bug-bounty473
google371
microsoft318
facebook271
xss267
rce184
apple178
malware177
exploit165
cve122
account-takeover110
bragging-post102
phishing85
csrf85
privilege-escalation83
browser71
supply-chain69
stored-xss65
authentication-bypass64
dos64
react58
reflected-xss57
cloudflare52
reverse-engineering50
access-control48
node48
input-validation48
aws48
cross-site-scripting48
writeup47
docker46
ssrf45
smart-contract45
ethereum44
web-security43
sql-injection43
defi43
web343
oauth41
web-application41
lfi38
info-disclosure37
pentest37
race-condition37
idor35
burp-suite35
auth-bypass35
vulnerability-disclosure34
cloud34
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