SalimWebLabs 리트윗함
SalimWebLabs
1.4K posts

SalimWebLabs
@devwithsalim
CS major | web dev | C++ | Java | Python | Algorithms 🇳🇬
Node 345 가입일 Ocak 2021
484 팔로잉75 팔로워
SalimWebLabs 리트윗함
SalimWebLabs 리트윗함
SalimWebLabs 리트윗함
SalimWebLabs 리트윗함
SalimWebLabs 리트윗함
SalimWebLabs 리트윗함
SalimWebLabs 리트윗함
SalimWebLabs 리트윗함
SalimWebLabs 리트윗함

Scraping data from 180 universities was the most challenging part of this project.
In total, we collected over 70,000 records📝📈.
Website Designer Nigeria@webdesignerng
Four months ago, we got the biggest gig of our career. Today, the project is completed. A university compare portal for UK and Ireland schools 🇮🇪🇬🇧 Stack: Django🐍 , Tailwind and JavaScript.
English
SalimWebLabs 리트윗함
SalimWebLabs 리트윗함

It was a pleasure to receive Tony Elumelu (@TonyOElumelu), Chairman of UBA, and his management team on a visit to our office today.
Our relationship goes back many decades, rooted in a strong business relationship built on trust, mutual respect, and shared objectives. We value this enduring partnership and the history we have shared, and we continue to build on it as we exchange ideas and strengthen our engagement.
We look forward to further strengthening our collaboration and creating even more value between our two groups.
#ASR
English
SalimWebLabs 리트윗함

‼️🇳🇬 A massive breach allegedly from Remita, a major Nigerian payment processing platform, has been leaked on a popular cybercrime forum.
▪️ Total Size: ~3TB of S3 storage
▪️ Data Includes: 800GB+ of KYC documents (IDs, passports, photos, bank statements, electricity bills), MySQL/Postgres databases, logs, docker registries, source codes, government HSM keys, GitKraken to S3 backups
▪️ Source codes, 35,000+ password hashes, and three databases

English
SalimWebLabs 리트윗함
SalimWebLabs 리트윗함

Based on everything explored in the source code, here's the full technical recipe behind Claude Code's memory architecture:
[shared by claude code]
Claude Code’s memory system is actually insanely well-designed. It isn't like “store everything” but constrained, structured and self-healing memory.
The architecture is doing a few very non-obvious things:
> Memory = index, not storage
+ MEMORY.md is always loaded, but it’s just pointers (~150 chars/line)
+ actual knowledge lives outside, fetched only when needed
> 3-layer design (bandwidth aware)
+ index (always)
+ topic files (on-demand)
+ transcripts (never read, only grep’d)
> Strict write discipline
+ write to file → then update index
+ never dump content into the index
+ prevents entropy / context pollution
> Background “memory rewriting” (autoDream)
+ merges, dedupes, removes contradictions
+ converts vague → absolute
+ aggressively prunes
+ memory is continuously edited, not appended
> Staleness is first-class
+ if memory ≠ reality → memory is wrong
+ code-derived facts are never stored
+ index is forcibly truncated
> Isolation matters
+ consolidation runs in a forked subagent
+ limited tools → prevents corruption of main context
> Retrieval is skeptical, not blind
+ memory is a hint, not truth
+ model must verify before using
> What they don’t store is the real insight
+ no debugging logs, no code structure, no PR history
+ if it’s derivable, don’t persist it

English
SalimWebLabs 리트윗함

ANTHROPIC ACCIDENTALLY LEAKED Claude Code source code and someone made a copy of it on GitHub, in just 1 hour it already got 1.5K stars.

Sigrid Jin 🌈🙏@realsigridjin
@Fried_rice i backed the source up on my github github.com/instructkr/cla…
English
SalimWebLabs 리트윗함
SalimWebLabs 리트윗함
SalimWebLabs 리트윗함
SalimWebLabs 리트윗함

































