Live data from Hacker News

Things we learned about LLMs in 2024

simonwillison.net

331–340 of 615 posts

Re: Things we learned about LLMs in 2024

#331

Some amount of LLM gullibility may be needed. Let's say I have a RAG use case for internal documents about how my business works. I need the LLM to accept what I'm telling it about my business as the truth without questioning it. If I got responses like "this return policy is not correct", LLMs would fail at my use case.

You don’t need gullibility for that, just the ability to work based on premises (hypotheticals) that you feed it. To the LLM it shouldn’t matter if the hypotheticals are real or not. That’s independent of whether the LLMs judges them as plausible or not. Not being able to semi-accurately judge the plausibility of things would make it gullible.

Re: Things we learned about LLMs in 2024

#332
post #30

Earlier quoted context omitted.

Cryptocurrency, at least PoW, the point is indeed to be the most wasteful — a literal Dyson swarm powered Bitcoin would provide exactly the same utility as the BTC network already had in 2010. LLMs (and the image, sound, and movie generating models) are more coincidentally power-hogs — people are at least trying to make them better at fixed compute, and lower compute at fixed quality.

I mean, I appreciate that distinction and don't disagree. And, if this is going to continue being a trend, I think we need more stringent restrictions on what sorts of resources are permitted to be consumed in the power plants that are constructed to meet the needs of hyperscaler data centers. Because whether we're using tons of compute to provide value or not doesn't change that we are using tons of compute and tons…

I think basically everyone should support a carbon tax. It's a really obvious solution that is both environmentally friendly and should be acceptable to free market fanatics because it is explicitly and only taxing a negative externality on the public - it's hard to imagine a more justified tax.

Combined with the increased cost effectiveness of renewables & batteries, & the new build-out of nuclear, it could plausibly speed up the clean energy transition, rather than just disincentivising building out more polluting power plants.

There are two main options for what to do with revenue from a carbon tax. The one that makes the most macroeconomic sense is to use those proceeds to fund subsidies for clean energy roll outs & grid adaptation. You are directly taxing the polluting power grid to fund the construction of a non-polluting power grid. As CO2 emitting industry (and thus carbon tax revenue) declines, we have less required spend on clean energy roll out, so the tax would balance nicely. The downside would be that a carbon tax would increase cost of living and this does nothing about that.

The other option is a disbursement. Give everyone in society a payment directly from the proceeds of the carbon tax. This would offset the regressive aspects of a carbon tax (because that tax would increase consumer costs), and would also act as a sort of auto-stimulus to stop the economy from turning down due to consumption costs increasing. The downside of this is that the clean energy transition happens slower than the above, and that there may be political instability & perverse incentives as people maybe come to rely on this payment that has to go away over the next few decades.

They're both good options. I don't know which is better and I think that's likely something individual countries will probably choose based on their situation. But we do need some sort of way to make those emitting CO2 pay for its negative externalities.

Re: Things we learned about LLMs in 2024

#333
post #256
post #248

I love your breadth-first approach of having an outline at the top.

I wrote custom software for that! https://tools.simonwillison.net/render-markdown - If you paste in some Markdown with ## section headings in it the output will start with a list of links to those headings.

It’s somehow funny to experience the juxtaposition of the technological progress with LLMs and how decades-old basic functions like TOC creation for a blog post still require custom software. ;)

Re: Things we learned about LLMs in 2024

#334
post #243
post #214

Earlier quoted context omitted.

When I started my career in 2010, google was a semi-serious skill. All of the little things that we know how to do now such as ignoring certain sites, lingering on others, and iteratively refining our search queries were not universally known at the time. Experienced engineers often relied on encyclopedic knowledge of their environment or by "reading the manual". In my experience, LLM tools are the same, you ask for…

The problems with that skill is that: * Most existing LLM interfaces are very bad at editing history, instead focusing entirely on appending to history. You can sort of ignore this for one-shot, and this can be properly fixed with additional custom tools, but ... * By the time you refine your input enough to patch over all the errors in the LLM's output for your sensible input, you're bigger than the LLM can actually…

ChatGPT basically lets you edit any of your messages at any point in the conversation, which I definitely use (e.g., if the conversation has gotten into a bad basin, the LLM misunderstood me, etc).

Also ChatGPT has a pretty big context window. Gemini supposedly has the biggest useful context window (~millions of tokens), though I don't have personal experience.

Re: Things we learned about LLMs in 2024

#335
post #243

Earlier quoted context omitted.

The problems with that skill is that: * Most existing LLM interfaces are very bad at editing history, instead focusing entirely on appending to history. You can sort of ignore this for one-shot, and this can be properly fixed with additional custom tools, but ... * By the time you refine your input enough to patch over all the errors in the LLM's output for your sensible input, you're bigger than the LLM can actually…

ChatGPT basically lets you edit any of your messages at any point in the conversation, which I definitely use (e.g., if the conversation has gotten into a bad basin, the LLM misunderstood me, etc). Also ChatGPT has a pretty big context window. Gemini supposedly has the biggest useful context window (~millions of tokens), though I don't have personal experience.

I tend to avoid editing previous messages because it breaks my mental model of the sequence that got me to the current state. That's more of a bias from my goal to do "research" into how these models work though - I'm always trying to maintain the cleanest possible record of what I did so I can learn from the transcript later.

Re: Things we learned about LLMs in 2024

#336

Earlier quoted context omitted.

Every image host and social media app automatically strips EXIF data (for privacy reasons at minimum).

Stenography with a known signature perhaps

Still easily defeated when the scheme is known.

Re: Things we learned about LLMs in 2024

#337
post #278

Earlier quoted context omitted.

I feel bad for your team. Let people work how they want. I wouldn’t not hire someone on the basis of them not using a language server. The creator of the Odin language famously doesn’t use one. He’s says that he, specifically, is faster without one.

No, it’s reasonable. If your team uses Git then it’s a valid question to establish if someone has only worked with Perforce. They didn’t say how heavily they weight the question. (All that said I expect that, soon, experience with the appropriate LLM tooling will be as important as having experience with the language your system is implemented in.)

You hire people based on their fundamental knowledge and the ability to learn, not skills in arbitrary tools and frameworks which come and go every other day. If someone has used Perforce they will be able to get perfectly comfortable with Git by the end of their first week. So not knowing Git is an idiotic reason to reject a skilled developer. Same with programming languages, and just about every other aspect of software development.

Re: Things we learned about LLMs in 2024

#338
post #54

About "people still thinking LLMs are quite useless", I still believe that the problem is that most people are exposed to ChatGPT 4o that at this point for my use case (programming / design partner) is basically a useless toy. And I guess that in tech many folks try LLMs for the same use cases. Try Claude Sonnet 3.5 (not Haiku!) and tell me if, while still flawed, is not helpful. But there is more: a key thing with L…

Is there a way to use this in Jetbrains IDEs? (I've not been impressed with their AI Assistant.) There are a few plugins, but from the reviews they all seem kind of mediocre.

Try Cursor. I’m serious.

Re: Things we learned about LLMs in 2024

#339

> I find the term “agents” extremely frustrating. It lacks a single, clear and widely understood meaning... but the people who use the term never seem to acknowledge that. This 100%. “Agentic” especially as a buzzword can piss off

The software "has agency"? That is, I can entrust it to carry out the task I've described, to completion, without telling it how to perform the task?

Re: Things we learned about LLMs in 2024

#340
post #317
post #314

Earlier quoted context omitted.

Using cloud-based AI is a no-go where I work, for IP and contractual reasons. And on-premises AI is not as capable and more difficult to integrate.

Have you tried the latest open weight models? They're SO MUCH better today than they were even six months ago. If I was in an environment that didn't allow hosted API models I'd absolutely be looking into the various Llama 3 models or Qwen2.5-Coder-32B.

Legal does not even want us running offline models for reasons. I assume that comes down to not knowing what offline-only means, but such is life.
Post reply on HN