Working on some research projects to test Opus 4.7.
The first thing I notice is that it never dives straight into research after the first prompt. It insists on asking follow-up questions. "I'd love to dive into researching this for you. Before I start..." The questions are usually silly, like, "What's your angle on this analysis?" It asks some form of this question as the first follow-up every time.
The second observation is "Adaptive thinking" replaces "Extended thinking" that I had with Opus 4.6. I turned Adaptive off, but I wish I had some confidence that the model is working as hard as possible (I don't want it to mysteriously limit its thinking capabilities based on what it assumes requires less thought. I'd rather control the thinking level. I liked extended thinking). I always ran research prompts with extended thinking enabled on Opus 4.6, and it gave me confidence that it was taking time to get the details right.
The third observation is it'll sit in a silent state of "Creating my research plan" for several minutes without starting to burn tokens. At first I thought this was because I had 2 tabs running a research prompt at the same time, but it later happened again when nothing else was running beside it. Perhaps this is due to high demand from several people trying to test the new model.
Overall, I feel a bit confused. It doesn't seem better than 4.6, and from a research standpoint it might be worse. It seems like it got several different "features" that I'm supposed to learn now.
I had a conversation right during the launch so not fully sure if it was Opus 4.7 but I also noticed the same behavior of asking questions that did not seem particularly useful to me, tho I still prefer that to not asking enough.
Assuming /effort max still gets the best performance out of the model (meaning "ULTRATHINK" is still a step below /effort max, and equivalent to /effort high), here is what I landed on when trying to get Opus 4.7 to be at peak performance all the time in ~/.claude/settings.json:
I'm not interested in new features when the main ones are mysteriously getting worse and worse. I need to have a sense of stability before I get excited about any other features.
100%. Every time I see a Claude Code announcement I sigh when I still can't get the desktop app to fullscreen without fritzing or make a plan and display it consistently. Many papercuts.
PAX ERP - full ERP + CRM for small manufacturers (5-50 people). Accounting, inventory, manufacturing, and CRM in one system. No QuickBooks dependency, no implementation fees, 3-day go-live.
Built it originally for internal use inside a medical device shop. The people running production were the same people responsible for financial accuracy, so every transaction (receiving a PO, issuing materials, completing production) auto-generates GL entries through database triggers. No configuration step, no separate accounting department required.
Current focus: SEO and content - competitor comparison pages (vs Fishbowl, vs Odoo, etc.), compliance landing pages for FDA/ISO 13485, blog posts targeting long-tail manufacturing ERP keywords. Building from 3 backlinks to 20-30.
Competing against Fishbowl (QuickBooks add-on), Odoo (powerful but a lot to configure), and the incumbent answer of spreadsheets + QuickBooks.
The SEO + content angle for niche B2B like manufacturing ERP is underrated - long-tail keywords with clear buyer intent and almost no competition at the content level.
I'm building ad-vertly.ai (marketing autopilots for solo founders) - one thing I've noticed is that the comparison page strategy you're running (vs Fishbowl, vs Odoo) compounds well. Organic search in manufacturing tends to have searchers with high commercial intent. The challenge is keeping up the publishing velocity solo.
Curious - are you doing the content yourself or using any tooling to help? And is your primary conversion from blog → demo request, or something else?
Blogs -> trials/contact seem to be decent, depending on the post. The comparisons are new and inconclusive. LinkedIn posts are minimally tested, but some clicks have come in. Haven't tested X or Meta platforms yet.
I've handled all blog posts so far. Comparisons were passed to the team. They use various tools for research.
Identifying the long-tail keywords with clear buyer intent, and then ranking high for the query, is easier said than done. Blogs are my attempt to catch specific keywords that match what PAX offers. The results are trivial compared to ads, so maybe we still haven't realized the full potential of SEO + content angle.
Thanks! The homepage has a short dashboard + payment video and the before/after section will show two basic dashboards as well. But I agree, we could use more static screenshots, expanding the /docs page with those is on the near-term list.
Feel free to reach out via the website forms to chat about ERP.
This is confusing. ULTRATHINK is a step below /effort max?
ULTRATHINK triggers high effort. /effort max is above high. Calling it ULTRATHINK sounds like it would be the highest mode. If someone has max set and types ULTRATHINK, they're lowering their effort for that turn.
For anyone reading this trying to fix the quality issues, here's what I landed on in ~/.claude/settings.json:
The env field in settings.json persists across sessions without needing /effort max every time.
DISABLE_ADAPTIVE_THINKING is key. That's the system that decides "this looks easy, I'll think less" - and it's frequently wrong. Disabling it gives you a fixed high budget every turn instead of letting the model shortchange itself.
The docs say that CLAUDE_CODE_EFFORT_LEVEL controls adaptive reasoning intensity, and CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING bypasses that entirely in favor of a fixed budget via MAX_THINKING_TOKENS. So setting both is contradictory. If true, disabling adaptive thinking would override what effort level is trying to do.
So if it bypasses, is the optimal setting for performance setting effort level to max, keeping adaptive on? I try to avoid letting the model decide what is unimportant and needs less thought
Nothing super noticeable. I've reached 35% in sessions on the 20x plan. Before these changes, 25-30% was pretty normal. I think these changes are best for people who are just past the 5x usage plan, but might be harder to manage if you already have to throttle usage to stay under limits.
I'd still recommend turning off sub agents entirely because it doesn't seem you can control them with /effort and I always find the output to be better with agents off.
There are several settings in my account relating to Copilot that are locked/enabled with a shield and key icon next to it. Any idea how to disable these settings? It's on the same settings/copilot/features page.
This resonates. We run a medical device manufacturing operation. We used an ERP for years that claimed to specialize in our industry. In practice it was a bloated system designed by people who'd never worked on a manufacturing floor. Bank reconciliation felt like threading a needle in the dark. Simple tasks required five nested menus.
So we built our own. Went live on it a few months ago. The bugs we catch now are ones we catch because we're running real production on it every day. There's no substitute for being the one who has to suffer through your own software.
I built an ERP system called PAX ERP mostly solo for small manufacturers in the USA.
Stack is React, Express, PostgreSQL, all on AWS with a React build pipeline through GitHub Actions. It handles inventory, work orders (MRP), purchasing, GAAP accounting, email campaigns, CRM, shipping (FDX or UPS), etc.
AI has been useful (I use Claude Code, mainly Haiku model), but only if I'm steering it carefully and reviewing everything. It is obviously not great at system design, so I still need to know exactly what I'm trying to do. If I don't it'll often make things overly complicated or focus on edge cases that don't really exist.
It helps a lot with: Writing/refactoring SQL, Making new API routes based on my CRUD template, Creating new frontend components from specs and existing templates, Debugging and explaining unexpected behavior, Integrating third-party APIs (Fedex for shipping, Resend for emails). It understands their documentation easily and helps connect the pieces.
In practice, it feels like a fancy copy/paste (new routes, components) or a helpful assistant. With careful guidance and review, it's a real efficiency boost, especially solo.
I’ve been building a custom ERP/CRM system for the medical device manufacturing company I work at. We went through two commercial ERPs over the years and both were slow and painful to customize, so I started building a simpler replacement.
It handles inventory, work orders (MRP), purchasing, sales orders, accounting, everything we need. After a couple failed attempts earlier on, I rebuilt it with a much simpler stack and it’s now running the company day to day.
Still learning a lot about manufacturing workflows and how much unnecessary complexity most ERP systems accumulate. Now I'm trying to focus on ways that the software can help other companies in a similar ERP boat that we were some years ago.
Completely agree. I found freedom, truth, comfort in Christ. From that relationship with God stems everything we need. “I am the way, the truth, and the life,” and “the truth will set you free.”
The first thing I notice is that it never dives straight into research after the first prompt. It insists on asking follow-up questions. "I'd love to dive into researching this for you. Before I start..." The questions are usually silly, like, "What's your angle on this analysis?" It asks some form of this question as the first follow-up every time.
The second observation is "Adaptive thinking" replaces "Extended thinking" that I had with Opus 4.6. I turned Adaptive off, but I wish I had some confidence that the model is working as hard as possible (I don't want it to mysteriously limit its thinking capabilities based on what it assumes requires less thought. I'd rather control the thinking level. I liked extended thinking). I always ran research prompts with extended thinking enabled on Opus 4.6, and it gave me confidence that it was taking time to get the details right.
The third observation is it'll sit in a silent state of "Creating my research plan" for several minutes without starting to burn tokens. At first I thought this was because I had 2 tabs running a research prompt at the same time, but it later happened again when nothing else was running beside it. Perhaps this is due to high demand from several people trying to test the new model.
Overall, I feel a bit confused. It doesn't seem better than 4.6, and from a research standpoint it might be worse. It seems like it got several different "features" that I'm supposed to learn now.
reply