Viewing profile — peterbell_nyc

Wait, did you let the same agent write the tests that wrote the implementation? Or was it that the plan was the wrong way round, and both the generator of code and the generator of…

Wow - so one really good researchers salary/stock grant. I feel like they're underinvesting...

Yeah, this has been my biggest contention with the models everywhere paradigm. I will definitely use a supervisor pattern and advisor pattern for simpler models when I just want to…

LOL - too competent for their own good :(

Also have a workspace as a personal email and ended up getting a personal gmail just to try out the subscriptions before I gave up. I have multiple anthropic and OpenAI max plans. …

I would take the other side of this bet. While I agree that the impact of any given advance is likely to resemble a sigmoid curve, I think there is a material chance of "stacking s…

So many thoughts AI can materially improve PRs - you just have to do it right. Firstly there are not going to be a material number of non-AI patches written in the future. I know s…

The problem isn't the AI - it's the assessments. It used to be that shipping a large, well-researched essay with multiple citations was proof of work. Now it's proof of prompting, …

I auto tune my prompts to a locked model version based on production data used as evals with holdback data. I think the use case for this would be one off interactive prompts? For …

Honestly my goal is to learn how to teach an agent to build a maintainable product, so I'm way more interested in the learnings at the agentic level (how to prompt/direct/manage co…

The agent isn't the hard part - it's the orchestration, skills, research systems, adversarial reviews, dreaming/compounding, context management and all the rest. Plus all the annoy…

This this this! Anyone have something they genuinely like for all of this? For now I'm rolling my own, but I can't believe I won't find a better OSS alternative soon...

Pi is a nice multi-agent wrapper. I use it to wrap my OpenAI max plan calls and my API calls. It takes care of some of the agent plumbing - still need sandbox, orchestrator, compou…

For me the heart of an agentic system is NOT using agents (except when you really have to). Components of a working system include: - Pipelines/recipes to describe multi-step flows…

Thank you. While I do not agree with him on every point (across his corpus - this one was excellent for it's time), it's a delight to re-read a Paul Graham essay. There are a few t…

There's a huge difference between one shot and few shot versus building a robust harness with deterministic and adversarial quality gates. And I'm finding that agents can actually …

Anyone using this headlessly got a read on how much of this an agent could do without human intervention? Would love to have a gut check on "sure, spend the $295 and you'll get som…

Re: the higher ranking plagarism, that stings and makes sense. AEO and SEO are a thing. We need better mechanisms for identifying "root sources" of content - it's something I find …

I do just want to highlight that this is also what humans do. We read a bunch of content online and then use it in our work product. The vast majority of the value that I provide c…

Love the DDD callout. I have explicit steps to review and rate delta's to the ubiquitous language and one of my architectural reviewers will often engage with me about where the bo…

I'm generally in agreement with everyone here. - Some code is ephemeral - it's generated to do the thing, thrown away end of session and the csv was imported successfully (or whate…

For me the distinction is the quality and rigor of your pipeline. Vibe coding: one shot or few shot, smoke test the output, use it until it breaks (or doesn't). Ideal for lightweig…

Helps if you both hand to original agent as strong guidance and then to an adversarial agent as a quality reviewer. The adversarial agent is more likely tro loop the work back if i…

Why crack one website when you can crack all of them? For a well funded (especially nation state) attacker, if $1 in compute and effort returns $2 in ransoms, when it's possible to…

Exactly this. I'm writing my own little orchestrator and memory system and because I have a modest number of workflows, I'm taking the time to specify them deterministically, descr…