biggestriverman
Joined 3 years ago
Karma
17
Submissions
22
Member since
Mar 14
Recent submissions
Comment · 3 hours ago
Last I checked Fable's prices have fallen not risen. Opus 5.5 is as intelligent as Fable 5. I think Anthropic is actually trying to make as good of a model as possible and the advances that their expensive models are getting distilled into the cheaper faster models quickly.
Comment · 6 hours ago
They have not run into a wall. The frontier labs distill their strongest models into their cheaper, faster models.
Having these highly rated models reflects (potentially) the frontier of what they are capable of producing. Essentially its and advertisement and shows directionally where the smaller faster model's capabilities are headed.
Comment · 21 hours ago
I had a similar issue with having to juggle multiple different projects. I found the key thing is to manage your time better and have an agent per project or sub-project with a manager agent you talk to. I wrote my own system to manage this https://github.com/mhalstrom/maximizepm feel free to try it, take the good parts for your own system or whatever
Comment · 1 day ago
I have been working on building an agent and workflow builder that converts chats with claude, chatgpt, gemini or any other chat agent into a workflow or autonomous agent. Its live at toolscaled.com
Also built a free apache 2 agent/ project management system: https://github.com/mhalstrom/maximizepm
Essentially I found the key thing with modern ai assisted development the key thing is to manage your own time/ parallelize without having to switch between chat session as much as possible.
Comment · 4 days ago
I had the same issue. What you need in a management system for your claude sessions.
Comment · 4 days ago
1) 2x Claude Max 20x + Chatgpt Pro
2) I dabble with open-code and hermes especially to try out the free models.
3) I use vanilla claude with an orchestrator on top
4) https://github.com/mhalstrom/maximizepm
5) I use Hermes.
- I use hermes as a "free" agent platforms as you can easily connect your chagpt sub and claude max plans come with api usage you can hook up. In my website https://app.toolscaled.com/docs/agents/how-agents-work/ instead of re-implementing agents and paying API costs you can hook up your automations to push to hermes, claude routines or chatgpt's equlvalent essentially getting agents for free which you can then incrementally convert them to workflows.
Comment · 5 days ago
Hermes is good! I set it up as an option for a local only agent for users of my website! Pretty cool and when you use it with your claude plan api credits or chatgpt essentially "free". Benchmarking it has been pretty interesting. What models have you tried?
Comment · 11 days ago
K2 horizon is the closest to actually releasing everything that I am aware of https://ifm.ai/blog/k2/
Comment · 12 days ago
The way you describe your ideal interview is how I conducted leet code style interviews. Ask a problem with a simple algorithm and then ask extensions until the time ran out. This worked pretty well.
For interviews where candidates are using AI I think you can supercharge this approach, but I do not think there is value in turning it into a code navigation puzzle as there is little value in that can be evaluated in the ~45 min you have for coding in a 1 hr interview slot. Ultimately in many software engineering jobs these days we need to understand how to build quality systems without looking into the underlying system except as necessary. I am not sure how to best evaluate this judgement in an AI assisted interview
Comment · 14 days ago
I used to use this approach as well for managing many agents and myself. I do think the bloat problem is real as well as the need to handle multiple disjoint workstreams.
My solution was to put tasks and their dependencies in a sqlite db. https://github.com/mhalstrom/maximizepm take a look if you're interested
Comment · 21 days ago
You have to design your process for writing code to handle more code than you could ever read. To do this you also have to accept that you will not be able to hand manage all of your agents and all of your projects. The key thing is to figure out how to manage your time better and spend your efforts unblocking your agents.
What I did was build my own process for this: https://github.com/mhalstrom/maximizepm
The main take away is: 1. You need an agent to manage your agents that you mainly interact with. 2. You need a durable way to manage tasks and the dependencies between them. 3. You need agents with multiple roles ie manage, build, review etc 4. You need to manage yourself across projects so any system you build needs to take that into account
Comment · 22 days ago
HOA's are necessary when you have shared resources or have physical connections between units. Sure they make little sense if they exist just to control what color you paint your house but having a agreed upon method to have discussions/ manage resources is important.
Comment · 26 days ago
Its funny the worst code I used to notice was my old code that solved the problem I had faced at the time but had some flaw in the thought process that I later corrected. The same thing applies to generated code. Yes there is a lot of garbage but you can figure out ways to generate better output as you learn the tools and the models get better
Comment · 1 month ago
We live in the real world so individual principles don't make as much of a difference to your community as leaving a decent tip.
https://markhalstrom.com
I am always happy to talk: [email protected]