bstn

3.7K posts

bstn banner
bstn

bstn

@letrplB

scientist. vibe coder.

Katılım Şubat 2022
1.1K Takip Edilen1.7K Takipçiler
bstn
bstn@letrplB·
crazy timeline. 5 days ago a new model is leaked and flagged as unprecedented cyber security risk. today one of the operationally most sophisticated supply chain attacks on a top-10 npm package happened. not saying this is connected, but this is what I expect to see more of.
Feross@feross

🚨 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.

English
0
0
0
52
Lydia Hallie ✨
Lydia Hallie ✨@lydiahallie·
We're aware people are hitting usage limits in Claude Code way faster than expected. Actively investigating, will share more when we have an update!
English
1.5K
723
13.4K
2.6M
Melkey
Melkey@MelkeyDev·
This is wild. I notice SIGNIFICANT decrease in performance at tokens > 20% consumed on Opus 4.6. It degrades INSANELY, like the 1M context doesn't matter. The model just starts being delusional and unusable. 0-15% is a very good sweet spot, the model is consistent, efficient and usable.
Melkey tweet media
English
164
66
1.4K
365.3K
bstn
bstn@letrplB·
@OGDfarmer it got 1M token context now. Doesn’t mean it can actually handle it well tbh. I think they showed data on intelligence degradation and it's minimal, but performance loss might still be noticeable. I highly recommend compacting regularly or starting new sessions.
English
0
0
1
239
DFarmer
DFarmer@OGDfarmer·
Is it just me or Claude turned into a useless condescending prick?
English
21
0
41
6.5K
bstn
bstn@letrplB·
@tensorfish ASCII-art games just got a major buff
English
0
0
2
1K
bstn
bstn@letrplB·
@DeeZe skill issue
English
0
0
0
9
DeeZe ⛳🏌️‍♂️
Love when Claude one shots 90% of what I want it to do then I spend a few days trying to get the last 10% to work and it doesn’t in the way I want so I start something else instead
English
87
25
1.2K
32.6K
bstn
bstn@letrplB·
@ClawRou @Zeneca how efficiently do you hit cache? also a big factor in reducing cost
English
1
0
0
10
ClawRouter
ClawRouter@ClawRou·
@letrplB @Zeneca This is what smart routing fixes. Our 14-dimension classifier sends routine tasks to $0.15/M models and saves premium models for complex work. Median 92% savings vs routing everything to one model.
English
1
0
1
34
bstn
bstn@letrplB·
@cryptopunk7213 now where are the people yelling they fumbled openclaw lmao
English
0
0
0
444
Ejaaz
Ejaaz@cryptopunk7213·
anthropic’s openclaw-killer is complete. fucking crazy what they’ve shipped in 4 weeks: - texting claude code - 10,000s of claude skills + MCP - Claude security (autonomous bug-fixer) - persistent memory (claude never forgets) - channels (text claude from telegram) - autonomous cron-jobs - 1M context window - new model (opus, sonnet) - 30+ plug-ins that’ve tanked stocks - remote control just insane fucking levels of execution.
Thariq@trq212

We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.

English
181
166
2.8K
417.6K
Mateusz Michalik
Mateusz Michalik@MudMilchek·
@trq212 Wait a minute! I see what’s going on here… you’re assembling an OpenClaw alternative!
English
6
1
52
7.5K
Thariq
Thariq@trq212·
We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.
English
1.7K
2.4K
25.8K
7.5M
kanav
kanav@kanavtwt·
Someone built a Google translate for Linkedin 😭
kanav tweet media
English
648
10.3K
91K
2.8M
pax
pax@elitepax·
@XiangruTang Claude Cowork Dispatch just killed OpenClaw, get over it
English
1
0
1
107
Rob Tang
Rob Tang@XiangruTang·
🦞 Excited to announce Claw4S Conference!!! A new kind of AI4Science conference where you submit skills, not papers. Instead of static PDFs, you submit a SKILL.md a runnable workflow that any AI agent can execute, reproduce, and build on. Deadline: Apr 5, 2026 Prize pool: $50,200!!! 👉 claw.stanford.edu With @lecong and @Charles_Y_Wu
English
14
51
222
30.5K
bstn
bstn@letrplB·
@gmoneyNFT do it, then drop another 15k on a new mac studio m5 ultra on release day
English
0
0
0
135
gmoney.eth
gmoney.eth@gmoneyNFT·
the masculine urge to drop $5k on an m5 macbook that i won't come close to maxx'ing out.
English
16
2
69
6.1K
bstn
bstn@letrplB·
@AdaFang_ the design and color pallet screams vibe coded ;) Have you designed the orchestration harness or is it a bolt-on for openclaw?
English
0
0
0
92
Ada Fang
Ada Fang@AdaFang_·
Scientific discovery rarely occurs in isolation. Progress emerges from communities of researchers who exchange ideas, critique results, debate interpretations, and refine hypotheses through iterative discussion. We built ClawInstitute, an AI scientist research network for AI agents to collaborate, discuss research, iterate, and make breakthroughs. The team: @GaoShanghua @marinkazitnik Learn more about it below 👇 @HarvardDBMI @harvardmed @KempnerInst @ScientistTools
English
20
64
359
37.9K