Antony Lewis

System Prompts - Anthropic See updates to the core system prompts on [Claude.ai](https://www.claude.ai) and the Claude [iOS](http://anthropic.com/ios) and [Android](http://anthropic.com/android) apps.

Not that short, eg you can see Claude’s at docs.anthropic.com/en/release-n...

Any data on how much regenerative breaking reduces breaking friction particulates?

Nice alternative would be to go back to first message and initial context and then auto summary of progress made so far.

Can confirm. Over the weekend I took a 15 year old crossword solver Java app, used agent Auto mode to restructure file base for vs code and gradle, modernised all the code and UI, build new multi-platform ci installation builds. After few manual fixes, only left with subtle high-dpi drawing issue.

Impressive model, but the knowledge cutoff date quoted in AI studio is wrong and has been for months. (If you ask it says 2023, which probably also wrong!)

How long does it take to “uncensor” a model a la perplexity/microsoft versions of Deepseek? Would be great to see an effectively automated pipeline to produce western versions quickly. (AFAIK none for Deepseek v3 update yet.)

They might effectively get some of that from chats - every “help me fix my washing machine” chat is a human-proxied interaction with the world? Though very unclear to me how they actually use the very noisy chat data.

GitHub - LaChatterie/Verger Contribute to LaChatterie/Verger development by creating an account on GitHub.

Interesting, how does it compare with Cherry Studio? I just today managed to make an English-based fork of that at github.com/LaChatterie/...

The treachery of images is about to get much worse

The knowledge cutoff in the shot and AI studio seems wrong, seems 2023 not Jan 25. Good model though!

It did one shot one of my toy research-level test maths questions from a recent paper, previously had to do multi-tries with a multi-agent system. But some mixed experience with coding and other things.

So there may be something interesting going on at low redshift, as also indicated by the H0 tension and some odd local densities/flows. But it seems premature to favour poorly-motivated evolving dark energy based on CMB+SN+DESI when this doesn't really help with the other low-redshift oddities.

The stronger evidence for evolving dark energy really comes from adding low-redshift supernovae. Combined with DESI this prefers weird dark energy density that *increases* with time (moving predictions to grey regions in figure).

The beautiful new ACT CMB spectra are also well fit by ΛCDM. The shifts in parameters adding DESI are slightly unusual, but in an expected direction - there was reason to think the Planck results gave an H0 value that was a statistical fluctuation to the low side.

DESI data points compared to ΛCDM model

It's been an interesting few weeks for cosmology. To me, the new precision BAO data points from DESI look like quite a decent fit to the best-fit (DESI+CMB) standard ΛCDM model (central point in this figure). Shifts in the model parameters (open to solid points) are not that large.

Neat, that was fast! ..and interesting it can be worse. Though I was thinking more of PhD level maths conjectures rather than fact statements. I’ve seen outputs that fudge steps to get the output they want (rather like students in exams…)

Some LLMs seem to do wishful thinking, e.g. asked to show X, will tend to favour X over not X. Hypothesis: using trio of “show X”, “show not X” or “show other” and then converging to best answer can give more reliable results than just “show X”.

This was just before dawn, now 7.5% solar this lovely spring morning.

Yes, lite is based on plik and was with sroll2.

If you use more of the Planck TT so much closer to actual joint, the combined constraint look more like you might expect - here compared to joint with your new DESI all in LCDM. (I think ACT TT is pulling things more towards high H_0 low Omega_m compared to their TE).

Could their deep nuclear waste storage be expanded to serve more of Europe? How can Finno-Estonian power transmission be made robust to Baltic sabotage?

Is it really 2/3 total energy, not 2/3 of current electricity?

I think they’ve now sensibly given up on hydrogen for home heating, but what’s the plan to replace gas for the old small terrace houses like mine with not enough space outside for a ground mounted air heat pump?

And more generally the use of wood pellets and the carbon accounting

Contour plot in LCDM of CMB vs DES+BBN

Interesting stuff, congrats - does seem to require phantom DE though! This plot for LCDM doesn't look too bad to me by eye: if the truth were at the intersection, CMB fluctuated 1-2 sigma in the high Omega_m direction (which would not be a surprise, various hints in that direction).

I guess that depends what he means by "small" and "quite a bit"! You don't get big shifts e.g. just by removing bump at L~1460.
Another curious feature of ACT joint is it shifts contours from Planck 2018 in a different direction than going Planck-2018 to Planck-NPIPE (Fig 37).

e.g. could be low L Planck gives low Omega_m, high-L Planck gives high Omega_m, you then combine ACT with just the low part, pulling you to lower Omega_m than either individually (missing the pull up from the part of the sky seen by Planck but not by ACT)?

I noticed that, could be projection effect from high-D contours, but would need full chains to explore. But ACT+Planck is also not a joint likelihood, it's ACT+Planck - Planck(L>600), so there are different sky areas/sensitivities

Would be good to hear how Carbon Border Adjustment Mechanism and similar schemes are going.

Direct power from burning oil etc. Current electricity is only small fraction of total (though you do of course gain efficiency in most cases by electrification) yearbook.enerdata.net/electricity/...