Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Warp builds self-improving agents on Claude

claude.com

Post reply on HN
Print view View original

51–60 of 62 posts

Re: Warp builds self-improving agents on Claude

#51

Post by conception »

blackqueeriroh wrote: post #45
conception wrote: post #28

Earlier quoted context omitted.

I can answer. 800k.

The arrogance with which so many developers post on HN is really exhausting. I thought the goal was to make the conversation better with each comment, not less contextual or relevant.

I’ve never heard of anyone using it for dev. That said I use it every day for terminal stuff and know a few others that do as well. It’s a bad pivot for them to focus on swe. Devops/sysadmin stuff is pretty amazing with warp. That number is probably closer to 800k.

Re: Warp builds self-improving agents on Claude

#52

Post by bredren »

kouteiheika wrote: post #19

> Engineers complained that their agent made unhelpful comments and produced low-quality output. Do you mean they found Claude's output, full of smoking-guns and honest caveats which are all load-bearing and genuinely bite -- they found it "low-quality" by default? Wow. Color me surprised. /s

Presumably their agent was running an anthropic model, or it wouldn’t have been a partner case study.

So, the premise is a bit of a self-own.

That said, the solution may still have merit regardless of the model that sent them looking.

Re: Warp builds self-improving agents on Claude

#53

Post by threecheese »

hnlmorg wrote: post #32
coder-pm wrote: post #31

My way to do the self improving agents is a CLAUDE.md instructed to write my every decision to the decision log with the relevant context. Agent is using it to challenge me, to make things better and remind me why I did something. It also helps with the invalidation. How is the invalidation handled in Warp? Is it actually self-improving, or just better retrieval?

How to you handle the problem of the decision log becoming so large that it cannot fit inside the context?

The ADR pattern works pretty well without any help; using frontmatter with context cues seems to be better than just descriptive file names, but I haven’t measured it. You do need to make sure every Decision is accurately scoped and is something you want to enforce, because the agent will use it as Law (in sometimes interesting and hilarious ways).

Re: Warp builds self-improving agents on Claude

#57

Post by dTal »

Kinrany wrote: post #41
mentalgear wrote: post #33

Earlier quoted context omitted.

What if it turns out the real 'AGI' was the recording of billions of 'thinking traces' from (paying) users giving feedback and guiding the model - so LLM providers could extract their thinking and privatize it ?

These off topic complaints about capitalism are pointless and exhausting and make HN a worse place.

Right. We must only talk about how to build the Torment Nexus. Never why - too upsetting.

Re: Warp builds self-improving agents on Claude

#58

Post by hnlmorg »

coder-pm wrote: post #37
hnlmorg wrote: post #32

Earlier quoted context omitted.

How to you handle the problem of the decision log becoming so large that it cannot fit inside the context?

Every decision has keywords picked from the predefined list and every time Claude is looking for the decisions made it’s querying it by the keywords (grep). I didn’t ever hit the context window issue with the log, even in a huge projects (months of work). Btw it’s a fair challenge, I will probably hit it one day so something like a “compact” skill for decision log would be useful.

And you build this just with an agents / Claude markdown file?

Re: Warp builds self-improving agents on Claude

#59

Post by hnlmorg »

threecheese wrote: post #53
hnlmorg wrote: post #32

Earlier quoted context omitted.

How to you handle the problem of the decision log becoming so large that it cannot fit inside the context?

The ADR pattern works pretty well without any help; using frontmatter with context cues seems to be better than just descriptive file names, but I haven’t measured it. You do need to make sure every Decision is accurately scoped and is something you want to enforce, because the agent will use it as Law (in sometimes interesting and hilarious ways).

Is there any skills or agents file you’d recommend for working with ADRs?

Re: Warp builds self-improving agents on Claude

#60

Post by threecheese »

hnlmorg wrote: post #59
threecheese wrote: post #53

Earlier quoted context omitted.

The ADR pattern works pretty well without any help; using frontmatter with context cues seems to be better than just descriptive file names, but I haven’t measured it. You do need to make sure every Decision is accurately scoped and is something you want to enforce, because the agent will use it as Law (in sometimes interesting and hilarious ways).

Is there any skills or agents file you’d recommend for working with ADRs?

The LLMs I use know what an ADR is; try asking for one the next time you and the agent come up with a significant one. What I will do is in Claude/agents.md specify where decisions live (usually docs/decisions), and then during inference I’ll ask them to produce one. I am using Claude mostly, and I find that it proactively reads most docs (too many lol), but something like the Pi harness may need explicit cues or a skill.

The “how” is less important though ime; keeping it from getting out of hand is the real trick. Agents will happily file ADRs all day and align their decisions with all of them, and this will cost you $tokens. Yegge’s recent article resonated with me for precisely this reason - I am in no way using these tools at his scale, but am seeing the same behavior. Its sunday, and an agent has asked me to “ratify” an adr twice already :)

Post reply on HN