←back to thread

GPT-5.2

(openai.com)
1053 points atgctg | 3 comments | 11 Dec 25 18:04 UTC | HN request time: 0.621s | source
Show context
onraglanroad ◴[11 Dec 25 21:06 UTC] No.46237160[source]▶
I suppose this is as good a place as any to mention this. I've now met two different devs who complained about the weird responses from their LLM of choice, and it turned out they were using a single session for everything. From recipes for the night, presents for the wife and then into programming issues the next day.

Don't do that. The whole context is sent on queries to the LLM, so start a new chat for each topic. Or you'll start being told what your wife thinks about global variables and how to cook your Go.

I realise this sounds obvious to many people but it clearly wasn't to those guys so maybe it's not!

replies(14): >>46237301 #>>46237674 #>>46237722 #>>46237855 #>>46237911 #>>46238296 #>>46238727 #>>46239388 #>>46239806 #>>46239829 #>>46240070 #>>46240318 #>>46240785 #>>46241428 #
1. plaidfuji ◴[11 Dec 25 23:19 UTC] No.46238727[source]▶
It is annoying though, when you start a new chat for each topic you tend to have to re-write context a lot. I use Gemini 3, which I understand doesn’t have as good of a memory system as OpenAI. Even on single-file programming stuff, after a few rounds of iteration I tend to get to its context limit (the thinking model). Either because the answers degrade or it just throws the “oops something went wrong” error. Ok, time to restart from scratch and paste in the latest iteration.

I don’t understand how agentic IDEs handle this either. Or maybe it’s easier - it just resends the entire codebase every time. But where to cut the chat history? It feels to me like every time you re-prompt a convo, it should first tell itself to summarize the existing context as bullets as its internal prompt rather than re-sending the entire context.

replies(1): >>46239006 #
2. int_19h ◴[11 Dec 25 23:48 UTC] No.46239006[source]▶
Agentic IDEs/extensions usually continue the conversation until the context gets close to 80% full, then do the compacting. With both Codex and Claude Code you can actually observe that happening.

That said I find that in practice, Codex performance degrades significantly long before it comes to the point of automated compaction - and AFAIK there's no way to trigger it manually. Claude, on the other hand, has a command for to force compacting, but at the same time I rarely use it because it's so good at managing it by itself.

As far as multiple conversations, you can tell the model to update AGENTS.md (or CLAUDE.md or whatever is in their context by default) with things it needs to remember.

replies(1): >>46240679 #
3. wahnfrieden ◴[12 Dec 25 03:47 UTC] No.46240679[source]▶
Codex has `/compact`