Guillaume86

What if I create the scarcity by buying all of it? Do you see the problem with the argument?

I would like to agree too but there's a genuine new debate here, with LLMs/agents, the storm of CVEs, supply chain attacks, AI assisted social engineering, etc, some custom code doing the minimal required task might be a better security posture than picking a popular library.

I don't know were it will leave us in the long term and I don't think I'll like the answer.

The most visible productivity gain I've seen from AI is in this kind of cool hoby RE stuff that just wasn't worth the time investment/resources before.

I'm using Ovis a plugin for herdr that adds a web app wich works well enough on web and desktop, but I feel like I'm playing Russian roulette every time I'm updating it and there's updates every day... It's the trust issue of vibe coded apps... Moshi I would feel slightly more confident they won't voluntarily add malware to it and pay attention to security.

Ah sorry didn't open my eyes apparently, still a bit expensive to me but I will probably test drive it then, hope the desktop app is good it's probably even more important than the mobile app to me and does not seem like their focus at all.

Looks good but not way I'm paying a subscription for a tool like this, make me pay a one time fee and give 1 year of updates (90€ would still be too much for me, 50€ I might reconsider).

Not even a link to a gh issue about the root cause? 2 secs Google search: https://github.com/react/react/issues/31819

Population would make more sense.

That's not what the marketing is saying, they keep comparing to their own super old intel models.

It's not bad on release, but it's very frustrating how quick they stop porting new features to one gen old models, basically instantly.

6 months after I bough mine (a 965 FR, top of the line, most recent model at the time), they released the new model 970 with new softwares features they won't port to mine...

Can’t wait until someone's decide to tackle Garmin firmwares updates (porting to older or cheaper models what is purely market segmentation and not hardware limitations).

Thanks for the review, will have to use Claude to interact with MCPs from my phone I guess, it's too bad from experience in personnal projects gemini flash is great at tool calling.

Was looking for this yesterray... US only, English language only apparently, Google still doesn't see the point of global releases unfortunately.

First models of the switch can be jailbroken by connecting pins accessible without disassembly (used to connect joycons), lookup switch jig RCM.

You don't need LLMs for much really but it does lower the bar massively and will make that sort of polish more common in contexts that typically didn't have the resources (time or skill or whatever) to pull it off.

Also underestimate that AI can be used to build a one click type installer (improve massively the install experience). The TitanFall 2 VR mod is an example of such a thing, the install experience is great, the mod is exceptional, it’s a great showcase of what AI coding will bring to the modding scene.

Had a similar experience with OpenRouter, put 10$, goes -50$, I just stopped using it. To their credit support agreed to reset my balance (AI refusal at first, then re-contacted me months later to agree). I'm being more careful now but I shouldn't have to be IMHO.

Eh I know it's a miskate (used both here), but yeah it's a conscious effort for people at my level I guess.

Instruct it to arm a monitor (every hour or so) to wake him up in case of quota or api issue.

My timeline might be wrong (I remember a cloudflare article mentionning the "in MCP" case), but anyway yes there's tools to do it in the harness now and it's the better idea.

Codemode is a fancy name some MCP authors coined for the practice of providing scripting/method chaining for their MCP tools. It's generally implemented by providing some kind of code execution tool, the LLM calls it with a script, and the MCP server runs it in a sandbox.

It's pretty effective because of the reasons you noted, but there's a composability problem since each MCP has its own sandbox and can't call into the other ones.

IIUC Pi offer a workaround for this, the harness runs the sandbox and populate it with the MCP tools, that way the composability problem is solved and every MCP do not have to implement their own sandbox.

I'm running it on my 8 years old 2080ti 11 gb VRAM + 32 gb ram. After tasking fable to optimize the setup for a few nights it's pretty good for some quick funny clips (2min30 for 5s , 5mins for 10s, with reference pics to insert anyone in the clip, not great quality but acceptable for some fun on a phone). I haven't had as much fun with Gen AI since the Stable Diffusion days.

Just took a glance so I may be completely wrong, fell free to ignore, but if I understand correctly, tsrx is just syntactic sugar for normal tsx code and does not enable anything new?

If this is the case: I think introducing tsrx as part of Octane muddies the water a bit and makes me more hesitant to try (even if it is optional).

The idea to make tsx files more readable may be interesting but in that case it should go into its own separate project, and maybe just put a lang toggle in Octane docs and a page about tsrx compat, that way if people are intrigued by the new syntax they can just look it up but the docs stay focused.

Just prompt it that way then, I can get Claude to plow through features for 12h with the correct prompt and setup, no need to destroy the tools that are useful when you want the opposite.

Just prompt it to not ask you questions then, the point of the ask user tool is to collect human input...

OrioleDB seems interesting, not sure it's what you're after but worth a look.

Great way to launder illegally obtained data too.

The EU could/should probably legislate against this, it's bonkers...

3. If your device run on battery, why not using a relatively cheap network call in place of a very power hungry local inference call?

Yes I'm also using it for coding: I often make the agent use WebSearch in the research phase when deciding on a stack or a library or research best/modern practices to do achieve something. As for images I find it super useful to be able to paste snipped screenshots to show the agent when something is wrong in a UI/frontend or just something I can't copy paste easily.