Hacker News Reader

Comment by faxmeyourcode | Hacker News Reader

> Filip also told me that he asked Claude to continue on the even case after the odd case had been resolved. “But there after a while it seemed to get stuck. In the end, it was not even able to write and run explore programs correctly anymore, very weird. So I stopped the search.”

Interesting snippet towards the end. I wonder if they were using claude.ai or claude code. Sounds like they ran out of context and entered the "dumb zone."

View on HN

What would be super cool is if this dumb zone could be quantified and surfaced to the user. I've noticed that copilot now has a little circle graph that indicates context use percentage and it changes color based on percentage. I'll bet these are very naive metrics on used tokens vs context availability. I wonder if there could be meta data streamed or sent along with the tokens that could show that you've entered the dumb zone.

In another part he says Filip restarted Claude many times so it seems they are aware of context polution and ways to avoid it (also why they kept telling Claude to write everything to a file). It could just be that Claude was caught between a rock and a hard place; dissapointing the user vs solving a problem it couldn't solve.

Then it needs to do context compacting, otherwise the results become garbage

They mentioned plan document

What is dumb zone?

When the LLMs start compacting they summarize the conversation up to that point using various techniques. Overall a lot of maybe finer points of the work goes missing and can only be retrieved by the LLM being told to search for it explicitly in old logs.

Once you compact, you've thrown away a lot of relevant tokens from your problem solving and they do become significantly dumber as a result. If I see a compaction coming soon I ask it to write a letter to its future self, and then start a new session by having it read the letter.

There are some days where I let the same session compact 4-5 times and just use the letter to future self method to keep it going with enough context because resetting context also resets my brain :)

If you're ever curious in Claude once you compact you can read the new initial prompt after compaction and see how severe it gets cut down. It's very informative of what it forgets and deems not important. For example I have some internal CLIs that are horribly documented so Claude has to try a few flags a few times to figure out specifics and those corrections always get thrown away and it has to relearn them next time it wants to use the CLI. If you notice things like that happening constantly, my move is to codify those things into my CLAUDE.md or lately I've been making a small script or MCP server to run very specific flags of stuff.

> I ask it to write a letter to its future self, and then start a new session by having it read the letter

Is that not one kf the primary technologies for compactification?

I think the point is that you have a better idea of what you want it to remember and even a small hint can have big impact.

Just saying "write up what you know", with no other clues, should not perform any better than generic compaction.

You should do your own experiment when you see compaction about to start use the end of your window to have it write one first, and then let the session compact and compare. I was surprised by how small the compact message is.

When I tell it to write a letter to itself I usually phrase it.

'write a letter to yourself Make notes of any gotchas or any quirks that you learned and make sure to note them down.'

It does get those into the letter but if you check compaction a lot of it is gone.

So you use the letter to itself in addition to the compacted context? I am curious what you ask it to include in the letter and how it is different from a custom instruction passed to /compact?

What prompt do you use for the letter-to-self? I've been trying that technique myself to manually reset context without losing the important parts (e.g. when it has barked up the wrong tree and I'm sensing that misstep might influence its current generation in a pathological way), but I've not had much success.

If the session was something where it struggled and had to do multiple attempts I have it write about 'gotchas' or anything it had to attempt multiple times.

The letters are usually more detailed than what I see in the compacted prompt.

It tends to be pretty manual. I mention the goal of the next session, the current stage of progress, the tests for the next steps, and any skills I want it to load next time.

Having a specific goal seems to make a big difference vs. asking it to summarize the session.

Shouldn't compaction be exactly that letter to its future self?

Look at the compaction prompt yourself. It's in my opinion way too short. (I'm running on Opus 4.5 most of the time at work)

From what my colleague explained to me and I haven't 100% verified it myself is that the beginning and end of the window is the most important to the compaction summary so a lot of the finer details and debugging that will slow down the next session get dropped.

Reply on news.ycombinator.com