Viewing profile — cheema33
cheema33
HN member- Joined
- Tue, Oct 16, 2012, 5:53 AM UTC
- HN karma
- 1,649
- Public activity
- 626 items
- HN profile
- View on Hacker News ↗
About cheema33
No profile information was provided.
Recent public activity
-
comment
Comment #49185445
> What do you think is unique to skills that does not apply to how MCP servers are managed? I have a skill that describes my database schema with hundreds of tables, stored procedu…
-
comment
Comment #49185253
[dead]
-
comment
Comment #49185166
> you can actually invoke an MCP App by name in both Codex and Claude using the @ handle Even when it is disabled? The point is to have the skill or mcp app to not use ANY tokens u…
-
comment
Comment #49180473
> Modern harnesses don't do that, MCP is also progressive disclosure now. Last time I checked, and it may be different now, Claude Code used tool search only if context usage was g…
-
comment
Comment #49180384
I can turn off auto invocation of a skill. It uses zero tokens when in this mode. I can still invoke it by calling it by name. How can I do that with MCP servers?
-
comment
Comment #49179362
My main issue with MCP servers has been context bloat. Skills have progressive disclosure, and allow me to turn off auto invocation with something like this in the SKILL.md file: d…
-
comment
Comment #49173000
> It’s covering all of the R&D costs like salaries, collecting training material, and running the large training operations that costs a lot of money. Are you claiming that the fro…
-
comment
Comment #49119097
> The problem with at least ChatGPT is no matter what personality you set it still reads like a smug asshole trying to sound smart. Some of this may be perception rather than reali…
-
comment
Comment #49090231
At our small 12-person company, I help manage DNS. Email service is through Microsoft. I had previously configured SPF and DKIM etc. but never DMARC. We are too small to have time …
-
comment
Comment #49055226
I imagine they would look similar to what they look now. You will have a 7" monitor in front. You can use it watch movies or look outside.
-
comment
Comment #49041319
Cinematic video link is incorrect. Podcast link is correct.
-
comment
Comment #49029061
> Fable-level results at 1/3 the cost I am guessing this is not targeting those of us on the heavily subsidized $200/mo plans. Sure, these plans may be temporary, but none of us re…
-
comment
Comment #48986409
> how is running servers supposed to be 0 cost, while running ai inferrence isn't? For a SaaS business, running servers isn't free. But compared to the cost of running GPUs for inf…
-
comment
Comment #48896086
> TLDR: Ran grok in $HOME. Surprised agent read content of folder. Did it really need to read all of $HOME and everything under it?
-
comment
Comment #48889099
Elon doing Elon things.
-
comment
Comment #48812418
Very cool. I don't have a remarkable, but have the Amazon Kindle Scribe. Same idea. Would any of you be so kind to waste your precious Fable tokens on getting something like this w…
-
comment
Comment #48789178
> most germs transfer over touch While true, your comment implies that infections through air are not important/critical. This includes COVID-19?
-
comment
Comment #48765936
I have switched on production and QA servers. I used AI tools to help with the migration. Easy peasy. On the desktop, I am still using docker. Old habits die hard. Eventually I pla…
-
comment
Comment #48765914
Agreed. My first thought after that page loaded was, "why is this page harder to read?"
-
comment
Comment #48715114
> I’d argue that this is more of a question of ‘do I need offline support?’ For Slack, sure, but for many apps, probably not. I like offline support. I enjoy it when an app I use s…
-
comment
Comment #48709671
Navigation was quiet confusing to me on my Macbook as well. If the topic was not so interesting I would have left in complete frustration instead of deciding to fight the interface…
-
comment
Comment #48704540
> I tested Fable through Cursor; I tested Fable for a whole day. And my experience was quite the opposite. I was blown away. Admittedly, I did not try it through a middleman like C…
-
comment
Comment #48682726
I recently moved from Obsidian to a self-hosted Outline. Primarily because I needed an easy to use solution for sharing a knowledgebase with the team. Obsidian doesn't do team. Not…
-
comment
Comment #48637351
I have the RAM, but not the VRAM. What kind of speed/tps could you expect from a 3090 with 24GBs of RAM? I am somewhat tempted to pick a GPU with 24GBs of RAM.
-
comment
Comment #48612111
> Maybe that's what Jesus used on the people that he healed I think this is what all healers used. They were all way ahead of their time and clearly misunderstood.