agents renaissance
Strawberry, CA
Joined September 2024
- Tweets1.2K
- Following198
- Followers2.9K
- Likes560
intern.🍓 retweeted
Low-agency: “Can I do this?”
High-agency: “I’m doing this unless someone stops me.”
The high-agency person has realized that most permissions are granted retroactively. It’s easier to get forgiveness than permission because once something is already done, the default switches from “no” to “well, I guess it’s fine.”
underrated: using @fiberplane to dissect big changes into smaller chunks, embrace the exponentials, come back and check the work
OVERRATED: running tons of agents in parallel; working on too many things at once; perpetual context-switching; opening lots of low-quality PRs that may never land.
UNDERRATED: using one or two agents at a time; focusing on the task in front of you; thinking deeply; finishing stuff; making your code works in prod.
Considering 90% of crypto frontends runs on Vercel
Super happy to have taken the contrarian route and go self hosted from the start
We’ve identified a security incident that involved unauthorized access to certain internal Vercel systems, impacting a limited subset of customers. Please see our security bulletin:
vercel.com/kb/bulletin/verce…
Crypto once again is in the LinkedIn era of AI
You can get SOTA uncensored models directly from huggingface by just searching for "Heretic"
You don't need TAO subnets to fine tune for modern obliteration
People out there are fine tuning uncensored sota OSS models with consumer GPUs
The information gap is so unreal here
Venice Uncensored 1.2 is now live.
Developed with @dphnAI, this model delivers the most uncensored version of Mistral 24B.
Upgraded with vision support, a 4x larger context window, and stronger tool-use capabilities.
Trained on Bittensor Subnet 4 @TargonCompute.
guess it's time to create a /no-npm-install skill
The cost of building from scratch went to 0 anyway
and btw, axios has always been shit from day 1
🚨 CRITICAL: Active supply chain attack on axios -- one of npm's most depended-on packages.
The latest axios@1.14.1 now pulls in plain-crypto-js@4.2.1, a package that did not exist before today. This is a live compromise.
This is textbook supply chain installer malware. axios has 100M+ weekly downloads. Every npm install pulling the latest version is potentially compromised right now.
Socket AI analysis confirms this is malware. plain-crypto-js is an obfuscated dropper/loader that:
• Deobfuscates embedded payloads and operational strings at runtime
• Dynamically loads fs, os, and execSync to evade static analysis
• Executes decoded shell commands
• Stages and copies payload files into OS temp and Windows ProgramData directories
• Deletes and renames artifacts post-execution to destroy forensic evidence
If you use axios, pin your version immediately and audit your lockfiles. Do not upgrade.
this is true but also wrong at the same time
in the context of AI trading you should start with a human thesis as the bare minimum and let the agent reiterate live, kinda like the an infinitely running montecarlo simulation.
also LLMs are lazy as fuck and they will not come up with novel ideas. You still need a proper human brain preparing the thesis for them
You should also provide the best quality data possible, and at least a python interpreter to reason over the data balancing speed + thinking
The output should only be SIGNAL (e.g. buy/sell): don't let agent handle execution and risk management, he will most likely lie to you when it starts losing
Keep a "lessons journal" and recursively refeed it on the next loop, see your agent improve and re-adapt to new market conditions
TLDR: The major perk of trading with agents is immediate readaptation to new market conditions, something that is hard to achieve with hardcoded algorithms, but you still have to put the work and basis thesis on the human side
bro created an ai crypto trading bot using
> Karpathy’s autorrsearch
> $200 of budget
> last 3 years trading signals
> the ability to buy its own compute
THE RESULT: didn’t perform well. pulling this off requires a massive token budget that only big hedge funds can afford. most X posts you see of people turning $100 to $1000 lack the evidence or are an advertisement to sell their bots.
Grab it while it's open source and feel free to reiterate on the concept.
As soon as it keeps on improving autonomously this is gonna become gated to Berry holders.
full code generated for this autonomous agent in the comment below 👇
github.com/strawberryai-lab/…
You could easily deploy this in any sandbox infrastructure and just tell him "start the loops" and it will start reasoning + journaling + predicting
Just loop it bro
