Philippe Modard @Philmod

Account not used anymore. Find me on https://t.co/wIOPoOgCPf Joined January 2011

Tweets

4K
Followers

6K
Following

2K
Likes

6K

Philippe Modard @Philmod

2 weeks ago

LLMs can't jump philsci-archive.pitt.edu/28024/1/Scient…

0 0 1 118 0

View Details

Philippe Modard @Philmod

2 months ago

I'm already tired of this frontend style we find everywhere now michalmalewicz.medium.com/vibe-coding-is…

0 0 1 86 0

View Details

Philippe Modard @Philmod

2 months ago

"The problem is that LLMs inherently lack the virtue of laziness. Work costs nothing to an LLM." bcantrill.dtrace.org/2026/04/12/the…

0 0 0 69 0

View Details

Philippe Modard @Philmod

2 months ago

@Eurostar I cannot submit a claim on your website, looks like the reCAPTCHA site key is wrong. Smart way to avoid claims indeed :)

2 0 0 212 0

View Details

Philippe Modard @Philmod

3 months ago

Great explanation of the new Google Gemma 4 open source models. newsletter.maartengrootendorst.com/p/a-visual-gui…

0 0 1 80 0

View Details

@yuvadm That seems to work locally to bind a directory as a npm package. In my case, the CI/CD pipeline needs to install the latest package from our private repository. We obviously trust the latest version and don't want to wait 7 days. yarn has `npmMinimumReleaseAgeExclude`,but not npm

0 0 0 70 0

View Details

Philippe Modard @Philmod

3 months ago

@tjlu_artwork @yuvadm Thanks, I was able to do that for `uv`. But I haven't found any solution with `npm`.

0 0 0 23 0

View Details

Philippe Modard @Philmod

3 months ago

@yuvadm My main repo has private dependencies (of my own). Using these tricks means I cannot install the latest versions of my own private packages.

1 0 1 259 1

View Details

Philippe Modard @Philmod

3 months ago

@giffmana I wonder if these models can also be creative at new types of attacks? I'm guessing not if they haven't seen them in their training data?

0 0 1 43 0

View Details

Philippe Modard @Philmod

3 months ago

New compression algorithm that reduces LLM key-value cache memory by at least 6x and delivers up to 8x speedup, all with zero accuracy loss. research.google/blog/turboquan…

0 0 1 58 0

View Details

Philippe Modard @Philmod

3 months ago

litellm package was compromised. futuresearch.ai/blog/litellm-p… Good time for a reminder to pin your packages, and check before upgrades.

0 0 0 131 0

View Details

Philippe Modard @Philmod

3 months ago

@doodlestein @Beetcoin I haven't been able to find the reply you're referring to. That said, I’m just looking at the data—there’s no need for personal insults when we’re just discussing technical performance.

1 0 0 193 0

View Details

Philippe Modard @Philmod

3 months ago

"LLMs optimize for plausibility over correctness. In this case, plausible is about 20,000 times slower than correct." x.com/KatanaLarp/sta…

Hōrōshi バガボンド @KatanaLarp

3 months ago

x.com/i/article/2029…

137 556 5K 1.9M 9K

1 0 1 1K 1

View Details

Philippe Modard @Philmod

3 months ago

Is AI singularity here already? x.com/karpathy/statu…

Andrej Karpathy @karpathy

3 months ago

I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then: - the human iterates on the

1K 4K 28K 11.1M 39K

0 0 2 157 0

View Details

Philippe Modard @Philmod

5 months ago

@ryzerth I got the exact same email.

0 0 0 95 0

View Details

Philippe Modard @Philmod

6 months ago

AI vs human code gen report: AI code creates 1.7x more issues coderabbit.ai/blog/state-of-…

0 0 0 104 0

View Details

Philippe Modard @Philmod

7 months ago

The venue (@lotto_arena) decided to change my @ElectricCallboy concert ticket from the pit to the seats, unilaterally. Really not cool! What's the point of booking my ticket year in advance if I can't enjoy the show the way I'd prefer?