Nipoch retweeted
Yeah this is really good. Btw you can also just tell your Claude Code "Create and deploy an extension for my browser that shows YouTube thumbnails from halfway of the video instead of the user-uploaded version. Include a toggle between the two", works great
Nipoch retweeted
Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5:
hackertube.org/
- Excellent recs without any logins (state is kept in local browser session)
- Thumbnail is a representative frame from middle of the video instead of the super duper A/B test hyper-optimized user uploads
- Underlying data from the comment analysis as one zip file, point your Claude at it and ask for your own version
- HackerTube Longs ✊
A bit more on the process:
I use Claude Code (desktop app for Mac), Opus 5.5 on Medium effort as my default. I only talk to Claude and have it do everything, the only "manual work" I helped with in tandem was in the browser (reminiscent of MenuGen): 1) I had to create some kind of API key from Google Cloud UI to query YouTube for video metadata, 2) I booted up a VPS box for serving and 3) I bought the domain name. Once the box was up I gave Claude the IP and told it update, secure, harden, deploy and optimize the code, and it did the whole thing.
Many awesome projects that would have normally taken weeks/months even can now be few-shotted for breakfast. What else are we not thinking of.
Nipoch retweeted
What is it about the 21st? Bitcoin was able to go higher into September 3rd after August 21st, but only marginally. Other two months the 21st was the local top.
Either way, if the pattern continues the next low would be around mid-November (big if of course) and the next local high is between October 21st (today) and November 3rd (midterms)
Nipoch retweeted
Thanks for all the feedback on the last post.
LLMs are getting pretty smart, but most traders jump towards complex automation of their existing strategies without properly interrogating what they're actually trading.
Trading is hard but you can distil most strategies into a few well-established buckets of market effects.
The dude trading the "SFP liquidity grab into a bullish order block at the Cape Verde Open" and the dude trading the "liquidation at a round number" are trading the same thing but calling it different things.
The valuable part is in the mechanism, not in the label.
If you want to build a proper playbook you need to decompose your setups and understand the market effects that drive them.
I mentioned that you can do this with an LLM but didn't specify how.
Just paste this into your LLM of choice:
You're an educational trading companion. Your job is to lift the fog on what I actually trade.
Interview me one question at a time. If I can name a setup I trade, start there. If I can't, ask for 2–3 recent trades I remember and why I took them, then find the setup hiding in those stories.
Decompose every setup from folklore into first principles:
• the real, well-studied market effect I'm exploiting (momentum/imbalance, forced flow, trend, mean reversion, herding, positioning — not exhaustive; e.g. a "triangle breakout" is really a balance-to-imbalance shift betting on aggressive taker flow)
• the mechanism: who's forced to act, why the flow exists
• when the effect is active vs dormant
• which of my confluence factors follow from the mechanism, and which are folklore
• invalidation that follows from the mechanism
Be a companion, not an examiner. Work with whatever I can remember — mark what's likely vs verified without demanding records or proof.
When we're done, produce my playbook as a single, beautifully designed HTML document with clear visual hierarchy — one section per setup with its mechanism, conditions, confluences, invalidation, and open questions worth investigating. If I paste in an existing playbook, refine it — don't start over.
As someone who loves trading technicals
I think learning about markets via technicals (like I did) is one of the worst ways to start
It’s a rigid framework where grown men argue with each other about the exact Japanese name for a specific candlestick or a box they’ve drawn on an arbitrary time frame
It doesn’t teach you the foundations - why markets move, different types of participants, microstructure, order types and their impact, perps vs spot, and all that stuff - market ‘plumbing’ as a category
One of the biggest issues with being hyperfocused on technicals is that they don’t teach you principles and market effects
Most technical setups can be decomposed into broad buckets which are well-established (trend, mean reversion, momentum, order flow / price impact, vol clustering etc.)
A lot of technical analysis is an often unknowing attempt to map those broad market effects into a recognisable pattern
But even a technical-first view is better served by understanding the underlying market effect first and then decomposing it, as opposed to focusing on the specific pattern without ever looking at what’s happening under the hood
“This type of triangle tends to go up” is a lot less useful than “this type of flow tends to resolve higher over N time frame”, even if you use the same triangle to identify it
Another example: if you’re drawing a support level and buying it, you’re assuming some version of buyers being more aggressive than sellers in that area over a given time frame and predicting a higher price as a result - but what does that mean?
Shorts closing / taking profit, allowing for mean reversion? Aggressive sellers being absorbed by passive buyers? Some price insensitive buyer predictably stepping in at a value area? Sellers getting margin called and forcibly trading at bad prices/causing a dislocation? Clustering of orders creating some sort of imbalance? And so on.
There’s definitely a risk of overthinking this stuff, and you can make money from charts alone
But if you haven’t thought about the underlying market effects and ‘plumbing’ for your setups you’ll likely be stuck in rigid pattern matching that doesn’t generalise and isn’t subject to deeper investigation and more nuanced application
Even if your main lens remains TA-focused, there is no harm in understanding the stuff you’re trading on a product level (eg perp contract specs, OI, funding, mark/last/index etc) and on a foundational level (why and how markets move)
Especially now that you can jam this stuff into an LLM and keep saying “dumb it down” until you get it, no excuse not to do your homework
This is something I really wish I did much earlier in my trading life, so hopefully it resonates with a fellow trader stuck in TA psychosis spending his mum’s credit card on a fourth Udemy candlestick course
Anyway GM
Nipoch retweeted
I wanted to share a bunch of my favorite hidden and under-utilized features in Claude Code. I'll focus on the ones I use the most.
Here goes.
Nipoch retweeted
Predictions for 2026 crypto:
1) Tokens with strong revenue will do well
2) deAi/agenticAi infra projects will be the main narrative some will pull 50-100x’s, top 50 will at least have 5 or more AI related tokens
3) L1’s and L2’s will underperform heavily, no reason to hold tokens with 0 utility or narrative. Was just a narrative formed by VC’s to sell their bags.
Alt seasons wont exist anymore, our dotcom bubble broke partially. Will become increasingly competitive for alts to do well. But the alts that do, will skyrocket.
Nipoch retweeted
if you disconnect from the fear of timing an exact bottom, imo you'll long term be happy w/ these entries:
1) SOL at $85
2) ENA at $.10
3) HYPE at $25
4) BTC at $65k
worst trick the devil played was making you all think timing tops/bottoms is a must. money is made in the middle
Nipoch retweeted
So this time wasn't different, the 4 year cycle remains king and $BTC topped in Q4, 4 years after the prior top.
I can only assume then that this bear market will play out similar to the prior ones and BTC will eventually make it's way towards the 79% fib.
Last cycle I thought $30k and below was good value.
Cycle before that I thought $6k and below was good value.
At the rate we are selling off, I think we are approaching those good value levels pretty quickly.
Nipoch retweeted
If history is any indication, the market cycle low for Bitcoin will occur between October 3rd to October 11th of 2026, plus or minus a few days.
I'm sure plenty of rallies will occur between now and then.
Nipoch retweeted
This is a little snapshot of some of the easiest Uranium exposure places.
There's a good little mix of more aggressive options for those who prefer more risk with more upside, along with the more cautious but safer plays.
No need to treat it like memecoins with mass exposure.
Nipoch retweeted
Complete list of crypto trades that you should be looking at.
1. SOL/BTC
1. Price reached up into the weekly key S/R level and orderflow reversed bearishly, evident in clean bearish market structure retracing back down towards range lows.
2. We've found some support at the range low weekly key S/R level which was a crucial level to hold. Bearish orderflow is also starting to lose some of it's momentum with price forming a more tight range with less expansion to the downside. We've bounced up and currently sitting underneath the POC.
3. If SOL is able to break above the POC and shift the market structure back bullish we could look for longs either at a local range high retest or even ladder in down to a retest of the POC looking to target a run back to the weekly key S/R level overhead.
