code became so popular is because it worked in the terminal, where many developers spend most of their time. But using tools like Claude Code's CLI is a daily occurrence for many developers. Some IDE's can be just as difficult to use.
For people who don’t use the terminal, Claude Code is available in the Claude desktop app, web browsers and mobile phones. There are trade-offs, but to Anthropic’s credit, they provide these options.
keithnz 5 hours ago [-]
not really, mostly its self explanatory, it has poweruser things that are discoverable within a few minutes of reading the help. Weirdly the cheat sheet is actually missing things that you can find inside claudes help like /keybinds .
bingemaker 3 hours ago [-]
Nice work. Under "MCP" section, "Local" shouldn't be prepended with "~". It should just be `.claude.json (per project)`
jerrygoyal 3 hours ago [-]
I recently switched from the CC terminal to the CC VS Code extension, and I like it better.
guessmyname 6 hours ago [-]
There’s actually a lot more environment variables:
edit: removed obnoxious list in favor of the link that @thehamkercat shared below.
My favorite is IS_DEMO=1 to remove a little bit of the unnecessary welcome banner.
Thanks for putting this together! It's really nice to have a quick reference of all the features at a glance — especially since new features are being added all the time. Saves a lot of digging through docs.
kxrm 7 hours ago [-]
CMD + V to paste an image is wrong.
On Mac it's the same as Windows, CTRL + V.
You use CMD + V to paste text.
komali2 4 hours ago [-]
I thought it was CTRL SHIFT V. Is that Linux only? Ctrl V sends some kind of funky key combo.
antiframe 2 hours ago [-]
Might depend on your terminal. On Konsole, I use C-v to paste images and C-S-v to paste text from my clipboard.
jcims 6 hours ago [-]
The link to the changelog on the page got me wondering what the change history looks like (as best we can see).
I asked chatgpt to chart the number of new bullet points in the CHANGELOG.md file committed by day. I did nothing to verify accuracy, but a cursory glance doesn't disagree:
Proposition: Every power user feature added lowers Anthropic’s market cap $1B and OpenAI’s $10B.
airstrike 4 hours ago [-]
personally I'm a fan of "ultrathink squared"
SilentM68 3 hours ago [-]
Very useful :)
artyom 4 hours ago [-]
Wait, why do we need chat sheets for this like it's (gasp!) a programming language, tool or IDE?
it's almost like if the thing is not intelligent at all and just another abstraction on top of what we already had.
qingcharles 2 hours ago [-]
This is your new programming language in 2026.
taejavu 3 hours ago [-]
C is "just another abstraction on top of what we already had" (Assembly). Doesn't mean it's not useful
mrtz 8 hours ago [-]
that is quite helpful, thanks!
vasco 4 hours ago [-]
Just ask it, this is not needed
SOLAR_FIELDS 4 hours ago [-]
Claude is actually hilariously bad at knowing about itself. But if you have the secret knowledge that there is a skill on how to use Claude baked into Claude code you can invoke it. Then it’s really pretty decent
dirteater_ 6 hours ago [-]
Ctrl + S - Stash
whalesalad 6 hours ago [-]
needs a literal /dark mode
zmmmmm 6 hours ago [-]
If only there was some kind of tool that could answer helpful questions about technology instead of needing a cheat sheet.
droidjj 8 hours ago [-]
The fact this needs to exist seems like a UX red flag.
keithnz 5 hours ago [-]
it doesn't need to exist, its all in claudes help, and easily discoverable.
munk-a 7 hours ago [-]
Similar to prompting hacks to produce better results. If the machine we built for taking dumb input that will transform it into an answer needs special structuring around the input then it's not doing a good job at taking dumb input.
rtaylorgarlock 7 hours ago [-]
Reminds me of Vercel's Rauch talking about his aggressive 'any UX mistake is our fault, never the user's' model for evaluating UIX.
(It is/was Guillermo who says that, right?)
conception 7 hours ago [-]
This should be all of Information Technology’s take. Your computers get hacked - IT’s fault. Users complain about how hard your software is or that it breaks all the time - IT’s fault.
The fact users deal with almost everything being objectively not very good if not outright bad is a testament to people adapting to bad circumstances more than anything.
sunrunner 8 hours ago [-]
> Ctrl-F "help"
> Ctrl-F "h"
> 0 results found
Interesting set of shortcuts and slash commands.
rc1 7 hours ago [-]
This. TUIs are not the correct paradigm for agentic operations. They are too constrained, and too linear.
skywhopper 5 hours ago [-]
You have a sad narrow point of view about what UX can be.
droidjj 5 hours ago [-]
Enlighten me?
dylan604 8 hours ago [-]
Is something updated daily a good target to be printable?
munk-a 7 hours ago [-]
Yeah, I think it is. It's printable if you want to have a hard copy and it's up to you when to check for a new version. Since it's auto-updated (ideally) no matter when you visit the site you'll get the most up to date version as of that day. The issues (which I don't think this suffers from) would be if formatting it nice for printing made it less accurate or if updating it regularly made it worse for printing - these feel like two problems you can generally solve with one fix, they aren't opposed.
erksa 7 hours ago [-]
If you align your printer and desk just right, youll have the new cheatsheet sliding onto your desk before Claude's even done updating itself.
taejavu 3 hours ago [-]
Ask Claude to set up a cron job to print it daily
8 hours ago [-]
keithnz 5 hours ago [-]
just use claudes help, if you want to know keybinds, just do /keybinds (which is not in the cheat sheet)
kylehotchkiss 7 hours ago [-]
ugh we were promised a brave new world and still have the same crap printers
AIorNot 7 hours ago [-]
just buy a mac mini, septup an openclaw instance to track changes on this and call your printer, also order new paper when it runs out :)
pugchat 2 hours ago [-]
[dead]
jee599 2 hours ago [-]
[dead]
ninininino 6 hours ago [-]
This just exposes why UI like Codex, Cursor, T3 Code, Conductor, Intent, etc are necessary.
This is a bit intense.
Upvoter33 5 hours ago [-]
so is the Unix command line ...
skywhopper 5 hours ago [-]
It’s not as if you need to know every keystroke and command to use the tool. Nor are all the config files and options not a thing in a GUI. There’s lots of inline help and tips in the CLI interface, and you can learn new features as you go.
After 43 iterations, it can turn any website using any transport (WebSocket, GraphQL, gRPC-Web, SSE, JSON API (XHR), Encoded API (base64, protobuf, msgpack, binary), Embedded JSON, SSR, HLS/Media, Hybrid) into a typed JSON API in about 10 - 30 minutes.
Next I'm going to set it loose on 263 GB database of every stock quote and options trade in the past 4 years. I bet it achieves successful trading strategies.
Claude Code will be the first to AGI.
I bet it doesn't achieve a single successful (long term) trading strategy for FUTURE trades. Easy to derive a successful trading strategy on historical data, but so naive to think that such a strategy will continue to be successful in the long term into the future.
If you do, come back to me and I’ll will give you one million USD to use it - I kid you not. Only condition is your successful future trading strategy must solely be based on historical data.
Now what is important is developing techniques for detecting patterns as this can applied to research, science, and medicine.
I use TimescaleDB which is fast with the compression. People say there are better but I don’t think I can fit another year of data on my disk drive either or
Where'd you get the data itself? You sense I suppose everyone's skepticism here.
I don't understand your question? Are you saying the source of the data I linked to is corrupt or lies? Should I be concerned they are selling me false data?
But they are in fact selling the actual data! https://massive.com/pricing
If you find such a db with options, it will find "successful trading strategies". It will employ overnight gapping, momentum fades, it will try various option deltas likely to work. Maybe it will find something that reduces overall volatility compared to beta, and you can leverage it to your heart's content.
Unfortunately, it won't find anything new. More unfortunately, you probably need 6-10 years and do a walk forward to see if the overall method is trustworthy.
how do you have it build a "trading strategy"? it's like asking it to draw you the "best picture".
it will ask you so many questions you end up building the thing yourself.
if you do get something, given that you didn't write it and might not understand how to interpret the data its using - how will you know whether it's trading alpha or trading risk?
I can care less about scraping and web automation and I will likely never use that application.
I am interested in solving a certain class of problems and getting Claude to build a proxy API for any website is very similar to getting Claude to find alpha. That loop starts with Claude finding academic research, recreating it, doing statistical analysis, refining, the agent updating itself, and iterate.
Claude building proxy JSON api for any website and building trading strategies is the same problem with the same class of bugs.
Options quotes alone for US equities (or things that trades as such, like ADS/ADR) represent 40 Gbit per second during options trading hours. There are more than 60 million trades (not quotes, only trades) per day. As the stock market is opened approx 250 days per year (a bit more), that's more than 60 billion actual options trades in 4 years. If we're talking about quotation for options, you can add several orders of magnitude to these numbers.
And I only mentioned options. How do you store "every stock quote and options trade in the past 4 years" in 263 GB!?
[0] https://massive.com/docs/flat-files/stocks/quotes
I think this would be pretty straightforward for Parquet with ZSTD compression and some smart ordering/partitioning strategies.
I've used/use both, and find them pretty comparable, as far as the actual model backing the tool. That wasn't the case 9 months ago, but the world changes quickly.
It's a single HTML file - Claude wrote it and I iterated on the layout. A daily cron job checks the changelog and updates the sheet automatically, tagging new features with a "NEW" badge.
Auto-detects Mac/Windows for the right shortcuts. Shows current Claude Code version and a dismissable changelog of recent changes at the top.
It will always be lightweight, free, no signup required: https://cc.storyfox.cz
Ctrl+P to print. Works on mobile too.
There’s something funny about this statement on a description of a key bind cheat sheet. I can’t seem to find ctrl on my phone and I think it may be cmd+p on mac.
But for something like Claude Code there are unlimited things you can do with it, so it's better for them to accept a free-form input.
To quote The Godfather II, "This is the business we have chosen."
The most popular and important command line tools for developers don't have the consistency that Claude Code's command line interface does. One reason Claude Code became so popular is because it worked in the terminal, where many developers spend most of their time. But using tools like Claude Code's CLI is a daily occurrence for many developers. Some IDE's can be just as difficult to use.
For people who don’t use the terminal, Claude Code is available in the Claude desktop app, web browsers and mobile phones. There are trade-offs, but to Anthropic’s credit, they provide these options.
edit: removed obnoxious list in favor of the link that @thehamkercat shared below.
My favorite is IS_DEMO=1 to remove a little bit of the unnecessary welcome banner.
On Mac it's the same as Windows, CTRL + V.
You use CMD + V to paste text.
I asked chatgpt to chart the number of new bullet points in the CHANGELOG.md file committed by day. I did nothing to verify accuracy, but a cursory glance doesn't disagree:
https://imgur.com/a/tky9Pkz
it's almost like if the thing is not intelligent at all and just another abstraction on top of what we already had.
The fact users deal with almost everything being objectively not very good if not outright bad is a testament to people adapting to bad circumstances more than anything.
> Ctrl-F "h"
> 0 results found
Interesting set of shortcuts and slash commands.
This is a bit intense.