
Building Audrey (https://nitter.cf/t.co/oSzf0vFyIs) & @domuxdev | prev @fin_ai, @getsolidroad
Dublin
Joined October 2009
- Tweets1.1K
- Following206
- Followers261
- Likes1.5K
Pranav retweeted
I strongly believe that if you don't have product-market fit, you usually need to go more narrow to get it. Longer term you might want product-market fit with multiple niches that add up to something broad. But if you try to take that leap straight to a broader product, you risk building all the features and never solving a specific enough problem for anyone.
Couldn’t have said it better - we really do need a better way to work with the agents
Agent work is the most frustrating and deeply unsatisfying way of working I’ve experienced
It is impossible to get in the flow of a task when you have 3 separate things going on, each step of progress needs you to wait 1-3 mins per task, then needing to parse a big wall of text before you decide the next step
And while you’re waiting for information to become available you inevitably get distracted, making the task even longer because you forget all the things going on in parallel (hence why I’m writing this tweet)
I don’t know what the solution or if there even is one but I wish there was something better than just an endless sidebar of tabs fighting for my limited attention
12
first use of @ClaudeDevs mods: `/use` to set model and effort together
/use opus xhigh sets the model and the effort
/use sonnet sets the model only
/use max sets the effort only
9
this resonates a lot. The paradigm that we have accidentally established of working with agents, needs to shift to something more stable and scalable - while not wrecking our brains! chat wouldn’t take us there.
I think most people multi-tasking with agents could benefit from slowing down
most of the stuff you're doing wont really matter- what's your P0? what would it look like if you gave it your full attention?
15
Video explainers are the way to go I think. With a bit of work videos can be made quite quick and cheap. I've put a lot of the reusable components in a shared library that can be run locally on a mac:
github.com/pranav7/video-exp…
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
if you're moving at a certain pace it's just impossible to drill down to that level of detail on every little change. You're working at a different abstraction level with agents, and reviews need to evolve to assist with that.
Pranav retweeted
I'm sorry I had to make this meme
Let me know if you agree 😅
With Opus 5.5, I think @claudeai is finally back.
Here’s my new video with my honest take and live demos on:
→ Can Opus rival Astra at building 3D scenes like the Golden Gate Bridge?
→ How does Opus handle computer use, UX design, and video editing?
→ Does it finally feel good to talk to again?
This is the most excited I’ve been about Opus since 4.6. Watch my video to understand why: youtu.be/UhBqorWNwlU
this resonates. even if there is no management pressure there is still this weird urge to move fast. pressing enter just one more time, sending claude to just do one more task, it really is horrible. slop is being produced, slop is being consumed. state of the world.
I am done with this shit. It is over. The state of engineering right now is horrible. It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made by Claude Code. Nobody on my team likes this. They are being forced to ship as much as they can. I have heard multiple times from higher management that pushing code is not a bottleneck, so why are we slow? People are working 12 to 13 hours a day just to press enter. Nobody is reading anything. Humans in corporate are doing nothing on their own. Everyone, literally everyone, from an L1 to an L7 engineer here is doing the same thing. Talk to Claude. There is no sense of victory. Nobody is resolving bugs. In reality, nobody is thinking anymore. Everything is done by LLMs. It is so soul-sucking. I would not mind it, to be honest, if we were at least given the time to check out the code and see what is going where. But no, the goal is to just ship. No matter what happens.
slowdown and do some independent thinking away from the model. brainstorming can be useful, but context sits in the models head not yours. take a pen paper instead, and do some brainstorming / slow thinking, and let the context sits in your head. specially for critical product decisions. The models would anyway agree, you’ll be surprised.
1
17
Pranav retweeted
Full credit to @harrybrundage for coining the term Slop Grenade. Let’s make it a thing.
Lazy work used to mean too little output.
Now, with AI, it often means too much and more work for everyone else.
@tobi call it "slop grenades."
A "Slop Grenade" is when you let AI produce the work and pass it on without adding any value (including checking it).
Someone else has to wade through it, catch the mistakes, and clean up the mess.
You save time and look productive but someone else pays for it.
Today Fin officially joins @Salesforce.
It’s a huge moment for us. Fin was the very first AI Agent for CX and started an entirely new category. Today Fin is the highest performing Customer Agent on the market, running on our custom AI models trained specifically for CX, and resolving over 2 million customer issues every week.
Thank you to our customers, teammates, partners, and supporters who’ve been a huge part of our journey so far. Now with Salesforce, Fin will make perfect customer experiences possible for millions more people.
You can read the full press release here. fin.ai/blog/salesforce-compl…
Pranav retweeted
This is brilliant. opusfived.dev



















