Context engineering

Join the discussion

• Hacker News
• Why would I believe that any of this works? This is just some blokes idea of what people should do.

  There is no evidence offered. No attempt to measure the benefits.

  by sgt101
• Imagine the gall of someone who just goes on the internet and writes something.
  by dwaltrip
• Most of the inference techniques (what the author calls context engineering design patterns) listed here originally came from the research community, and there are tons of benchmarks measuring their effectiveness, as well as a great deal of research behind what is happening mechanistically with each.

  As the author points out, many of the patterns are fundamentally about in-context learning, and this in particular has been subject to a ton of research from the mechanistic interpretability crew. If you're curious, I think this line of research is fascinating: https://transformer-circuits.pub/2022/in-context-learning-an...

  by calebkaiser
• Are we still calling this things engineering?
  by aeve890
• Engineering how to engineer things might be engineering in some ways.
  by j45
• "professionally trained & legally responsible for the results" is definitely not the same thing as what we used to just call "good at googling".
  by skeeter2020
• There was a good series interviewing people that worked in both software engineering and traditional engineering: https://www.hillelwayne.com/post/are-we-really-engineers/. The conclusion was that yes, a lot of what we do as software engineers is engineering.
  by Zababa
• Yes, and we've also decided that they deserve the title "engineering" more than software engineering does.

  Most engineering disciplines have to deal with tolerances and uncertainty - the real world is non-deterministic.

  Software engineering is easy in comparison because computers always do exactly what you tell them to do.

  The ways LLMs fail (and the techniques you have to use to account for that) have more in common than physical engineering disciplines than software engineering does!

  by simonw
• I'd like a RSS feed of this blog..
  by grigio
• Seems I broke this with a recent change! Reinstated: https://chrisloy.dev/rss.xml
  by chrisloy
• It's available, https://buttondown.com/chrisloy/rss but it's not in sync with the blog, just a single 2024 entry found. :shrug:
  by vladsanchez
• This looks AI generated slop.
  by alecco
• I know this is a bit of a non sequitur but, on my feed just below your comment, some asked for the RSS for this blog. The juxtaposition of the two comments here is just soooo HN
  by Balgair
• Are there any open source examples of good context engineering or agent systems?
  by elteto
• I‘d consider DSPy to be one. While the prompts it is using are not the most elaborate, they are well tested and reliable
  by CjHuber
• Any of the "design patterns" listed in the article will have a ton of popular open source implementations. For structured generation, I think outlines is a particularly cool library, especially if you want to poke around at how constrained decoding works under the hood: https://github.com/dottxt-ai/outlines
  by calebkaiser
• The only thing that passed the test of time,so far is specificity: if you ask for multiple things or vague things, you receive half-baked answers trying to cover all bases. If you ask for specific one thing and describe it, the answer quality goes up;e.g. LLMs creating multi-part content mix up the parts and qualities of them, so e.g. asking for Part 1*specific, will always get a better answer than "list all parts of X"(quality drops with length of list).
  by 8474_s
• There is nothing precise about crafting prompts and context—it's just that, a craft. Even if you do the right thing and check some fuzzy boundary conditions using autoscorers, the model can still change out from beneath you at any point and totally alter the behavior of your system. There is no formal language here. After all, mathematics exists because natural language is notoriously imprecise.

  The article has some good practical tips and it's not on the author but man I really wish we'd stop abusing the term "engineering" in a desperate attempt to stroke our own egos and or convince people to give us money. It's pathetic. Coming up with good inputs to LLMs is more art than science and it's a craft. Call a spade a spade.

  by voidhorse
• "Context crafting", ok, sure. I think a lot of expert researchers (like simonw) would agree.
  by chrisweekly
• I agree with you one hundred percent.

  But: Interestingly, the behavior of LLMs in different contexts is also the subject of scientific research.

  by qrios
• My thoughts exactly. The author is saying we should think strategically about the use of context. Sure. Yes. But for that to qualify as engineering we need solid theory about how context works.

  We don’t have that, yet. For instance experiments show that not all parts of the context window are equally well attended. Imagine trying to engineer a bridge when no one really knows how strong steel is.

  by satisfice
• I think it's fair to question the use of the term "engineering" throughout a lot of the software industry. But to be fair to the author, his focus in the piece is on design patterns that require what we'd commonly call software engineering to implement.

  For example, his first listed design pattern is RAG. To implement such a system from scratch, you'd need to construct a data layer (commonly a vector database), retrieval logic, etc.

  In fact I think the author largely agrees with you re: crafting prompts. He has a whole section admonishing "prompt engineering" as magical incantations, which he differentiates from his focus here (software which needs to be built around an LLM).

  I understand the general uneasiness around using "engineering" when discussing a stochastic model, but I think it's worth pointing out that there is a lot of engineering work required to build the software systems around these models. Writing software to parse context-free grammars into masks to be applied at inference, for example, is as much "engineering" as any other common software engineering project.

  by calebkaiser