Viewing profile — brabel
brabel
HN member- Joined
- Sat, Feb 25, 2017, 10:17 AM UTC
- HN karma
- 8,340
- Public activity
- 3,637 items
- HN profile
- View on Hacker News ↗
About brabel
No profile information was provided.
Recent public activity
-
comment
Comment #49216325
A lot of companies were founded by one or a group of people leaving a company and opening a competitor with the knowledge they gained while working for them. Anthropic, as I unders…
-
comment
Comment #49198152
[flagged]
-
comment
Comment #49197707
The counter seems broken. It jumps from 100 to 250 then back down to 120. It did that a few times while I was reading.
-
comment
Comment #49195162
No, a company will always build whatever they think will make them more money. If you want an editor without the bullshit try Sublime as it has a history of staying that way, or th…
-
comment
Comment #49195143
For a large application the language it is written in has almost no bearing on the perceived speed by users. VSCode is one example.
-
comment
Comment #49195085
That’s why nowadays every company will require that they legally own projects you work on during work hours unless explicitly asked. And many ask you to sign non compete clauses so…
-
comment
Comment #49194937
Because that is convenient and everyone does it??
-
comment
Comment #49194929
You can’t be seriously proposing HTTP auth (you probably mean basic auth??) as a solution!? Just hand your raw credentials to the LLM, what could go wrong?
-
comment
Comment #49194899
MCP and skills complement each other, it’s not one vs the other. > MCP apps do not have a manual invocation option. If you enable them, they are always on, eating away tokens This …
-
comment
Comment #49194765
You’re asking for AI censorship ( that’s the term used for when you patch the AI to not do obviously bad things according to the owners, which as with any censorship, may be widely…
-
comment
Comment #49194739
The rovo CLI is beating Claude Code in some benchmarks. It works pretty well for me.
-
comment
Comment #49194709
Are you saying you would prefer a perfectly deterministic code writer? So, humans shouldn’t write any code anymore?!
-
comment
Comment #49181067
Skills and MCP can be treated by the harness in the exact same way. What do you think is unique to skills that does not apply to how MCP servers are managed?
-
comment
Comment #49180999
Because while an agent can indeed call a REST API directly using some other tool ( probably curl) what LLMs are good at is calling tools, and all MCP is doing is turning an API int…
-
comment
Comment #49180894
Even on your own machine with CLI tools , you really think it’s a great idea to let the LLM use the CLI as if it were you, with all permissions you have without any way to differen…
-
comment
Comment #49180848
Show me then how to convert my MCP, including auth, behind a CLI like interface. I don’t think that’s even possible.
-
comment
Comment #49167371
Thank you for writing exactly why people who complain about LLMs making it harder to understand what’s going on are so off. Nothing helps more than asking LLMs to tell you exactly …
-
comment
Comment #49167189
I would say any programmer has found themselves so deep in the metaphorical woods that they forgot what they were actually trying to achieve in the first place. For example, you st…
-
comment
Comment #49165109
I thought the Australians did burn entire forests to the extent that much of Australia is the result of millennia of that practice.
-
comment
Comment #49155832
That's the worst case scenario right there: so many fake reports that the real vulnerabilities can no longer be reported properly and fixed quickly. Assuming some LLMs really are c…
-
comment
Comment #49153952
No. There is this persistent belief in the industry that programmers should be good at everything, not just programming itself: communication, product management, design, sysops, U…
-
comment
Comment #49153192
Yeah people never wanted to update Windows since they had been burned in previous upgrades and their current setup just worked. Not only were upgrades difficult to do and took a lo…
-
comment
Comment #49134709
> also buggier, more bloated, and just generally worse than ever. Citation needed. I have seen enormous improvements in bug fixes across our projects and many other companies (one …
-
comment
Comment #49134464
The ai does what you ask it to do. One thing you can ask is for it to refactor the code base to achieve some goal, for example to make new features easier to add , or to just make …
-
comment
Comment #49132666
We have a QA team but it’s small in comparison to the dev team. We didn’t have one before as we thought automated tests and “good developers” who take testing seriously was enough.…