amitbarkan (@amitbarkan) profile picture
Joined May 2008
amitbarkan retweeted
If you use Claude Code, you'll probably need this. 59 useful commands for every situation: Context and cost /insights - HTML report on how you use Claude Code and where things go wrong /skill-doctor - shows how many tokens each skill costs and how often it's used /context - shows what's filling your context window /compact [instructions] - summarizes the chat, you can tell it what to keep /fewer-permission-prompts - scans your transcripts for read-only commands you run often and allowlists them for the project /btw [question] - asks a side question without adding it to the chat history /autocompact [auto|tokens] - sets how full the context gets before it auto-compacts, like 500k /clear [name] - starts a fresh session, the old one stays in /resume /usage - session cost, plan limits and what counts against them Models /advisor [fable|opus|sonnet|off] - adds a second model that Claude consults at key moments /effort [low|medium|high|xhigh|max|auto] - how hard the model thinks /fast [on|off] - toggles fast mode, applies from the next turn /model [model] - switches the model, press s in the picker to switch for this session only Getting work done /plan [task] - jumps straight into plan mode with the task /goal [condition|clear] - keeps working across turns until the condition is met /loop [interval] [prompt] - repeats a prompt on an interval while the session is open, like 5m /batch [instruction] - splits a big change into 5 to 30 units, each in its own worktree and PR /subtask [task] - background subagent with your full chat, result comes back to you /fork [prompt] - copies the chat into a background session and you keep working /branch [name] - tries a different direction without losing the current chat /background [prompt] - detaches the session and frees your terminal /tasks - everything running in the background /rewind - rolls back code and chat to a checkpoint /resume [name] - reopens a past session /rename [name] - names the session so you can find it later /export [file] - saves the conversation to a file or the clipboard /add-dir [path] - adds a second working folder /cd [path] - moves the session to another folder and keeps the chat Before you ship /diff - uncommitted changes, plus a diff for each turn /code-review [low|medium|high|xhigh|max|ultra] [--fix] [--comment] - finds bugs in the diff, --fix fixes them, ultra runs a deep multi-agent review in the cloud billed separately /simplify [target] - 4 agents in parallel clean up the code you just wrote /security-review - checks your branch for vulnerabilities /run - launches your app to check the change actually works, not just the tests Setup /init - generates a starter CLAUDE.md /memory - edits CLAUDE.md files and memory settings /import [codex|gemini|cursor] - pulls your rules, MCP servers and skills from another tool /doctor [prompt-audit] - checks your setup, prompt-audit reviews your CLAUDE.md and instructions /update-config [request] - describe a settings change in words and it edits settings.json /config [key=value] - opens settings or sets one directly /permissions - allow and deny rules for tools /hooks - shows the hooks that fire on tool events /mcp [reconnect|enable|disable] [server|all] - manages MCP servers /plugin [list|install|enable|disable] - installs and manages plugins /skills - lists the skills loaded in this session /status - version, model, account and connectivity /statusline - builds a status line from your shell prompt /terminal-setup - installs the Shift+Enter newline binding /install-github-app - sets up Claude GitHub Actions for a repo From anywhere /remote-control - continue this session from your phone /teleport - sends this session to the cloud, or pulls a cloud session into your terminal /desktop - continues this session in the Claude Desktop app /schedule [description] - cloud tasks that run on a schedule /autofix-pr [prompt] - a cloud session watches your PR and pushes fixes for CI failures and review comments Small ones /copy [N] - copies the Nth latest answer, press w to save it to a file /recap - one-line summary of the session /release-notes - what changed in each version /theme - changes the color theme /powerup - quick interactive lessons on features /heapdump - hidden from the menu, writes a memory dump to your Desktop, it contains your conversation so don't share it Short aliases /tp teleport, /rc remote-control, /bg background, /cost and /stats usage, /checkup doctor, /reset and /new clear, /checkpoint and /undo rewind, /routines schedule
30
10
2
169
33,690
amitbarkan retweeted
For me, this is the biggest issue when following somebody that covers only ONE asset class. Whether it be Uranium, Miners, Bitcoin, Gold or Silver... Will they be able to tell you when the ride is done? Or have excuses to hang on when price goes bear market? Think about it.
12
5
146
13,592
amitbarkan retweeted
Entering trades at higher prices, well AFTER the low will improve your results. Patience pays 👇 – at Whickham, England
20
27
1
351
36,350
amitbarkan retweeted
Chart Trading Definitions. Lower Risk = Odds of getting triggered out DECREASE. Higher Reward = Odds of riding an aggressive, longer lasting uptrend INCREASE. A lower risk, higher reward entry REQUIRES a big base breakout. BIGGER, the better.
8
2
1
107
10,597
There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper so I barely even touch the keyboard. I ask for the dumbest things like "decrease the padding on the sidebar by half" because I'm too lazy to find it. I "Accept All" always, I don't read the diffs anymore. When I get error messages I just copy paste them in with no comment, usually that fixes it. The code grows beyond my usual comprehension, I'd have to really read through it for a while. Sometimes the LLMs can't fix a bug so I just work around it or ask for random changes until it goes away. It's not too bad for throwaway weekend projects, but still quite amusing. I'm building a project or webapp, but it's not really coding - I just see stuff, say stuff, run stuff, and copy paste stuff, and it mostly works.
1,499
3,837
2,698
38,014
8,303,572
amitbarkan retweeted
Congratulations - You're living through the 4th signal in 100 years. DON'T MESS IT UP BY LISTENING TO FAIRYTALE NARRATIVES.
132
1,084
60
6,195
745,894
amitbarkan retweeted
3 out of the 4 horsemen are already galloping. 1) Bankruptcies on the move. 2) 10 minus 2 year yields on the move. 3) Unemployment Rate on the move. 4) Only initial jobless claims left to move. Time is ticking for the business cycle to roll over...
21
73
2
418
20,410
amitbarkan retweeted
MYTH BUSTING. ACCELERATING money supply increase will NOT always help the markets go up. Other macro forces in play.
History has shown us that using liquidity (m2) to anticipate stock market reaction is a dangerous game. It can work, until it doesn't. What always works is analyzing the price chart based on its own merits.
5
8
1
98
14,493
amitbarkan retweeted
I don't care how many diplomas you have OR how many dollars you manage. If price ain't trending up and away from your entry point, you aren't making any gains. It's pretty simple.
The following is CONTRARY to mainstream belief and might SHOCK some of you. The BEST way to get trapped into a corner, reducing your options as a market participant, is to actually STUDY the fundamentals of any single instrument. MORE time you study, more dangerous it is. You are wiring your brain to think that instrument can ONLY go up, that you are right. Ego then gets involved. If you want to be FREE floating, and simply play ANYTHING that is breaking out of a big base, starting to trend UPWARDS, is to learn NOT to learn. You won't feel like you HAVE to study the fundamentals for 5 years to be comfortable BEFORE entering the a trade. You will SIMPLY be accepting that the plethora of OTHER market participants did their homework, placing their bets accordingly. The IS the actual price chart, and is all that WARRANTS analysis. The OTHER stuff is time consuming and mental TRAPS, making it much harder for you to exit when the price falls apart. You have been PROGRAMMING yourself to seek confirmation bias AND dismiss any contrary takes. ANYBODY telling you to read a white paper OR any non chart defined piece of evidence, are slowly helping you get trapped. Spend time learning PROPER chart analysis. It is THE tool that will give you LIBERTY, not take it away.
5
6
100
12,995
amitbarkan retweeted
The following is CONTRARY to mainstream belief and might SHOCK some of you. The BEST way to get trapped into a corner, reducing your options as a market participant, is to actually STUDY the fundamentals of any single instrument. MORE time you study, more dangerous it is. You are wiring your brain to think that instrument can ONLY go up, that you are right. Ego then gets involved. If you want to be FREE floating, and simply play ANYTHING that is breaking out of a big base, starting to trend UPWARDS, is to learn NOT to learn. You won't feel like you HAVE to study the fundamentals for 5 years to be comfortable BEFORE entering the a trade. You will SIMPLY be accepting that the plethora of OTHER market participants did their homework, placing their bets accordingly. The IS the actual price chart, and is all that WARRANTS analysis. The OTHER stuff is time consuming and mental TRAPS, making it much harder for you to exit when the price falls apart. You have been PROGRAMMING yourself to seek confirmation bias AND dismiss any contrary takes. ANYBODY telling you to read a white paper OR any non chart defined piece of evidence, are slowly helping you get trapped. Spend time learning PROPER chart analysis. It is THE tool that will give you LIBERTY, not take it away.
20
24
3
217
42,682
amitbarkan retweeted
In 1973, US debt/GDP was 31%...today it's 122%. US fiscal deficit/GDP was 1%...today, it's 6% on its way to 8-10% (or more if the war drags on.) Translation: "That 70s Show" will feel like "1980s Argentina with US characteristics."
Replying to @Fullcarry
April hike odds now 20%... market thinking that 70s show
41
120
5
1,010
98,312
amitbarkan retweeted
Our digital credit vehicle achieved escape velocity this week.
208
549
45
5,727
255,985
amitbarkan retweeted
Confirmation that the big $STRC buyer yesterday were Strive. They bought a cool $50M worth. Some other important updates: 1) $SATA dividend reserve increased to 18 months (12 months cash + 6 months $STRC) up from 12 months of just cash. 2) $SATA dividend increase to 12.75%. 3) Strive to not issue $SATA via ATM or offering below $100 (no more discounts). I must say this is some good work from the team. The company is in a much stronger position now than 6 months ago. The fun truly begins when $SATA trades consistently at par.
STRIVE UPDATES - $SATA dividend increased to 12.75% - Targeted SATA price range narrowed to $99-$101 - Updated guidance to not issue SATA below $100.00 - SATA dividend reserve increased to 18 months - Purchased 179 Bitcoin & now hodl 13,311 BTC - Purchased $50M $STRC $ASST $SATA
19
24
1
333
21,962
amitbarkan retweeted
STRIVE UPDATES - $SATA dividend increased to 12.75% - Targeted SATA price range narrowed to $99-$101 - Updated guidance to not issue SATA below $100.00 - SATA dividend reserve increased to 18 months - Purchased 179 Bitcoin & now hodl 13,311 BTC - Purchased $50M $STRC $ASST $SATA
80
218
37
1,907
291,406
Anthropic's Revealing Chart on AI's Impact on Jobs Anthropic has unveiled a pivotal chart that underscores the chasm between AI's capabilities and its real-world application in the workforce. Derived from analyzing 2 million actual conversations with Claude, this radar chart, titled "Theoretical Capability and Observed Usage by Occupational Category," paints a stark picture of untapped automation potential across various job sectors. At its core, the chart is a spider web diagram plotting occupational categories around a circular axis, with values ranging from 0 to 1.0 representing the share of job tasks. The expansive blue area illustrates the theoretical coverage tasks that large language models (LLMs) like Claude could perform right now based on their inherent abilities. In contrast, the much smaller red area shows observed usage, drawn from real user interactions. The visual disparity is immediate and profound: blue spikes outward significantly in fields like computer and math (reaching about 0.75), business and finance, and office administration, while red hugs close to the center, often below 0.2 across most categories. This gap isn't just academic; it's a "career runway," as highlighted in discussions around the chart. For programmers, 75% of tasks are theoretically automatable, yet actual usage lags far behind. Similar vulnerabilities appear in customer service, data entry, and financial analysis, roles traditionally seen as white-collar strongholds. Meanwhile, hands-on fields like construction, agriculture, and protective services show lower theoretical exposure, with blue areas dipping to around 0.1-0.3, suggesting AI's current limitations in physical or unpredictable environments. Broader data amplifies the chart's message. As of early 2026, 49% of U.S. jobs expose at least 25% of tasks to AI, up from 36% a year prior. Yet, mass layoffs haven't materialized; unemployment in AI-vulnerable roles remains steady. Instead, subtler shifts are underway: a 14% drop in hiring for 22-25-year-olds in exposed positions indicates companies are prioritizing experienced workers, shortening entry-level pathways for recent graduates. The implications are clear: while AI's red footprint grows incrementally each month, the blue expanse signals accelerating change. College-educated, higher-earning professionals, once insulated are now most at risk, flipping the script on traditional labor disruptions. Anthropic's chart isn't a doomsday prophecy but a wake-up call, urging workers and businesses to bridge the gap through adaptation, upskilling, and ethical integration of AI tools. Please read the 5000 Days Series at ReadMultiplex.com for answers on how you can thrive in the Interregnum.
106
314
58
1,361
227,226
amitbarkan retweeted
What all BITCOIN MAXIS refuse to acknowledge...
There's one simple chart that explains why Michael Saylor, Tom Lee & the guy with the highest IQ in the world got it so wrong. I'll post it in a few hours, but members at northstarbadcharts.com know already & that's why they were positioned in gold & silver NOT Bitcoin.
14
28
7
173
26,708
🇺🇸 LATEST: Jerome Powell says not to read much into the rise in gold prices.
511
439
232
3,841
677,755