wcoenen

I wonder what would happen if you give the model access to edit the conversation history itself? Would it try to fix the "glitches"?

I don't see it happening.

Isn't it already happening with Cerebras? It's mentioned at the end of OpenAI's GPT 5.6 announcement:

"We're also launching GPT‑5.6 Sol on Cerebras at up to 750 tokens per second in July"

why the EU doesn’t develop something like RuPay

We used to have Europay, which competed with Visa and MasterCard. But it merged with MasterCard in 2002.

The UX problem is elsewhere I think. Many users probably don't realize that the agent's context window is limited, and that clever compaction is happening regularly to make it seem infinite. But that necessarily means the agent has to forget stuff.

As a result, users will keep reusing the same coding or chat session again and again. While it would be better to start fresh for unrelated tasks.

Once you realize how much more efficient solar panels are (compared to plants) at capturing energy from the sun, the next logical question is: could it make sense to synthesize food with the help of electricity from solar power?

There is a company called Solar Foods which is exploring exactly that: they use solar power to produce hydrogen, feed that hydrogen and CO2 to Xanthobacter bacteria, and harvest the produced protein.

https://www.sciencedirect.com/science/article/pii/S016777992...

You don't even need to double the tokens. Tokens are mapped to vectors right at the input of the LLM, so one of the numbers in that vector could be reserved to represent something like "authority". This way information about the source of each individual token can be injected right at the input.

System prompt tokens would get the maximum authority value, and random downloaded data would get the minimum authority value. Tokens from the user prompt could be somewhere in between.

Then train the model with examples that show that system prompts should be respected, and prompt injection attacks should be ignored.

The coal price has a tendency to spike during an energy crisis. The market is more volatile than crude oil. For example, check what happened in 2022.

https://tradingeconomics.com/commodity/coal

It seems the S&P 500 indices only take the free-float shares into account when calculating weights:

S&P DJI’s market cap-weighted indices are float-adjusted – the number of shares outstanding is reduced to exclude closely held shares from the index calculation because such shares are not available to investors.

page 6 of https://www.spglobal.com/spdji/en/documents/methodologies/me...

As far as I know, glyphs are determined by the font and rendering engine. They're not in the Unicode standard.

I was thinking the same thing. Perhaps the trade-off made by evolution is about saving energy?

In that case it shouldn't be a problem to boost the innate immune system, as long as you have surplus calories to spend. But it could be something else entirely.

There is not going to be any shortage of plastics in the medium term.

Shale oil and gas production in the US produces vast quantities of ethane as a byproduct. This ethane is cracked into ethylene, a feedstock for making plastic. There is an oversupply of the stuff.

Thanks! I didn't know it was a known phenomenon. Now I know what to google.

My tinnitus is fortunately not super loud; it's only noticeable when it's relatively quiet, or I'm blocking sounds (with ear plugs, or noise cancelling headphones without input, etc.). So it's not like I habitually blast my ears with loud sine waves out of desperation. But I can imagine it may be different for other readers, so that's a good caveat.

I can play a pure sine wave tone with a tone generator app, and dial the frequency up until it precisely matches my tinnitus. I originally did this just to determine that frequency.

But I noticed a side-effect: if I then turn off the tone generator, my tinnitus would disappear! Unfortunately that effect only lasts for a minute or less, so it is not really practical to get relief this way.

Those "Thumping great Unix boxes" (or indeed even integrated circuits) didn't exist before the sixties. So it seems that technological revolutions do occur from time to time.

EV batteries degrade nowhere near that fast.

https://www.teslarati.com/tesla-battery-life-80-percent-capa...

As far as I understand, the "entity list" you are referring to is part of the "Export Administration Regulations", so it restricts sales from the US to restricted entities, not the other way around.

This comes up in every discussion about demographics. But counterintuitively, there are no examples of financial incentives actually fixing this problem.

For example, in 2022 Hungary was spending 6.2% of GDP on such incentives[1], but this only managed to bring total fertility rate up to about 1.6 [2].

It is the same everywhere else. The real reason fertility has declined since the sixties is because people have access to effective birth control. Nobody wants to be a baby factory.

[1] https://abouthungary.hu/news-in-brief/hungary-to-spend-6-2-o...

[2] https://www.macrotrends.net/global-metrics/countries/hun/hun...

Do you have "Get the latest updates as soon as they're available" enabled? This automatically installs preview releases, so you may unwittingly be doing QA for Microsoft.

When LLMs process tokens, each token is first converted to an embedding vector. (This token to vectors mapping is learned during training.)

Since a token itself carries no information about whether it has "authority" or not, I'm proposing to inject this information in a reserved number in that embedding vector. This needs to be done both during post-training and inference. Think of it as adding color or flavor to a token, so that it is always very clear to the LLM what comes from the system prompt, what comes from the user, and what is random data.

The article talks about strike prices but doesn't provide much context.

The context: this is about bids from wind farm operators to win "contracts for difference" with the Low Carbon Contracts Company, an entity owned by the UK government. It's essentially a subsidy scheme where the wind farms can lock in a specific price per MWh for all the electricity they will produce over a certain period. But only if they bid low enough to be among the winners of the auction.

https://en.wikipedia.org/wiki/Contracts_for_Difference_(UK_e...

you cannot prevent prompt injection

I wonder if might be possible by introducing a concept of "authority". Tokens are mapped to vectors in an embedding space, so one of the dimensions of that space could be reserved to represent authority.

For the system prompt, the authority value could be clamped to maximum (+1). For text directly from the user or files with important instructions, the authority value could be clamped to a slightly lower value, or maybe 0 because the model needs to be balance being helpful against refusing requests from a malicious user. For random untrusted text (e.g. downloaded from the internet by the agent), it would be set to the minimum value (-1).

The model could then be trained to fully respect or completely ignore instructions, based on the "authority" of the text. Presumably it could learn to do the right thing with enough examples.

Citation for a 2018 study with submarine-qualified sailors: https://pubmed.ncbi.nlm.nih.gov/29789085/

Noticeable cognitive impairment starts in the 700-1000ppm range

The US navy failed to detect such effects in submarine crew, even at much higher levels like 10,000 ppm.

Another reason to be skeptical is that exhaled breath is 4% CO2 (40,000 ppm!). Therefore a few thousand extra ppm in the inhaled air should not make much of a difference to the homeostasis mechanisms in our bodies.

But if someone ever got closer to filling up the disk in the past, the chances of contiguous gigabytes are much lower.

By default, Windows automatically defragments filesystems weekly if necessary. It can be configured in the "defragment and optimize drives" dialog.

Meanwhile it feels like half my colleagues don't understand the difference between starting a new Teams conversation ("thread" in Slack), or replying to an existing one. And there's no way to move a message that was posted in the wrong conversation. AFAIK it's the same with Slack threads.

Getting people to post in the "correct" channel faces similar challenges.

Imagine the chaos that would result if we ran everything through Teams.

Increasing the framerate by rendering at a lower resolution + upscaling, or outright generation of extra frames has already been a thing for a few years now. NVidia calls it Deep Learning Super Sampling (DLSS)[1]. AMD's equivalent is called FSR[2].

[1] https://en.wikipedia.org/wiki/Deep_Learning_Super_Sampling

[2] https://en.wikipedia.org/wiki/GPUOpen#FidelityFX_Super_Resol...

The map of planned data centers shows how badly the UK needs to split its single pricing zone for electricity.

There should be more incentive to build data centers in the north, where there is plenty of renewable power but limited capacity to transport that power south.

Germany also has a single pricing zone and a similar north/south problem. It causes expensive curtailment and redispatch operations whenever the grid cannot physically transport the power from north to south the way it was traded.

Geosynchronous orbits do not pass through the Earth's shadow as much as you might think. These orbits sit in the same plane as the equator, which is tilted 23.5 degrees when compared to a line from the sun to the earth.

They still pass through the earth's shadow in the weeks around the equinoxes though. Worst case is about 70 minutes of shadow.

That said, it seems more likely to me that there is no requirement to stay over the same spot on the earth, and a lower altitude sun-synchronous orbit would be used.

For a small amount of water, I would be afraid of flashing the water into steam, and the resulting steam explosion.

If all else fails, banks can generate terabytes of random one-time pad bytes, and then physically transport those on tape to other banks to set up provably secure communication channels that still go over the internet.

It would be a pain to manage but it would be safe from quantum computing.