Thanks for sharing this tool. A ~5GB KV cache is impressive, but if you persist full 1M-token sessions, that still means several GB of storage per session. For local open-source runtimes like DS4, the bigger bottleneck is probably still model weights/RAM, but storing many long sessions would also require a decent amount of SSD space!
sharing your learning process like this is really awesome
just a simple idea, but what if you turned the code or concepts you studied into public github repos? I’d definitely give them a star
for example, this is a repo I made around 7–8 years ago when I was studying nlp and ai models as an ai researcher:
https://t.co/mvuAXriMDi
1/3 PropAMM liquidity is now fully operational on Ethereum mainnet!
Three makers are live in every Titan block, and quotes are already consistently beating Binance VIP9 taker fees for retail orders (trades <$1k).
Appreciate Ivan tweet. To put this into context, to build DS4 I used: my MacBook M3 Max (mine, 8k euros), 1 M3 Ultra with 512 GB (got access, 10k euros), one DGX Spark (got access, 4k euros?). Are we far from the times all you needed to do hacking was a computer? That's sad.
tested out @antirez' ds4.c this morning. so impressive and delivers.
on a M3 max, 128GB, stock ds4 settings:
- 14–15 t/s at 62K pre-filled actual coding conversation
- memory usage was flat during gen ~85GB res
- disk cache is ~8GB for a full 100K context window
- thermals were normal, light fan activity
- inference server is rock solid so far
biggest constraint: anytime there's a compact, we pay the wait-time price of a fresh prefill (~1min per 10k context) before we are back in action.
sequential inference + multiple agents in parallel performance is unclear, will report back.
I'm so amped.
월간 다운로드 110만 건을 기록하는 PyPI 패키지가 해킹당해 정보 탈취 악성코드가 유포
공격자가 인기 있는 elementary-data 패키지인 파이썬 패키지 인덱스(PyPI)의 악성 버전을 배포하여 개발자의 민감한 데이터와 암호화폐 지갑을 탈취, 위험한 릴리스는 0.23.3 버전
after the axios incident, I started building packvet, an ai agent that vets dependencies before install and flags real risks. if you’re into dev tooling / security, let’s talk!
🚨 CRITICAL: Active supply chain attack on axios -- one of npm's most depended-on packages.
The latest [email protected] now pulls in [email protected], 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.
In my view:
In the past, a great engineer was defined by spending 10+ years mastering a single tech stack
going forward, it’s more about how broadly you’ve explored different domains, how many real problems you’ve actually solved, and how many times you’ve gone through the full cycle of building and shipping products