bug-bounty467
google369
microsoft315
facebook269
xss264
rce178
apple177
malware177
exploit156
cve119
account-takeover107
bragging-post102
phishing85
csrf84
privilege-escalation83
supply-chain69
browser68
stored-xss65
authentication-bypass64
dos63
reflected-xss57
react55
cloudflare52
reverse-engineering50
access-control48
input-validation48
cross-site-scripting48
node48
aws47
docker46
smart-contract45
ssrf44
ethereum44
writeup43
defi43
web-security43
sql-injection43
web343
web-application41
oauth40
race-condition37
burp-suite35
info-disclosure35
auth-bypass35
vulnerability-disclosure34
idor34
lfi34
pentest33
buffer-overflow33
html-injection33
0
6/10
A former backend lead at Manus proposes replacing traditional function-calling in LLM agents with a single Unix-style run(command="...") tool that leverages pipes and shell operators, arguing that LLMs are naturally aligned with CLI patterns they've seen extensively in training data and that this approach reduces cognitive load on tool selection while enabling composition.
llm-agents
function-calling
tool-use
cli-design
prompt-engineering
agent-architecture
unix-philosophy
agentic-systems
Manus
Meta
Pinix
agent-clip
LocalLLaMA
MorroHsu