billzh

1.1K posts

billzh

billzh

@billzh

building @tribedotrun (@AllianceDAO ALL13)

Join Tribe 👉 Katılım Şubat 2015
497 Takip Edilen18.5K Takipçiler
Sabitlenmiş Tweet
billzh
billzh@billzh·
building a new social app on Solana and I'd love your help if you are a degen & into socialfi crypto has long promised us the ability to bet on underrated chads and get rich. any account's worthiness should be measured in market price, not Twitter followers but today this is still an unsolved problem. most prior attempts were too extractive and executed poorly I don't have all the answers but I'm experimenting and plan to iterate fast, starting with small degen chats so if you are interested in trying out the alpha version & giving feedback, please dm
English
214
63
596
214.9K
billzh
billzh@billzh·
recently I just ask my claude to go autopilot after we have created a plan let's go. go into autopilot mode and implement everything, verify, and iterate. make sure you have implemented every item in [plan file] and custom e2e completed verification without any issues. as a last step, run /x-pr and address all PR comments. this basically allows me to hand off the task to claude and come back in 1 hour to check verification results (recoding or screenshots) in pr
English
0
0
1
434
billzh
billzh@billzh·
apparently claude code has a tendency to avoid doing work by claiming something is out of scope so I added a stop hook that detects keywords like "pre-existing", "defer", "separate issue" etc it nudges the model into fixing everything it finds (but doesn't block the thread)
billzh tweet media
English
1
1
4
1.3K
billzh
billzh@billzh·
I'm glad that we never need to touch figma again just run 8 agents using @paper w/ Impeccable's claude skills
billzh tweet media
English
0
0
10
635
billzh
billzh@billzh·
claude code has another two annoying habits that I guard against - useless backward compat / legacy code for no reason - answers w/o runtime evidence (basically hallucinating), esp. when it uses the word "probably" stop hooks here are more effective than claudemd rules
billzh tweet media
billzh@billzh

apparently claude code has a tendency to avoid doing work by claiming something is out of scope so I added a stop hook that detects keywords like "pre-existing", "defer", "separate issue" etc it nudges the model into fixing everything it finds (but doesn't block the thread)

English
3
0
6
787
billzh
billzh@billzh·
@bcherny why is claude code taking ~500 GB with 5 tabs on iTerm2??
billzh tweet media
English
2
0
6
1.4K
billzh
billzh@billzh·
@ScottWu46 overall works great, but it seems to be really slow on larger PRs
English
0
0
1
378
Scott Wu
Scott Wu@ScottWu46·
Devin Review (devinreview.com) has been live for a week now. Would love to hear your feedback on what's working and what's not! What can we do to make it better?
Scott Wu tweet media
English
34
1
160
19.3K
billzh
billzh@billzh·
@bcherny how many MCPs do you usually load into your context window? they occupy a lot of tokens
English
0
0
0
2K
Boris Cherny
Boris Cherny@bcherny·
I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit. My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently. So, here goes.
English
1.3K
7K
54.2K
8M
billzh
billzh@billzh·
why is there a big slippage when bridging $hype from Solana on Wormhole??
billzh tweet media
English
11
0
14
3K
billzh
billzh@billzh·
@bengoodger @OpenAI need to support long running tasks or at least the ability to wait and check back in a bit (e.g. when talking to amazon customer support)
English
0
0
1
85
Ben Goodger
Ben Goodger@bengoodger·
When I joined @OpenAI last year all I had was an idea: that putting the world’s best AI assistant at the heart of your browsing experience would transform the way we get stuff done online. Since then we have been able to build an incredible team, and today we’re thrilled to release an all-new product: ChatGPT Atlas - a new web browser designed for the AI era - an era that will be shaped by more human natural language interaction, agents and ultimately AGI. Atlas has ChatGPT as its beating heart - ChatGPT is woven into the fabric of the product so it’s always nearby and ready to go. As I’ve used Atlas I’ve noticed I’ve become more curious. I ask more questions about the web around me. I’m finding better deals online, interpreting my personal health data, understanding my kids’ homework and much more - it’s all making me feel like a more informed, more self-actualized human. But Atlas doesn’t stop there. With its built-in browser agent, Atlas can browse the web for you, including to your logged-in sites (if you choose), and it’s SUPER FAST. This is one of those “feel the AGI” moments. Ask it to find all the ingredients for a recipe and load them into a shopping cart for you, ready to check out. Ask it for tips on how to write a better doc or use advanced features of your spreadsheets. Or even watch it play a web game! Atlas’ browsing agent cuts through piles of tedious clicking. Atlas is available for free download right now for MacOS users at chatgpt.com/atlas - I hope you’ll give it a try! If you’re on Windows or mobile hang tight, we’ll have something for you soon! BTW, this product was built by a small inter-disciplinary team. The amount of hustle shown by this crew over the past few months has been jaw dropping. It’s a real privilege to work with talented people like this @OpenAI. If working on a small, high-agency task force building the future of the web appeals to you - we’re hiring in SF, Seattle & NYC! I’ll follow up with more details in a post a bit later.
English
216
129
1.6K
445.1K
billzh
billzh@billzh·
@stevenyuntcap any idea how XYZ index works under the hood? which oracle is it tracking
English
0
0
2
367
steven.hl
steven.hl@_stevenhl·
I have had the privilege to play around with Trade’s frontend and put on XYZ100 perps positions. I know that not many are in this position, so ask me anything you’d like to know and I’ll try to answer people’s questions. Hyperliquid
trade.xyz@tradexyz

Equity perps are now live. Trade [XYZ100] with up to 20x leverage 24/7, 365. The XYZ US 100 Index tracks the value of the top 100 non-financial companies. The first 100 users on the waitlist will get alpha access to trade.xyz today.

English
49
5
170
25.5K
billzh
billzh@billzh·
what needs to happen for Hyperliquid to have CEX-level spot volume?
English
2
4
10
3.6K
encrypt.trade
encrypt.trade@encifherio·
Buy $ZEC privately using your SOL/USDC Inspired by @mert, we've built a bridging solution to send funds from @solana to @Zcash PRIVATELY with @near_intents Zolana Try it 👇 (link & steps in tweet below)
English
129
92
625
185.4K
billzh
billzh@billzh·
wtf?
QST
1
0
6
2.4K
billzh
billzh@billzh·
@QwQiao what's an example of defensive holdings in crypto?
English
6
0
3
2.3K
qw
qw@QwQiao·
quotes from howard marks’ essay 1.5mo ago: “ The last sustained market correction ended in early 2009, meaning it’s been over 16 years since risk bearing was seriously punished and ‘buying the dips’ wasn’t rewarded. That means no one under 35 or so – professional and amateur investors alike – has ever experienced a prolonged bear market. Older investors have experienced one or more, but, with the passage of such a long time, some may have been lulled into a false sense of security.” “Fundamentals appear to me to be less good overall than they were seven months ago, but at the same time, asset prices are high relative to earnings, higher than they were at the end of 2024, and at high valuations relative to history.” “Rather, I think it’s the average p/e ratio of 22 on the 493 non-Magnificent companies in the index – well above the mid-teens average historical p/e for the S&P 500 – that renders the index’s overall valuation so high and possibly worrisome.” “I think of progressively applying the following Investment Readiness Conditions, or INVESTCONs, in the face of above average market valuations and optimistic investor behavior: 6. Stop buying 5. Reduce aggressive holdings and increase defensive holdings 4. Sell off the remaining aggressive holdings 3. Trim defensive holdings as well 2. Eliminate all holdings 1. Go short In my view, it’s essentially impossible to reasonably reach the degree of certainty needed to implement INVESTCON 3, 2, or 1. Because ‘overvaluation’ is never synonymous with ‘sure to go down soon,’ it’s rarely wise to go to those extremes. I know I never have. But I have no problem thinking it’s time for INVESTCON 5.”
English
26
8
267
32.3K
billzh
billzh@billzh·
leveraging speculation to fund public goods is still an underrated idea
English
6
0
12
4.5K
billzh
billzh@billzh·
I'll also be dm'ing more people as part of this experiment
English
2
0
7
4.1K
billzh
billzh@billzh·
doing an experiment with my tribe I spend a lot of time onchain + talking to builders / traders etc. (esp on Hyperliquid & Solana) so I'm now systematizing this approach to bring more alphas & maybe even dealflows to my tribe
English
6
1
11
5K