Viewing profile — guluarte
guluarte
HN member- Joined
- Sat, Feb 11, 2023, 8:11 PM UTC
- HN karma
- 335
- Public activity
- 396 items
- HN profile
- View on Hacker News ↗
About guluarte
No profile information was provided.
Recent public activity
-
comment
Comment #49258703
will this solve anything? people will build tools to remove the watermarks
-
comment
Comment #49249371
the problem with this is... now i trust the agents more than myself lol
-
comment
Comment #49182708
cli tools > mcps
-
comment
Comment #49174512
I think most of the cost is in R&D
-
comment
Comment #48960360
i just use terminus + wireguard + tmux and works great, i can control claude/codex from my phone while working out
-
comment
Comment #48951152
cool, meanwhile people will use pixelated pepes instead
-
comment
Comment #48925380
"Hey Codex, help me design the most useless hardware you can think of"
-
comment
Comment #48897823
2 base jumps? are those really that dangerous?
-
comment
Comment #48886840
Check all MCP you have enabled in claude.ia
-
comment
Comment #48848770
They announced that GPT-5.6 Sol, along with Terra and Luna, will launch publicly today.
-
comment
Comment #48846841
A lot of these benchmarks are unfamiliar. Are labs just choosing the ones that make them look best?
- comment
-
comment
Comment #48826036
I don't think one week is enough to learn the complex business rules that some software needs to follow.
-
comment
Comment #48819116
At the moment, AI is creating more work for me, not less. The more capable the models become, the more responsibilities and expectations you have as a developer. Nowadays, I spend …
-
comment
Comment #48809513
At least they’re honest and not blaming AI.
-
comment
Comment #48766675
use /goal with bypass permission then
-
comment
Comment #48766656
for me fable does things nobody asked for
-
comment
Comment #48720010
This feels like telecom "massive demand, bad returns". If a good enough model can be swapped in every few months, the value moves away from the model and toward cheap inference. Th…
-
comment
Comment #48668083
or tell an llm to do it for you
-
comment
Comment #48667937
Anthropic training their models full of copyright data, so?
-
comment
Comment #48571035
I would agree but in this case they are buying the talent and the data.
-
comment
Comment #48512781
Also fable was good but not Manhattan level project, i honestly did not find a major difference between it and gpt 5.5
-
comment
Comment #48512655
well... Leason learned i guess, they hyped mythos too much
-
comment
Comment #48491327
For me, AI can sometimes create a false sense of productivity. It's similar to how in the past, people would spend time creating the perfect setup with notion templates, pomodoro t…
-
comment
Comment #48469175
AI creates more work