ex1fm3ta

Nice is this Jensen Huang response's to Alex Karp recent statement on AI companies stealing people data with a subvention (token price) ? Because building ontologies is Palantir's core business.

They just ruined my startup and started ruining Palantir's business.

ohh boy, guess who's gonna pay for all of this ? Retail investors of course. VCs want to get out quickly hence the crazy valuation, institutionnal investors are already heavily positionned on this through energy, semiconductors and cloud actors ..

it will cost a kidney + Apple would remove the keyboard and sell it back to you for 499$.

I still think those expensive Apple monitors (which even had RAM) were intended to be 'iMac Pros,' but due to stagnant growth in the all-in-one market, they never saw the light of day.

they put some on macbook neos ... But one thing for sure, Apple reserve those flashy colors for entry levels models (Ipad 10/11th gen, Macbook Neo).

if you care about data-retention policy or you have to use european models ...

Automated vulnerability detection existed long before the era of artificial intelligence; many people have been doing this for a long time. All the existing tools and documentation paved the way for what AI is capable of today. Furthermore, undisclosed vulnerabilities still do exist—often discovered by state-sponsored actors who exploit them for opaque purposes (frequently operating outside the legal framework of the country in question).

hmmm not sure about this one, the disease was already there it just available to anynone (not only for state sponsored actors) and the vaccine is globally available at a fraction of what it cost to build it.

unless you are not into home automation you cannot understand how useful this is. Years ago I bought a slightly broken Ipad Pro just to hang it on the wall and control my lights. But I agree the screen size is not right. I cant do shit besides listening to music

Yesss this was needed so much.

it has to be. But you can ClaudeCode it works fine straight out of the box. I need custom workflow because I want to keep my independance in case Anthropic start acting like Uber on pricing.

Nope. Memory and data sharing for training are turned off. (I put 'turned off' in quotes because I don't know if Anthropic really keeps its promise. Often, it is cheaper for companies to break the law and just pay the fine.) I also use adversarial review and the '10th man' rule a lot. In fact, I spend more time planning than executing. I explicitly told Claude never to make a choice without proving it with numbers. By numbers, I mean benchmark results and score-based decisions (for example: 0.5 points for speed, 1 point for libraries, 2 points for documentation). The only thing I doubt are benchmark numbers, because they change depending on the hardware and what you test. Anyway, we always end up choosing PostgreSQL for large projects or SQLite for light ones (which makes sense).

Huawei can do something funny in this new trade war era.

I feel you, I am completely lost with all new ''graph flavoured DB". I keep challenging those (with the help of Opus model ) and the answer is always the same "use progresql".

benchmarks.

what do you want it's the era of vibecoding.

True, noting a nuance doesn't mean ignoring the majority. While there are certainly many Zionists who are not Jewish, the vast majority of them are. A classical case of 'the habit does not make the monk,' but the monk does wear the habit.

More importantly, let's refocus the debate on Israel's actions. Even if 'God the Father' himself were committing these illegal acts, they remain strictly illegal under international human law.

hmmyou should add random delays for each actions. Also add random freezings for each element. This is too clean to be windows.

There you go, the word is dropped. That is exactly how people's mouths are shut whenever they mention the illegal occupation of Gaza. I am actually very aware of the Israeli population who are not aligned with the current actions led by the government. I specifically used double quotes for the expression 'chosen people' because that is exactly what they (Zionists) call themselves. In fact, they really believe their God gave them that land and that they have to retake it, no matter how many of God's creations they have to eliminate. I will leave it at that; I could, of course, add more substance to this subject, but the word 'antisemitism' would quickly come up.

The "chosen people" do not really care about international laws nor UN resolutions. All they care is they own political agenda. This really has to stop by any means necessary. I would start by Trump not giving any money or ammo to this country. Since the US lacks missibles, what a wonderful alibi to not give them more.

Project like this make me excited with AI. You can pretty much custom firmware, tailored for your specific needs. Thanks for this repo. Quick question to the community : why does nobody makes afordable huge e-ink displays ?

It is also worth mentioning that the openpilot AI model is a world model. The way a world model understands physical reality and geometry makes it inherently safer for driving than an LLM, which is essentially a text-based statistical machine with no concept of the physical world.

LLMs are really good at discovering patterns on huge dataset. Google also had similair breakthrough discoveries they stopped marketing them

I am using Pi with anthropic models for plan & execution, openai models for code review and fallback in case I run out of tokens. Also have custom hooks to automatically compact, switch models based on the type of tasks, change effort and custom statusline. Also have custom setup in Pi to calls tools and CLIs instead of relying on mcps. The level of customization I can reach with pi is not really feasiable with codex or claudeCode. By the way anthropic changed it's ToS regarding custom harness: you can`t use their model unless you got extra usage enabled or paying through APi billing, you cant use your subscription anymore. We all guessed what the reason might be. Also codex is open source, I havent really looked at that project yet because Pi fulfill my desires for now.

ioT is nice but only for people who know how to make softwares.

I have mixed feelings about this. Going all-in on Model Context Protocol (MCP) is definitely a bad idea because I noticed the Jira and GitLab MCPs were consuming an excessive amount of tokens. To solve this, I decided to install their respective CLIs instead so we could find a balance and get the best of both worlds. For example, certain MCPs bring too much overhead, especially when they only handle a single task. Instead of letting the coding agent constantly waste resources re-discovering how to fetch a specific work item field, I had Claude recursively run --help on the CLIs and save all possible actions into separate Markdown files. This approach allowed me to build two lightweight plugins that do exactly what an MCP is supposed to do but with significantly less token consumption. If anyone wants to check out the code or use them, I have open-sourced both repositories on my profile:

* * acli-skills: An Atlassian CLI agent skill that maps out Jira commands cleanly. * glab-skills: A GitLab CLI companion built directly for efficient agent workflows. *

To maintain visibility with this setup, we also developed a custom [Claude Code](https://code.claude.com/docs/en/plugins) plugin that streams live updates regarding our background operations directly into the console. That said, MCPs are still extremely useful for rapid prototyping and when we build custom internal tools to speed up development. We found them particularly valuable for:

* * Sampling: Asking the LLM directly to detect entities and summarize log files. * Notifications: Handling long-running tasks that require fetching data from multiple sources. By logging each step and aggregating them via sampling, a single update is sent back to the coding agent, preventing it from spinning up multiple redundant processes. *

I kinda find it funny when I use the advisor on claude code and it agrees with the ideas that the previous model did.

For info: the advisor(s) available are higher end models. For example: you use sonnet, the available advisors are opus and fable. If you use Haiku, the advisor are sonnet, opus and fable.

I mean they all do it right ? Mistral is just the first one to publicly say it.

hmm that's a bit low right now, since you need at least 48Gb of VRAM to be confortable. 32Gb might do it (on quantitized models + optimized) but it would be very slow.