Bootvis

The early GPTs were supposedly reasonable at chess but it indeed is not a very useful skill to have for an LLM (Elo 1800 IIRC) which is stronger than most players and for them it could be a useful tool.

Even at higher levels, I think there could be use. The Dvoretsky example on my GitHub is real but it’s not a guarantee you get it and it could just be reiterating from training. What didn’t work for me was forcing it to look at lines in detail, but maybe with larger context and better engineering, you can get the LLM to extract themes from the search tree. With compare and contrast, it could maybe figure out why a move works in one variant and not in another and produce a coherent explanation of this nuance.

I’m not trying this yet because it would take a lot of tokens and I don’t have the time.

Already a year ago I vibe coded Babelfish: https://github.com/bobjansen/Babelfish

It integrates an LLM of your choice with StockFish to analyze games. Back then, the results weren't very good and I abandoned the project but a lot has changed (the LLM's got better and I did too) so maybe it is time to take another stab at it.

In the examples above, that’s really your own loss? There will only be one or two events in your local village, it seems self defeating to ignore what they offer because you don’t like the medium. At least these posters are well laid out and easy to read.

Nothing was derailed, they put pipes on the rails that tricked the system into believing there was a train on the track, shutting it down

GP is saying it’s not a very good one.

Everyone in AI used to know this.

It’s a joke. Mt. Scenery is in the Caribbean, part of the Netherlands but not in the flat mainland.

That’s an API design question. What is the more common use case.

You seem to suggest they did it for benchmarking reasons only. They could use the option there themselves without changing the default so that is unlikely to be the motivation.

Or you know, just better performance for people that know how to use their tool of choice.

I'm working on my typed, fast data frame language Ibex: https://github.com/bobjansen/Ibex

It is usable stand alone but also through an R package:

https://bobjansen.net/faster-than-data-table-introducing-ibe...

It performs better than data.table in my benchmarking on a wide array of tasks and is competitive with Polars on low core counts.

Then you need to read the original. A translator is a product of their time.

So the original link should be: https://artificialanalysis.ai/models/qwen3-8-max?intelligenc...

Even then, this seems a much more marginal win than the headline suggested to me.

Indeed, and this Qwen 3.8 max specific page:

https://artificialanalysis.ai/models/qwen3-8-max

Doesn't have the claim either. Clickbait?

I went to VB.NET first using a previous generation of LLM's (that was quite manual back then) and then from VB.NET to C# or just keeping the VB.NET around worked very well. The code was not highly complex but more than just CRUD. The porting from VB6 to VB.NET included building tests which helped.

Zero. I don’t think that implies the product is bad though. I haven’t marketed it much yet and I’m not great at it either. Even if it is marketed well, integrating the tool into existing workflows would take some effort. This has nothing to do with the suitability of LLMs though.

I have solo built this:

https://github.com/bobjansen/Ibex

Ibex is a usable DSL for table manipulation that is quite fast

https://bobjansen.github.io/Ibex/benchmarks.html

I'm still managing to add more features, such as multithreading. The LLM's do make mistakes but they have gotten better and they tend to self correct these days. I'm also comparing results to mature products such as Polars and DuckDB and the results match.

Rendering followed by OCR and making sure that the computer doesn’t see more or less than the user does. Tricky and computionally more expensive.

Excellent reason to stand up and take a short walk.

For him, the cost of editing was much larger. Condensing your writing in his time meant rewriting it more concisely, requiring strictly more time than collecting his thoughts as he went.

With LLM's, we are in a new state of the world: it can expand any one sentence off hand remark in an essay.

It’s a terrible adage. There are thousands of ways to cheat honest people that place bets. For example, they definitely cheated everyone that only placed bets before June.

He went to prison, served his time, paid his debt to society. There is no need for further punishment.

But do they use it when their homework is due?

I do really like the idea.

But pardon my ignorance, but one could quite easily roll this themselves? Script the hooks and fire off a headless agent with a hook specific prompt.

What is the benefit of realizing the gains for France? They had gold, they still have gold. They don't pay tax on their gold or gains.

> Nice

< Look at the tasteful colouring. The tasteful thickness of it. Oh my God.

On the other hand, others don’t have to adopt, use or like your stuff which would be the reasons to publish it.

One big commit definitely doesn’t help with creating confidence in this project.

Proving her point.

Also for a * b + c ? I know clang tidy wants me to do this but I think it is overkill.

From the Stockfish docs at https://official-stockfish.github.io/docs/stockfish-wiki/Sto....

> Rating Stockfish against a human scale, such as FIDE Elo, has become virtually impossible. The gap in strength is so large that a human player cannot secure the necessary draws or wins for an accurate Elo measurement.

[1]: https://computerchess.org.uk/ccrl/4040/

A large telecommunications satellite operates at about 15kW. A Blackwell GPU consumes 1kW so you would be at 15 Blackwells per satellite. The cooling surface needs to scale linearly so there is little return to scale.

This doesn't sound like a good idea to me.