Viewing profile — philipp-gayret
philipp-gayret
HN member- Joined
- Tue, Jul 22, 2025, 9:07 AM UTC
- HN karma
- 148
- Public activity
- 95 items
- HN profile
- View on Hacker News ↗
About philipp-gayret
Recent public activity
-
comment
Comment #49132782
Having spent too many years in CI/CD I'd agree but there is an even better solution; decouple deployments from releases. Make it possible to deploy without releasing, and release w…
-
comment
Comment #49046607
> makes me concerned that you believe the only way someone would/could become more attractive is by performing some sort of charade. I am unapologetically my authentic self, I find…
-
comment
Comment #49042694
He changed what he says his values are when dating women, to make dating woman easier for himself. Why he mentioned it, I don't know. He holds IMHO strange views on internet cultur…
-
comment
Comment #48829580
> Is there a way to segment access per agentic workflow, so that you can have both habe an agentic workflow that has access to sensitive data and one that has only access to public…
-
comment
Comment #48815270
Impressive. Now, let's see the link in this post to fastcompany.com; It opens a website that also pulls in 6MB using more "server requests" than 169, in fact the number keeps going…
-
comment
Comment #48803557
My diagnosis is.. You are working with people. Smart ones at that, who have been working for a very long time in their own, niche, specific way. To assume all engineers will become…
- story
-
comment
Comment #48269922
In the DORA group's reporting on AI-assisted software engineering, they indeed state that across industries, quality goes UP with the use of AI assistants like Claude and others. M…
-
comment
Comment #48213733
I worked for a food retail store once. I remember going in the first day wondering, how hard can it really be... From the outside, it looks like they have a simple website. The web…
-
comment
Comment #48213642
> It was Qwen-coder when it launched but I don’t know what it is now. This was also what I used at the time, the Qwen 3 Coder 480b on Cerebras. Worked great and was so stupidly fas…
-
comment
Comment #48211969
If you have a Cerebras Code subscription you can experience it right now. Indeed, a very different experience.
-
comment
Comment #48205377
> - A SKILL.md system mirroring Anthropic's skills convention. > - Subagents, an artifacts review workflow (slash commands), and conversation rewind. Antigravity CLI, like Gemini C…
-
comment
Comment #48205229
Nice work! I've worked through all kinds of local models, very extensively for a week on an NVidia Spark. Gemma and Qwen, quantized, somewhat shine but the results overall compared…
-
comment
Comment #48177588
[dead]
-
comment
Comment #48091915
Would be an interesting concept and read were it grounded in reality. Unfortunately, it's data and graphs pulled out of someone's imagination. Reality is nowadays with the right sk…
-
comment
Comment #48084248
For Hooks (IMO the most powerful feature) Id recommend only https://code.claude.com/docs/en/hooks-guide and for Plugins, Skills, MCP and so on the official documentation by Anthrop…
-
comment
Comment #48060410
Native integrations with agents, i.e. Claude Code's system of Hooks. Harnesses, which kick off agents with what to do. Tools, which show an agent where in a process it is, and what…
-
comment
Comment #48048312
Interesting project. I am working on a similar solution. Eventually you will run into the following with harnesses, so I wonder how these questions work with your project; 1) Can y…
-
comment
Comment #48047071
In the Netherlands, it's the name for anyone between junior and senior, in software. From my perspective it's more something used by recruiters and employers to tell people they do…
-
comment
Comment #48046770
You have described exactly the situation of almost all of my clients. And in some way it is good to see our business model validated as we help steer organisations at this level, a…
-
comment
Comment #47845998
Nice work, I applied my own benchmarking tools to it. On my single NVidia Spark I get 173.3 tokens/s on baseline config, 372.4 tokens/s with added tuning/parallel options. Most not…
-
comment
Comment #47817494
Fun read and honestly very impressive demonstration of what can be done with the tech by someone with no experience whatsoever.
-
comment
Comment #47731162
> 1. What do you use the hooks for? I use hooks to automate decisionmaking (i.e. stronger permissions than a regex by parsing the bash) and similarly automate guidance. Our tooling…
-
comment
Comment #47701796
I like and do use Zed but be aware functionality like Hooks is not supported for their integration with Claude Code, as a heavy user of Hooks I would stick with the terminal.
-
comment
Comment #47524226
Having managed GitHub enterprises for thousands of developers who will ping you at the first sign of instability.. I can tell you there has not been one year pre-AI where GitHub wa…