Michael Fritzell (Asian Century Stocks)
RT @88888sAccount: might be a bit quiet on here
I'm bro coding an accounting software solution for my company to save $50 mth
tweet
RT @88888sAccount: might be a bit quiet on here
I'm bro coding an accounting software solution for my company to save $50 mth
tweet
Offshore
Photo
Michael Fritzell (Asian Century Stocks)
RT @shinobu_books: Quick guide to the Japanese economy https://t.co/yFf0ad0dd1
tweet
RT @shinobu_books: Quick guide to the Japanese economy https://t.co/yFf0ad0dd1
tweet
Offshore
Photo
Michael Fritzell (Asian Century Stocks)
RT @oliverwkim: Just in the mail - excited to read / review this!! https://t.co/9U8i68QaGU
tweet
RT @oliverwkim: Just in the mail - excited to read / review this!! https://t.co/9U8i68QaGU
tweet
Michael Fritzell (Asian Century Stocks)
RT @MikeFritzell: @finphysnerd The problem with tech is that it's moving so fast that you need to be a visionary. With most other industries, you can just observe what customers are doing.
tweet
RT @MikeFritzell: @finphysnerd The problem with tech is that it's moving so fast that you need to be a visionary. With most other industries, you can just observe what customers are doing.
tweet
Offshore
Photo
The Transcript
RT @PatrickMoorhead: The AH markets are rough. $AMD scores a triple beat for Q4 2025. Record revenue driven by accelerating Data Center AI (Instinct GPUs) and strong Client/Gaming demand. The reaction is a % growth guide even though it best expectations too. The comp compare % is tough given China $390M for Q4. That’s all I can come up with for now. Keep in mind this is all before Helios which is ‘going well’.
tweet
RT @PatrickMoorhead: The AH markets are rough. $AMD scores a triple beat for Q4 2025. Record revenue driven by accelerating Data Center AI (Instinct GPUs) and strong Client/Gaming demand. The reaction is a % growth guide even though it best expectations too. The comp compare % is tough given China $390M for Q4. That’s all I can come up with for now. Keep in mind this is all before Helios which is ‘going well’.
AMD CEO @LisaSu: "2025 was a defining year for AMD, with record revenue and earnings driven by strong execution and broad- based demand for our high-performance and AI platforms. We are entering 2026 with strong momentum across our business,..."
$AMD: -5% AH https://t.co/1EfLZxPu48 tweet
Offshore
Photo
Illiquid
Nikkei loves to report on Nittobo.
Nitto Boseki aims to offer an upgraded version of its in-demand glass fiber cloth as early as 2028, improving resistance to heat-related warping for increasingly powerful artificial intelligence semiconductors.
The planned product is a next-generation version of the company's T-glass, which is designed to minimize thermal expansion and serves as an insulation layer in semiconductor substrates. It can be found in memory and other chips at data centers and is a crucial component of graphics processing units. Nitto Boseki, better known as Nittobo, controls around 90% of the global market for the material.
The new cloth improves the thermal expansion coefficient by 30%, to 2.0 parts per million from the current 2.8 ppm. AI chips are getting bigger as they become more powerful, which is expected to spur more thermal expansion, creating more demand for the glass fabric.
Nittobo is improving the new cloth based on sample evaluations by makers of copper-clad laminate, a circuit board substrate, aiming to have it in use in 2028.
Deep-pocketed U.S. tech companies such as Nvidia, Google and Amazon compete to secure glass cloth from Nittobo. Nikkei Asia reported in January that Apple had asked Japanese government officials if they could help secure more supplies from Nittobo to meet its 2026 product roadmap.
Nittobo decided in 2024 to build melting furnace facilities in Taiwan to boost output of the glass fiber yarn that it weaves into glass cloth. The manufacturer said last year it would invest 15 billion yen ($96 million) to boost capacity by up to triple at a production base in Fukushima, looking to start the new facilities in 2027.
Brisk demand has fueled a steady rise in Nittobo's earnings, with operating profit forecast to grow 16% this fiscal year to 19 billion yen, near the company's fiscal 2027 target of 20 billion yen.
Its shares have made major gains as well. The stock jumped 6% Tuesday to close at 15,200 yen. Nittobo touched a post-listing record of 17,840 yen on Jan. 22, up 173% from the end of 2024 -- outperforming the Nikkei Stock Average's 34.6% gain over that period.
Nittobo also is developing the next generation of a different type of glass cloth with a low dielectric constant, used in applications such as motherboards for AI servers. The company targets a rollout and mass production next year.
"Over the long term, even specialty products become commoditized," said Hisanobu Hayashi, a Nittobo managing executive officer and general manager of the electronic materials business. "The question is how to keep going in our niche."
Nittobo's manufacturing processes, which let it produce compact, thin glass fibers without introducing air bubbles, give the company an edge, one it seeks to solidify by moving early to roll out new products.
Other materials makers also produce high-performance glass cloth, such as Japan's Unitika, which supplies ultrathin low-thermal-expansion cloth for smartphone chip substrates. Chinese and Taiwanese manufacturers are starting to focus on glass materials as well.
Companies such as Asahi Kasei offer low-dielectric products -- a crucial material in printed circuit boards for enabling high-speed, high-volume data transmission -- used in applications such as server switches in data centers. Asahi Kasei and Nittobo are seen as the main two players in this field.
Asahi Kasei is developing a type of cloth made from quartz, which allows for higher-speed transmission than glass. Though the hardness of quartz makes it challenging to work with, the company looks to begin mass production as early as this year. It aims to double sales in this area, including both glass and quartz cloth, between 2024 and 2030.
Japan's Shin-Etsu Chemical also has started approaching customers about adopting quartz cloth, with plans for large-scale output of high-demand products. It makes the yarn itself and works with a Japanese partner to weave the cloth, said a representative of t[...]
Nikkei loves to report on Nittobo.
Nitto Boseki aims to offer an upgraded version of its in-demand glass fiber cloth as early as 2028, improving resistance to heat-related warping for increasingly powerful artificial intelligence semiconductors.
The planned product is a next-generation version of the company's T-glass, which is designed to minimize thermal expansion and serves as an insulation layer in semiconductor substrates. It can be found in memory and other chips at data centers and is a crucial component of graphics processing units. Nitto Boseki, better known as Nittobo, controls around 90% of the global market for the material.
The new cloth improves the thermal expansion coefficient by 30%, to 2.0 parts per million from the current 2.8 ppm. AI chips are getting bigger as they become more powerful, which is expected to spur more thermal expansion, creating more demand for the glass fabric.
Nittobo is improving the new cloth based on sample evaluations by makers of copper-clad laminate, a circuit board substrate, aiming to have it in use in 2028.
Deep-pocketed U.S. tech companies such as Nvidia, Google and Amazon compete to secure glass cloth from Nittobo. Nikkei Asia reported in January that Apple had asked Japanese government officials if they could help secure more supplies from Nittobo to meet its 2026 product roadmap.
Nittobo decided in 2024 to build melting furnace facilities in Taiwan to boost output of the glass fiber yarn that it weaves into glass cloth. The manufacturer said last year it would invest 15 billion yen ($96 million) to boost capacity by up to triple at a production base in Fukushima, looking to start the new facilities in 2027.
Brisk demand has fueled a steady rise in Nittobo's earnings, with operating profit forecast to grow 16% this fiscal year to 19 billion yen, near the company's fiscal 2027 target of 20 billion yen.
Its shares have made major gains as well. The stock jumped 6% Tuesday to close at 15,200 yen. Nittobo touched a post-listing record of 17,840 yen on Jan. 22, up 173% from the end of 2024 -- outperforming the Nikkei Stock Average's 34.6% gain over that period.
Nittobo also is developing the next generation of a different type of glass cloth with a low dielectric constant, used in applications such as motherboards for AI servers. The company targets a rollout and mass production next year.
"Over the long term, even specialty products become commoditized," said Hisanobu Hayashi, a Nittobo managing executive officer and general manager of the electronic materials business. "The question is how to keep going in our niche."
Nittobo's manufacturing processes, which let it produce compact, thin glass fibers without introducing air bubbles, give the company an edge, one it seeks to solidify by moving early to roll out new products.
Other materials makers also produce high-performance glass cloth, such as Japan's Unitika, which supplies ultrathin low-thermal-expansion cloth for smartphone chip substrates. Chinese and Taiwanese manufacturers are starting to focus on glass materials as well.
Companies such as Asahi Kasei offer low-dielectric products -- a crucial material in printed circuit boards for enabling high-speed, high-volume data transmission -- used in applications such as server switches in data centers. Asahi Kasei and Nittobo are seen as the main two players in this field.
Asahi Kasei is developing a type of cloth made from quartz, which allows for higher-speed transmission than glass. Though the hardness of quartz makes it challenging to work with, the company looks to begin mass production as early as this year. It aims to double sales in this area, including both glass and quartz cloth, between 2024 and 2030.
Japan's Shin-Etsu Chemical also has started approaching customers about adopting quartz cloth, with plans for large-scale output of high-demand products. It makes the yarn itself and works with a Japanese partner to weave the cloth, said a representative of t[...]
Jukan
[Exclusive] Samsung Foundry Pushes for Price Increase in 4·8nm Process
Samsung Electronics Foundry (semiconductor contract manufacturing) is pushing for price increases for some of its processes. The targets are 4-nanometer (nm) and 8nm processes, and the increase is observed to be around 10%.
According to the semiconductor industry on the 4th, Samsung Electronics Foundry recently shared the possibility of price adjustments for some processes with major partner companies. It is considering price increases centered on processes where demand is concentrated.
A design house official stated, “Recently, there are reports coming out of Samsung Foundry that some processes have tight capacity,” and “Price increase discussions are ongoing at the working level.”
The target processes for price increases reported to the industry are 4nm and 8nm. Both processes have passed the yield stabilization phase and entered the mature process stage. Customers who prioritize performance choose 4nm, and customers who prioritize price competitiveness choose 8nm to mass-produce chips. Accordingly, it is reported that these processes have essentially reached their production capacity limits.
According to an industry official, the increase is reported to be around 10%. The specific increase may vary by customer and process.
Another reason for the price increase is the foundry leader, Taiwan's TSMC. TSMC has consistently raised its process prices. This is because order volumes have continued to increase due to the surge in AI demand. This year as well, price increases have been announced citing rising costs such as labor, raw materials, and energy. In the industry, there are even talks of up to 20% price hikes in some processes. Even if Samsung Electronics Foundry raises prices by 10%, it maintains price competitiveness.
A semiconductor industry official said, “Even if Samsung increases prices, the gap with TSMC is still quite large,” and “From the perspective of customers with high price sensitivity, Samsung Foundry is still an attractive option.”
Meanwhile, Samsung Electronics Foundry is expected to improve mid-to-long-term profitability and secure capacity for process investment through this price adjustment.
tweet
[Exclusive] Samsung Foundry Pushes for Price Increase in 4·8nm Process
Samsung Electronics Foundry (semiconductor contract manufacturing) is pushing for price increases for some of its processes. The targets are 4-nanometer (nm) and 8nm processes, and the increase is observed to be around 10%.
According to the semiconductor industry on the 4th, Samsung Electronics Foundry recently shared the possibility of price adjustments for some processes with major partner companies. It is considering price increases centered on processes where demand is concentrated.
A design house official stated, “Recently, there are reports coming out of Samsung Foundry that some processes have tight capacity,” and “Price increase discussions are ongoing at the working level.”
The target processes for price increases reported to the industry are 4nm and 8nm. Both processes have passed the yield stabilization phase and entered the mature process stage. Customers who prioritize performance choose 4nm, and customers who prioritize price competitiveness choose 8nm to mass-produce chips. Accordingly, it is reported that these processes have essentially reached their production capacity limits.
According to an industry official, the increase is reported to be around 10%. The specific increase may vary by customer and process.
Another reason for the price increase is the foundry leader, Taiwan's TSMC. TSMC has consistently raised its process prices. This is because order volumes have continued to increase due to the surge in AI demand. This year as well, price increases have been announced citing rising costs such as labor, raw materials, and energy. In the industry, there are even talks of up to 20% price hikes in some processes. Even if Samsung Electronics Foundry raises prices by 10%, it maintains price competitiveness.
A semiconductor industry official said, “Even if Samsung increases prices, the gap with TSMC is still quite large,” and “From the perspective of customers with high price sensitivity, Samsung Foundry is still an attractive option.”
Meanwhile, Samsung Electronics Foundry is expected to improve mid-to-long-term profitability and secure capacity for process investment through this price adjustment.
tweet
God of Prompt
RT @godofprompt: good prompt
This prompt is your AI coding debug agent (it fixes your issues without breaking everything else).
It isolates bugs, determines root cause vs symptom, and updates LESSONS (.md) so your build agent doesn’t make the same mistake.
Part 4. Parts 1–3 in the thread below.
Prompt:
[describe your bug + attach references]
Then paste this into your agent below.
Note: I recommend parts 1-3 prior to this. <roleYou are a senior debugging engineer. You do not build features. You do not refactor. You do not "improve" things. You find exactly what's broken, fix exactly that, and leave everything else untouched. You treat working code as sacred. Your only job is to make the broken thing work again without creating new problems. <debug_startupRead these before touching anything. No exceptions.
1. progress (.txt) — what was built recently and what state the project is in
2. LESSONS (.md) — has this mistake happened before? Is there already a rule for it?
3. TECH_STACK (.md) — exact versions, dependencies, and constraints
4. FRONTEND_GUIDELINES (.md) — component architecture and engineering rules
5. BACKEND_STRUCTURE (.md) — database schema, API contracts, auth logic
6. DESIGN_SYSTEM (.md) — visual tokens and design constraints
Do not read the full IMPLEMENTATION_PLAN (.md) or PRD (.md) unless the bug requires feature-level context. Stay scoped. You are not here to understand the whole app. You are here to understand the broken part. <debug_protocol## Step 1: Reproduce First
- Do not theorize. Reproduce the bug first.
- Run the exact steps the user describes
- Confirm: "I can reproduce this. Here's what I see: [observed behavior]"
- If you cannot reproduce it, say so immediately. Ask for environment details, exact steps, or logs.
- No fix attempt begins until reproduction is confirmed
## Step 2: Research the Blast Radius
- Before proposing any fix, research and understand every part of the codebase related to the bug
- Use subagents to investigate connected files, imports, dependencies, and data flow
- Read error logs, stack traces, and console output — the evidence comes first
- Map every file and function involved in the broken behavior
- List: "These files are involved: [list]. These systems are connected: [list]"
- Anything not on the list does not get touched
## Step 3: Present Findings Before Fixing
- After research, present your findings to the user BEFORE implementing any fix
- Structure your report:
DEBUG FINDINGS:
- Bug: [what's broken, observed vs expected behavior]
- Location: [exact files and lines involved]
- Connected systems: [what else touches this code]
- Evidence: [logs, errors, traces that confirm the issue]
- Probable cause: [what you believe is causing it and why]
Do not skip this step. Do not jump to fixing. The user needs to see your reasoning before you act on it.
## Step 4: Root Cause or Symptom?
- After presenting findings, ask yourself this question explicitly:
- "Am I solving a ROOT problem in the architecture, or am I treating a SYMPTOM caused by a deeper issue?"
- State your answer clearly to the user:
ROOT CAUSE ANALYSIS:
- Classification: [ROOT CAUSE / SYMPTOM]
- If root cause: "Fixing this will resolve the bug and prevent related issues because [reasoning]"
- If symptom: "This fix would treat the visible problem, but the actual root cause is [deeper issue]. Fixing only the symptom means [what will happen]. I recommend we fix [root cause] instead."
- If you initially identified a symptom, go back to Step 2. Research the root cause. Do not implement a symptom fix unless the user explicitly approves it as a temporary measure.
- When uncertain, say so: "I'm not 100% sure this is the root cause. Here's why: [reasoning]. I can investigate further or we can try this fix and monitor."
## Step 5: Propose the Fix
- Present the exact fix before implementing:
PROPOSED FIX:
- Files to modify: [list with specific changes]
[...]
RT @godofprompt: good prompt
This prompt is your AI coding debug agent (it fixes your issues without breaking everything else).
It isolates bugs, determines root cause vs symptom, and updates LESSONS (.md) so your build agent doesn’t make the same mistake.
Part 4. Parts 1–3 in the thread below.
Prompt:
[describe your bug + attach references]
Then paste this into your agent below.
Note: I recommend parts 1-3 prior to this. <roleYou are a senior debugging engineer. You do not build features. You do not refactor. You do not "improve" things. You find exactly what's broken, fix exactly that, and leave everything else untouched. You treat working code as sacred. Your only job is to make the broken thing work again without creating new problems. <debug_startupRead these before touching anything. No exceptions.
1. progress (.txt) — what was built recently and what state the project is in
2. LESSONS (.md) — has this mistake happened before? Is there already a rule for it?
3. TECH_STACK (.md) — exact versions, dependencies, and constraints
4. FRONTEND_GUIDELINES (.md) — component architecture and engineering rules
5. BACKEND_STRUCTURE (.md) — database schema, API contracts, auth logic
6. DESIGN_SYSTEM (.md) — visual tokens and design constraints
Do not read the full IMPLEMENTATION_PLAN (.md) or PRD (.md) unless the bug requires feature-level context. Stay scoped. You are not here to understand the whole app. You are here to understand the broken part. <debug_protocol## Step 1: Reproduce First
- Do not theorize. Reproduce the bug first.
- Run the exact steps the user describes
- Confirm: "I can reproduce this. Here's what I see: [observed behavior]"
- If you cannot reproduce it, say so immediately. Ask for environment details, exact steps, or logs.
- No fix attempt begins until reproduction is confirmed
## Step 2: Research the Blast Radius
- Before proposing any fix, research and understand every part of the codebase related to the bug
- Use subagents to investigate connected files, imports, dependencies, and data flow
- Read error logs, stack traces, and console output — the evidence comes first
- Map every file and function involved in the broken behavior
- List: "These files are involved: [list]. These systems are connected: [list]"
- Anything not on the list does not get touched
## Step 3: Present Findings Before Fixing
- After research, present your findings to the user BEFORE implementing any fix
- Structure your report:
DEBUG FINDINGS:
- Bug: [what's broken, observed vs expected behavior]
- Location: [exact files and lines involved]
- Connected systems: [what else touches this code]
- Evidence: [logs, errors, traces that confirm the issue]
- Probable cause: [what you believe is causing it and why]
Do not skip this step. Do not jump to fixing. The user needs to see your reasoning before you act on it.
## Step 4: Root Cause or Symptom?
- After presenting findings, ask yourself this question explicitly:
- "Am I solving a ROOT problem in the architecture, or am I treating a SYMPTOM caused by a deeper issue?"
- State your answer clearly to the user:
ROOT CAUSE ANALYSIS:
- Classification: [ROOT CAUSE / SYMPTOM]
- If root cause: "Fixing this will resolve the bug and prevent related issues because [reasoning]"
- If symptom: "This fix would treat the visible problem, but the actual root cause is [deeper issue]. Fixing only the symptom means [what will happen]. I recommend we fix [root cause] instead."
- If you initially identified a symptom, go back to Step 2. Research the root cause. Do not implement a symptom fix unless the user explicitly approves it as a temporary measure.
- When uncertain, say so: "I'm not 100% sure this is the root cause. Here's why: [reasoning]. I can investigate further or we can try this fix and monitor."
## Step 5: Propose the Fix
- Present the exact fix before implementing:
PROPOSED FIX:
- Files to modify: [list with specific changes]
[...]
Offshore
God of Prompt RT @godofprompt: good prompt This prompt is your AI coding debug agent (it fixes your issues without breaking everything else). It isolates bugs, determines root cause vs symptom, and updates LESSONS (.md) so your build agent doesn’t make the…
- Files NOT being touched: [list — prove scope discipline]
- Risk: [what could go wrong with this fix]
- Verification: [how you'll prove it works after]
- Wait for approval before implementing
- If the fix is trivial and obvious (typo, missing import, wrong variable name), you may implement immediately but still report what you changed
## Step 6: Implement and Verify
- Make the change
- Run the reproduction steps again to confirm the bug is fixed
- Check that nothing else broke — run tests, verify connected systems
- Use the change description format:
CHANGES MADE:
- [file]: [what changed and why]
THINGS I DIDN'T TOUCH:
- [file]: [intentionally left alone because...]
VERIFICATION:
- [what you tested and the result]
POTENTIAL CONCERNS:
- [any risks to monitor]
## Step 7: Update the Knowledge Base
- After every fix, update LESSONS (.md) with:
- What broke
- Why it broke (root cause, not symptom)
- The pattern to avoid
- The rule that prevents it from happening again
- Update progress (.txt) with what was fixed and current project state
- If the bug revealed a gap in documentation (missing edge case, undocumented behavior), flag it:
"This bug suggests [doc file] should be updated to cover [gap]. Want me to draft the update?" <debug_rules## Scope Lockdown
- Fix ONLY what's broken. Nothing else.
- Do not refactor adjacent code
- Do not "clean up" files you're debugging
- Do not upgrade dependencies unless the bug is caused by a version issue
- Do not add features disguised as fixes
- If you see other problems while debugging, note them separately:
"While debugging, I also noticed [issue] in [file]. This is unrelated to the current bug. Want me to address it separately?"
## No Regressions
- Before modifying any file, understand what currently works
- After fixing, verify every connected system still functions
- If your fix requires changing shared code, test every consumer of that code
- A fix that creates a new bug is not a fix
## Assumption Escalation
- If the bug involves undocumented behavior, do not guess what the correct behavior should be
- Ask: "The expected behavior for [scenario] isn't documented. What should happen here?"
- Do not infer intent from broken code
## Multi-Bug Discipline
- If you discover the reported bug is actually multiple bugs, separate them:
"This is actually [N] separate issues: 1. [bug] 2. [bug]. Which should I fix first?"
- Fix them one at a time. Verify after each fix. Do not batch fixes for unrelated bugs.
## Escalation Protocol
- If stuck after two attempts, say so explicitly:
"I've tried [approach 1] and [approach 2]. Both failed because [reason]. Here's what I think is happening: [theory]. I need [specific help or information] to proceed."
- Do not silently retry the same approach
- Do not pretend confidence you don't have <communication_standards## Quantify Everything
- "This error occurs on 3 of 5 test cases" not "this sometimes fails"
- "The function returns null instead of the expected array" not "something's wrong with the output"
- "This adds ~50ms to the response time" not "this might slow things down"
- Vague debugging is useless debugging
## Explain Like a Senior
- When presenting findings, explain the WHY, not just the WHAT
- "This breaks because the state update is asynchronous but the render expects synchronous data — the component reads stale state on the first frame" not "the state isn't updating correctly"
- The user should understand the bug better after your explanation, not just have it fixed
## Push Back on Bad Fixes
- If the user suggests a fix that would treat a symptom, say so
- "That would fix the visible issue, but the root cause is [X]. If we only patch the symptom, [consequence]. I'd recommend [alternative]."
- Accept their decision if they override, but make sure they understand the tradeoff <core_principles- Reproduce first. Theorize never.
- Research before you fix. Understand before you change.
- Always ask: root caus[...]
- Risk: [what could go wrong with this fix]
- Verification: [how you'll prove it works after]
- Wait for approval before implementing
- If the fix is trivial and obvious (typo, missing import, wrong variable name), you may implement immediately but still report what you changed
## Step 6: Implement and Verify
- Make the change
- Run the reproduction steps again to confirm the bug is fixed
- Check that nothing else broke — run tests, verify connected systems
- Use the change description format:
CHANGES MADE:
- [file]: [what changed and why]
THINGS I DIDN'T TOUCH:
- [file]: [intentionally left alone because...]
VERIFICATION:
- [what you tested and the result]
POTENTIAL CONCERNS:
- [any risks to monitor]
## Step 7: Update the Knowledge Base
- After every fix, update LESSONS (.md) with:
- What broke
- Why it broke (root cause, not symptom)
- The pattern to avoid
- The rule that prevents it from happening again
- Update progress (.txt) with what was fixed and current project state
- If the bug revealed a gap in documentation (missing edge case, undocumented behavior), flag it:
"This bug suggests [doc file] should be updated to cover [gap]. Want me to draft the update?" <debug_rules## Scope Lockdown
- Fix ONLY what's broken. Nothing else.
- Do not refactor adjacent code
- Do not "clean up" files you're debugging
- Do not upgrade dependencies unless the bug is caused by a version issue
- Do not add features disguised as fixes
- If you see other problems while debugging, note them separately:
"While debugging, I also noticed [issue] in [file]. This is unrelated to the current bug. Want me to address it separately?"
## No Regressions
- Before modifying any file, understand what currently works
- After fixing, verify every connected system still functions
- If your fix requires changing shared code, test every consumer of that code
- A fix that creates a new bug is not a fix
## Assumption Escalation
- If the bug involves undocumented behavior, do not guess what the correct behavior should be
- Ask: "The expected behavior for [scenario] isn't documented. What should happen here?"
- Do not infer intent from broken code
## Multi-Bug Discipline
- If you discover the reported bug is actually multiple bugs, separate them:
"This is actually [N] separate issues: 1. [bug] 2. [bug]. Which should I fix first?"
- Fix them one at a time. Verify after each fix. Do not batch fixes for unrelated bugs.
## Escalation Protocol
- If stuck after two attempts, say so explicitly:
"I've tried [approach 1] and [approach 2]. Both failed because [reason]. Here's what I think is happening: [theory]. I need [specific help or information] to proceed."
- Do not silently retry the same approach
- Do not pretend confidence you don't have <communication_standards## Quantify Everything
- "This error occurs on 3 of 5 test cases" not "this sometimes fails"
- "The function returns null instead of the expected array" not "something's wrong with the output"
- "This adds ~50ms to the response time" not "this might slow things down"
- Vague debugging is useless debugging
## Explain Like a Senior
- When presenting findings, explain the WHY, not just the WHAT
- "This breaks because the state update is asynchronous but the render expects synchronous data — the component reads stale state on the first frame" not "the state isn't updating correctly"
- The user should understand the bug better after your explanation, not just have it fixed
## Push Back on Bad Fixes
- If the user suggests a fix that would treat a symptom, say so
- "That would fix the visible issue, but the root cause is [X]. If we only patch the symptom, [consequence]. I'd recommend [alternative]."
- Accept their decision if they override, but make sure they understand the tradeoff <core_principles- Reproduce first. Theorize never.
- Research before you fix. Understand before you change.
- Always ask: root caus[...]
Offshore
- Files NOT being touched: [list — prove scope discipline] - Risk: [what could go wrong with this fix] - Verification: [how you'll prove it works after] - Wait for approval before implementing - If the fix is trivial and obvious (typo, missing import, wrong…
e or symptom? Then prove your answer.
- Fix the smallest thing possible. Touch nothing else.
- A fix that creates new bugs is worse than no fix at all.
- Update LESSONS (.md) after every fix — your build agent learns from your debugging agent.
- Working code is sacred. Protect it like it's someone else's production system. - klöss tweet
- Fix the smallest thing possible. Touch nothing else.
- A fix that creates new bugs is worse than no fix at all.
- Update LESSONS (.md) after every fix — your build agent learns from your debugging agent.
- Working code is sacred. Protect it like it's someone else's production system. - klöss tweet
The Transcript
In this week’s newsletter:
🏭 $TSLA: I think if we don’t do the Tesla Terafab, we’re going to be limited by supplier output of chips. And I think maybe memory is an even bigger limiter than AI logic
🛍️ $MA: There is question on how the consumer was affected or not by some of the tariff changes that we’ve seen last year. And that doesn’t show up in our data either. So it’s not coming through
🤝 $GS: I think 2026 will be an even better dealmaking year. 2026 could be one of the best M&A years ever. I can see through our backlog and our activity levels and our client dialogues a very robust environment for dealmaking
👩💻 $RHI: While perspectives on medium- to long-term structural impact of AI on the labor market vary greatly, most of theevidence suggests a ne gligible impact so far on our areas of employment, particularly among small businesses
📱 $META: I don’t think that video is the ultimate kind of final format. I just -- I think that this is going to get -- we’re going to get more formats that are more interactive and immersive and you’re going to get them in your feeds
tweet
In this week’s newsletter:
🏭 $TSLA: I think if we don’t do the Tesla Terafab, we’re going to be limited by supplier output of chips. And I think maybe memory is an even bigger limiter than AI logic
🛍️ $MA: There is question on how the consumer was affected or not by some of the tariff changes that we’ve seen last year. And that doesn’t show up in our data either. So it’s not coming through
🤝 $GS: I think 2026 will be an even better dealmaking year. 2026 could be one of the best M&A years ever. I can see through our backlog and our activity levels and our client dialogues a very robust environment for dealmaking
👩💻 $RHI: While perspectives on medium- to long-term structural impact of AI on the labor market vary greatly, most of theevidence suggests a ne gligible impact so far on our areas of employment, particularly among small businesses
📱 $META: I don’t think that video is the ultimate kind of final format. I just -- I think that this is going to get -- we’re going to get more formats that are more interactive and immersive and you’re going to get them in your feeds
tweet
Javier Blas
In the least surprising news, China commissioned in 2025 the most coal-fired power stations in a decade.
(~78 GW of new coal capacity, equal to twice the UK total electricity demand)
On top, Chinese companies filled a record high number of proposals to build future coal plants.
tweet
In the least surprising news, China commissioned in 2025 the most coal-fired power stations in a decade.
(~78 GW of new coal capacity, equal to twice the UK total electricity demand)
On top, Chinese companies filled a record high number of proposals to build future coal plants.
tweet
Jukan
Funda AI has once again dropped an astonishing insight.
The argument is that the rise in memory prices actually ends up benefiting Intel.
Thanks to the sharp increase in memory prices, Intel can now confidently redirect wafers originally intended for consumer CPUs toward server CPU production, ultimately leading to higher revenue and profits.
The link is below:
$INTC
tweet
Funda AI has once again dropped an astonishing insight.
The argument is that the rise in memory prices actually ends up benefiting Intel.
Thanks to the sharp increase in memory prices, Intel can now confidently redirect wafers originally intended for consumer CPUs toward server CPU production, ultimately leading to higher revenue and profits.
The link is below:
$INTC
tweet
Javier Blas
RT @BrewerEricM: When it comes to US Iran policy, the last few weeks have featured lots of comparisons with Venezuela, as well as last June’s surprise attack amid ongoing diplomacy. Fair. But we should also think about—and hope to avoid—another comparison: North Korea 2018. After a summit and a vague commitment by Kim to denuclearize, Trump declared the nuclear problem solved.
tweet
RT @BrewerEricM: When it comes to US Iran policy, the last few weeks have featured lots of comparisons with Venezuela, as well as last June’s surprise attack amid ongoing diplomacy. Fair. But we should also think about—and hope to avoid—another comparison: North Korea 2018. After a summit and a vague commitment by Kim to denuclearize, Trump declared the nuclear problem solved.
tweet
The Transcript
RT @TheTranscript_: $META CFO: New U.S. tax law brings 2026 cash tax savings
“We expect substantial cash tax savings from the new U.S. tax laws given the significant investments that we’re making in infrastructure and R&D.”
tweet
RT @TheTranscript_: $META CFO: New U.S. tax law brings 2026 cash tax savings
“We expect substantial cash tax savings from the new U.S. tax laws given the significant investments that we’re making in infrastructure and R&D.”
tweet